Add new SentenceTransformer model

45a4a40 verified 25 days ago

90.2 kB

	---
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- dense
	- generated_from_trainer
	- dataset_size:17793
	- loss:MultipleNegativesRankingLoss
	base_model: allenai/specter2_base
	widget:
	- source_sentence: Achieving high cell transfection efficiency is essential for various
	cell types in numerous disease applications. However, the efficient introduction
	of genes into natural killer (NK) cells remains a challenge. In this study, we
	proposed a design strategy for delivering exogenous genes into the NK cell line,
	NK-92, using a modified non-viral gene transfection method. Calcium phosphate/DNA
	nanoparticles (pDNA-CaP NPs) were prepared using co-precipitation methods and
	combined with low-voltage pulse electroporation to facilitate NK-92 transfection.
	The results demonstrated that the developed pDNA-CaP NPs exhibited a uniform diameter
	of approximately 393.9 nm, a DNA entrapment efficiency of 65.8%, and a loading
	capacity of 15.9%. Furthermore, at three days post-transfection, both the transfection
	efficiency and cell viability of NK-92 were significantly improved compared to
	standalone plasmid DNA (pDNA) electroporation or solely relying on the endocytosis
	pathway of pDNA-CaP NPs. This study provides valuable insights into a novel approach
	that combines calcium phosphate nanoparticles with low-voltage electroporation
	for gene delivery into NK-92 cells, offering potential advancements in cell therapy.
	sentences:
	- ZEISS Airyscan is an advanced imaging technology that enhances traditional confocal
	microscopy by using a 32-channel detector to capture more light with higher resolution
	and sensitivity. Unlike standard confocal systems that rely on a single pinhole,
	Airyscan collects the entire Airy disk pattern and reconstructs images for super-resolution
	clarityâ down to 120 nm laterally. This results in significantly improved signal-to-noise
	ratio and reduced photodamage, making it ideal for detailed imaging of live cells
	and biological samples. It's compatible with ZEISS LSM systems like the LSM 880
	and 900, offering researchers a powerful tool for high-precision fluorescence
	microscopy
	- 'the zeiss lsm 900 with airyscan 2 is a compact confocal microscope designed for
	high-quality imaging and intelligent analysis of biological samples, supporting
	a wide range of research applications from resolving nanoscale structures to observing
	dynamic processes in living systems. its key technologies enable researchers to
	acquire detailed and quantitative data while maintaining sample integrity and
	maximizing experimental efficiency. key research and application areas: - super-resolution
	imaging: investigating the ultrastructure of biological specimens by achieving
	resolution beyond the diffraction limit (down to 90 nm laterally) through airyscan
	2 and joint deconvolution (jdcv). this allows for the detailed visualization of
	cellular and molecular architecture. - gentle live cell imaging: studying biological
	processes in living organisms with minimized phototoxicity and photobleaching
	due to optimized components and sensitive detectors. this facilitates long-term
	observation of cellular dynamics and molecular interactions without disturbing
	the sample. - fast multiplex imaging: acquiring data from multiple fluorescent
	labels or large fields of view rapidly using multiplex modes of airyscan 2, enabling
	the study of dynamic events and efficient screening of samples. - enhanced confocal
	imaging: improving the signal-to-noise ratio and resolution of standard confocal
	imaging through lsm plus, allowing for better data quality in multi-color and
	live cell experiments with minimal user interaction. - molecular dynamics analysis:
	determining molecular concentration, diffusion, and flow in living samples using
	the zeiss dynamics profiler, which leverages the unique capabilities of the airyscan
	2 detector for advanced spatial cross-correlation analyses. this enables the study
	of molecular behavior in various biological contexts, including flow in microfluidic
	systems and blood vessels and asymmetric diffusion in cellular condensates. -
	automated and reproducible experiments: streamlining complex imaging workflows
	with zen microscopy software, including features like ai sample finder for rapid
	region of interest identification and smart setup for automated application of
	optimal imaging settings. the experiment designer module allows for the creation
	of sophisticated, repeatable imaging routines. - correlative microscopy: integrating
	data from different imaging modalities and sources using zen connect to provide
	a comprehensive understanding of the sample, from overview to high-resolution
	details, including the possibility of correlative cryo microscopy workflows. typical
	sample types: - cultured cells and cell lines: for studying subcellular structures,
	dynamics, and responses to stimuli. - tissues and tissue sections: to investigate
	cellular organization, protein localization, and interactions within a complex
	environment. - small model organisms and embryos: such as drosophila and zebrafish
	for in vivo studies of development, physiology, and disease. - organoids and 3d
	cell cultures: for studying tissue architecture and development in vitro. - plant
	samples: such as pollen grains, for investigating cellular structures. - samples
	requiring correlative microscopy: like yeast cells for cryo-em workflows. - microfluidic
	systems: for controlled studies of fluid dynamics and molecular flow. commonly
	performed tasks: - confocal laser scanning microscopy: obtaining high-resolution
	optical sections of samples to visualize internal structures and create 3d reconstructions.
	- super-resolution imaging with airyscan: resolving nanoscale details beyond the
	limits of conventional light microscopy. - live cell imaging: capturing time-lapse
	sequences of living samples to study dynamic biological processes. - multi-color
	fluorescence imaging: simultaneously detecting multiple fluorescent probes to
	study the co-localization and interactions of different molecules. - spectral
	imaging and unmixing: separating the signals of spectrally overlapping fluorophores
	for accurate multi-target analysis. - quantitative image analysis: extracting
	meaningful data from images, including measurements of intensity, area, distance,
	and co-localization, using tools within zen software and the bio apps toolkit.
	- automated sample identification and imaging: utilizing ai sample finder to quickly
	locate and image regions of interest on various sample carriers. - analysis of
	molecular dynamics: measuring parameters such as diffusion coefficients, flow
	speeds, and molecular concentrations using the dynamics profiler. - creating 3d
	and 4d visualizations: reconstructing volumetric datasets and generating animations
	to understand spatial and temporal relationships within samples. - correlating
	light and electron microscopy data: combining functional light microscopy data
	with ultrastructural details from electron microscopy. - performing bleaching
	experiments: such as frap, to study molecular mobility within cellular compartments
	(although frap is mentioned in the software features , no specific application
	examples are provided in the excerpts). - tiling and multi-position imaging: acquiring
	large datasets by automatically imaging and stitching together multiple adjacent
	fields of view or imaging multiple regions of interest.'
	- 'the zeiss sigma family of field emission scanning electron microscopes (fe-sems)
	offers versatile solutions for high-quality imaging and advanced analytical microscopy
	across a multitude of scientific and industrial domains. these instruments are
	engineered for reliable, high-end nano-analysis, combining fe-sem technology with
	an intuitive user experience to enhance productivity. key research and application
	areas: - advancing materials science: facilitating the development and understanding
	of novel materials by enabling the investigation of micro- and nanoscale structures.
	this includes characterizing metals, alloys, polymers, catalysts, and coatings
	for various applications such as electronics and energy. - driving innovation
	in nanoscience and nanomaterials: providing capabilities for the analysis of nanoparticles,
	thin films, 2d materials (like graphene and mos2), and other nanostructures to
	understand their properties and potential applications. - supporting energy research:
	enabling the study of materials and devices relevant to energy storage and conversion,
	such as battery components, to improve their performance and longevity. - enabling
	life sciences investigations: allowing for the exploration of the ultrastructural
	details of biological samples, including cells, tissues, spores, and diatoms,
	often utilizing low voltage to minimize beam damage. - contributing to geosciences
	and natural resources: supporting the characterization of rocks, ores, and minerals
	for improved understanding, processing, and modeling in geology and related fields.
	- ensuring quality in industrial applications: serving as a vital tool for failure
	analysis of mechanical, optical, and electronic components, as well as for quality
	inspection of particles and materials to meet defined standards. typical sample
	types: - a wide variety of materials including metals, ceramics, polymers, composites,
	thin films, and coatings. - nanomaterials such as nanoparticles, nanotubes, nanowires,
	and 2d crystals. - biological specimens encompassing cells, tissues, bacteria,
	fungi (e.g., spores), and diatoms. - geological samples including rocks, minerals,
	ores, and thin sections. - particulates for quality inspection and technical cleanliness
	analysis. - non-conductive samples such as polymers, biological tissues, and ceramics,
	often analyzed without coating using variable pressure modes. - beam-sensitive
	samples like biological materials and some nanomaterials, which can be imaged
	at low voltages to prevent damage. commonly performed tasks: - high-resolution
	imaging of sample surfaces and internal structures, often at low accelerating
	voltages (e.g., 1 kv and below) to enhance resolution and contrast, especially
	on challenging samples. - material contrast imaging to visualize different phases
	or compositions within a sample using backscattered electron (bse) detectors.
	- elemental analysis and mapping using energy dispersive x-ray spectroscopy (eds)
	to determine the chemical composition and distribution of elements in a sample.
	- variable pressure (vp) imaging and analysis of non-conductive and outgassing
	samples without the need for conductive coatings, often utilizing nanovp lite
	mode to minimize the skirt effect and enhance image quality and analytical precision.
	- crystallographic orientation imaging using techniques like electron backscatter
	diffraction (ebsd) to study the microstructure of crystalline materials. - transmission
	imaging of thin samples using scanning transmission electron microscopy (stem)
	with dedicated detectors. - correlative microscopy by combining sem imaging with
	other techniques such as raman spectroscopy (rise microscopy) to gain complementary
	chemical and structural information. - automated workflows for imaging, analysis
	(e.g., particle analysis, non-metallic inclusion analysis), and in situ experiments
	to increase productivity and ensure reproducible results. - surface topography
	and 3d reconstruction using techniques like the annular bse detector (absd) and
	dedicated software to obtain quantitative information about the sample surface.
	- in situ experiments such as heating and tensile testing within the sem chamber
	to observe material behavior under controlled conditions. - failure analysis to
	investigate fractures, defects, and corrosion in various materials and components.
	- particle analysis for technical cleanliness and material characterization, including
	automated detection, measurement, counting, and classification of particles based
	on morphology and elemental composition. - quantitative mineralogy using automated
	sem and eds to classify mineral phases based on their chemical composition and
	provide detailed information on their properties.'
	- source_sentence: Spinally projecting serotonergic neurons play a key role in controlling
	pain sensitivity and can either increase or decrease nociception depending on
	physiological context. It is currently unknown how serotonergic neurons mediate
	these opposing effects. Utilizing virus-based strategies and Tph2-Cre transgenic
	mice, we identified two anatomically separated populations of serotonergic hindbrain
	neurons located in the lateral paragigantocellularis (LPGi) and the medial hindbrain,
	which respectively innervate the superficial and deep spinal dorsal horn and have
	contrasting effects on sensory perception. Our tracing experiments revealed that
	serotonergic neurons of the LPGi were much more susceptible to transduction with
	spinally injected AAV2retro vectors than medial hindbrain serotonergic neurons.
	Taking advantage of this difference, we employed intersectional chemogenetic approaches
	to demonstrate that activation of the LPGi serotonergic projections decreases
	thermal sensitivity, whereas activation of medial serotonergic neurons increases
	sensitivity to mechanical von Frey stimulation. Together these results suggest
	that there are functionally distinct classes of serotonergic hindbrain neurons
	that differ in their anatomical location in the hindbrain, their postsynaptic
	targets in the spinal cord, and their impact on nociceptive sensitivity. The LPGi
	neurons that give rise to rather global and bilateral projections throughout the
	rostrocaudal extent of the spinal cord appear to be ideally poised to contribute
	to widespread systemic pain control.
	sentences:
	- 'the zeiss stemi 508 is an apochromatic stereo microscope with an 8:1 zoom range,
	designed for high-contrast, color-accurate three-dimensional observation and documentation
	of diverse samples. its ergonomic design and robust mechanics support demanding
	applications in laboratory and industrial settings. key research and application
	areas: - biological research: suitable for observing the development and growth
	of model organisms like spider crabs, chicken, mouse, or zebrafish, including
	the evaluation, sorting, selection, or dissection of eggs, larvae, or embryos.
	it is also used in botany to observe changes in plant organs, diseases, and root
	development, in entomology for insect observation, documentation, and identification,
	in marine biology to study the life and reproduction of fish, and in parasitology
	for detecting and identifying the spread of parasites. the microscope is valuable
	for forensic analysis of ammunition parts, tool marks, documents, fibers, coatings,
	glass, textiles, or hair, and in art restoration for analyzing and conserving
	artworks layer by layer. - industrial inspection and quality control: applied
	in printed circuit board (pcb) inspection to check for contact quality, wiring,
	residues, and solder joint faults. it is also used in failure search and analysis
	to identify reasons for faulty circuits, in the diamond industry for quality evaluation
	and impurity detection, and in the assembly of small, high-precision components
	in medical devices, sensor manufacturing, and the clocks and watches industry.
	the microscope is also relevant for evaluating the surface quality in printing
	and engraving and for inspecting minted coins and medals. - geology and paleontology:
	used for collecting and investigating assemblages of fossil foraminifera to determine
	rock age. typical sample types: - biological specimens: eggs, larvae, embryos
	of various organisms, plant organs, insects, fish, parasites, tissues, hairs,
	fibers. - industrial components: printed circuit boards, electronic contacts,
	wiring, solder joints, metal parts, small mechanical components (e.g., in medical
	devices, sensors, watches), optical fibers, diamonds, paper, engravings, minted
	coins, medals. - forensic evidence: ammunition parts, tool marks, documents, fibers,
	coatings, glass, textiles, hair. - artworks: paintings, sculptures, various materials
	used in art. - geological samples: fossil foraminifera. - transparent and semi-transparent
	materials: may be analyzed using transmitted light techniques. commonly performed
	tasks: - detailed observation and examination: utilizing the 8:1 zoom to transition
	from large overviews (up to 122 mm object field) to high magnification (up to
	50x with basic system, or 2x to 250x with interchangeable optics) for minute structural
	analysis. the apochromatic correction ensures distortion-free and color-fringe-free
	imaging. - three-dimensional viewing: leveraging the greenough stereoscopic design
	with twin body tubes inclined by 11deg to achieve a strong spatial impression
	and depth perception, essential for understanding sample morphology. the precise
	zoom adjustment maintains a well-balanced 3d impression for relaxed viewing. -
	specimen manipulation and preparation: the long working distances (up to 287 mm
	with specific optics) provide ample space for easy specimen handling, dissection,
	and manipulation using tools or micromanipulators. - illumination and contrast
	optimization: employing a variety of reflected and transmitted light techniques,
	including brightfield, darkfield, polarization, and oblique illumination, facilitated
	by interchangeable led illuminators (spot, double spot, segmentable ringlight)
	and fiber optic light sources. these techniques enhance the visibility of specific
	features like surface structures, defects, or internal details in diverse sample
	types. - image acquisition and documentation: integrating with zeiss axiocam cameras
	and other digital cameras via interchangeable camera adapters to capture high-resolution
	images and videos for documentation, archiving, and sharing. software like zen
	lite and labscope facilitates image processing and analysis. - ergonomic operation:
	maintaining a comfortable posture during extended use due to the low 35deg viewing
	angle. optional accessories like hand rests further enhance user comfort. - reproducible
	settings: utilizing the optional zoom click stops to easily reproduce magnification
	levels for consistent observation and documentation. the memory function in stand
	m led allows storing and recalling illumination settings. - customizable configurations:
	adapting the microscope to specific application needs by choosing from a wide
	range of stands, interchangeable optics (eyepieces and front optics), and illumination
	systems. various stages (gliding, tilting, rotating polarization) enable precise
	specimen positioning.'
	- 'the zeiss lsm 990 is a versatile confocal microscope system offering a wide range
	of multimodal imaging options for advanced biological research. its capabilities
	extend beyond traditional confocal microscopy, enabling intricate investigations
	into cellular structures, molecular dynamics, and physiological processes in various
	biological samples. key research and application areas: - high-resolution imaging
	of biological structures: investigating subcellular details and resolving fine
	structures down to 90 nm using super-resolution techniques like airyscan. this
	allows for the detailed study of components like the synaptonemal complex and
	sperm flagella. - live cell imaging and dynamics: observing dynamic biological
	processes in living cells and organisms, including molecular dynamics, protein
	interactions, flow in microfluidic systems, and developmental processes. the system
	supports high-speed volume acquisition up to 80 volumes per second for capturing
	fast events like the beating of a zebrafish heart. - advanced spectral imaging
	and multiplexing: identifying and separating multiple fluorescent labels across
	a broad emission wavelength range (380 to 900 nm), enabling the simultaneous study
	of over 10 labels in a single scan. this facilitates in-depth understanding of
	spatial biology through techniques like lambda scans and spectral unmixing. -
	deep tissue imaging: recovering information from deep within tissues, organoids,
	and spheroids using multiphoton excitation (690 - 1300 nm). this is crucial for
	studying complex biological systems in a more native context. - molecular dynamics
	and interaction studies: gaining insights into protein concentrations, movement,
	and interactions using techniques like fluorescence correlation spectroscopy (fcs)
	and spectral rics. the system also supports fluorescence lifetime imaging microscopy
	(flim) and fluorescence resonance energy transfer (fret) to investigate physiological
	parameters and molecular proximity. - volumetric imaging of living organisms:
	studying the dynamics of entire living organisms and tissues in 3d over time using
	lightfield 4d microscopy, capturing up to 80 volumes per second. this is beneficial
	for visualizing development and other dynamic processes in intact animals and
	organoids. - correlative microscopy: combining light microscopy with electron
	microscopy under cryogenic conditions to study cellular structures in a near-to-native
	state. - imaging of cleared samples: achieving increased optical penetration depth
	in cleared biological samples like brains, organoids, and spheroids, allowing
	for imaging up to 5.6 mm deep with specialized objectives. typical sample types:
	- live cells and cell cultures: including various cell lines and primary cells.
	- tissues and tissue sections: from various organs and organisms, both fixed and
	live. - whole organisms and embryos: such as zebrafish larvae and drosophila pupae.
	- organoids and spheroids: including 3d cell cultures and tissue models. - cleared
	biological samples: such as whole mouse brains, tissue sections, organoids, and
	spheroids rendered transparent for deep imaging. - microfluidic systems: for studying
	flow and molecular dynamics in controlled environments. - yeast cells: for advanced
	spectral multiplexing experiments. commonly performed tasks: - confocal microscopy:
	high-resolution optical sectioning of various samples. - super-resolution imaging:
	resolving structures beyond the diffraction limit down to 90 nm. - live imaging:
	capturing dynamic events in living samples over time. - volumetric imaging: acquiring
	3d datasets of biological samples. - spectral imaging and unmixing: separating
	and analyzing the emission spectra of multiple fluorescent labels. - multiphoton
	microscopy: deep tissue imaging using longer excitation wavelengths. - fluorescence
	correlation spectroscopy (fcs) and spectral rics: investigating molecular concentrations,
	diffusion, and interactions. - fluorescence lifetime imaging microscopy (flim):
	analyzing fluorescence decay to gain information on molecular interactions and
	environmental parameters. - fluorescence resonance energy transfer (fret): studying
	protein interaction and distance. - fluorescence recovery after photobleaching
	(frap) and photomanipulation: investigating molecular and cellular dynamics through
	targeted laser manipulation. - image analysis and processing: utilizing software
	like zen and arivis pro for visualization, segmentation, tracking, and quantification
	of imaging data. - correlative light and electron microscopy (clem): combining
	light and electron microscopy data for comprehensive ultrastructural analysis.
	- imaging of cleared samples: deep imaging of transparent biological specimens
	for 3d structural analysis.'
	- 'the zeiss lsm 910 is a compact confocal microscope designed for innovative imaging
	and smart analysis, enabling a broad spectrum of biological research applications.
	its core capabilities facilitate the detailed visualization and analysis of diverse
	biological specimens, ranging from subcellular structures to dynamic processes
	in living organisms. key research and application areas: - high-resolution structural
	imaging: achieving super-resolution down to 90 nm laterally using airyscan technology
	to resolve fine details of cellular and molecular structures. this enables the
	investigation of intricate biological organization. - live cell and high-speed
	imaging: capturing dynamic processes in living samples with high temporal resolution,
	including 4d imaging at up to 80 volumes per second using lightfield 4d. this
	allows for the study of rapid biological events such as zebrafish heartbeats and
	intracellular movements. - advanced spectral analysis: employing spectral flexibility
	with nanometer precision for multi-color imaging and efficient spectral unmixing
	of multiple fluorescent labels, facilitating the detailed study of spatial biology.
	- gentle imaging for sensitive samples: utilizing an efficient beam path and sensitive
	detectors (gaasp-pmts and ma-pmts) to achieve high signal-to-noise ratios while
	minimizing phototoxicity, crucial for long-term live cell imaging. - quantitative
	molecular dynamics studies: investigating molecular concentration, diffusion,
	and flow dynamics in living samples using the dynamics profiler based on airyscan.
	this allows for the analysis of molecular behavior in various biological contexts.
	- deep tissue imaging with clearing: integrating with clearing techniques and
	specialized objectives to significantly increase optical penetration depth in
	samples like brains, organoids, and tissues, enabling the visualization of structures
	in deeper layers. - correlative cryo microscopy: facilitating workflows that combine
	light and electron microscopy under cryogenic conditions to study cellular structures
	in a near-to-native state, bridging the gap between functional and ultrastructural
	information. typical sample types: - cells and cell cultures: including various
	cell lines for studying subcellular structures and dynamics. - tissues and tissue
	sections: allowing for the investigation of cellular organization and molecular
	distribution within complex environments. - organoids and spheroids: enabling
	the study of 3d tissue models and their development using various imaging modalities,
	including high-speed volume acquisition. - whole organisms and embryos: such as
	zebrafish embryos, for observing developmental processes and physiological functions
	in vivo with high spatiotemporal resolution. - cleared biological samples: including
	whole brains, tissue sections, organoids, and spheroids made transparent to enable
	deep optical imaging. - microfluidic devices: for controlled studies of flow and
	molecular dynamics. - plant tissues: such as arabidopsis thaliana stems, for investigating
	protein behavior in response to environmental stimuli. commonly performed tasks:
	- confocal imaging: high-resolution optical sectioning to visualize specific planes
	within a sample and generate 3d reconstructions. - super-resolution microscopy:
	resolving structures beyond the diffraction limit to visualize nanoscale details
	of cellular components. - live cell imaging: capturing time-series data of living
	cells and organisms to study dynamic processes and cellular behaviors over time.
	- high-speed volumetric imaging: acquiring 3d datasets at rapid frame rates to
	visualize fast biological events in their entirety. - spectral imaging and unmixing:
	separating the contributions of multiple fluorescent probes based on their emission
	spectra to allow for simultaneous multi-target analysis. - fluorescence recovery
	after photobleaching (frap): investigating molecular mobility and dynamics within
	cellular compartments. - fluorescence correlation spectroscopy (fcs) and dynamics
	profiling: measuring molecular concentrations, diffusion coefficients, and flow
	velocities in living samples. - image processing and analysis: utilizing software
	tools like zen and arivis pro for image enhancement, quantification, segmentation,
	tracking, and 3d visualization of complex datasets. - correlative light and electron
	microscopy (clem): combining light microscopy for functional identification with
	electron microscopy for ultrastructural details. - imaging of large volumes and
	tiled acquisitions: acquiring data from large samples or multiple regions of interest
	and stitching them together for comprehensive analysis. - automated imaging workflows:
	setting up and executing complex imaging experiments with automation features
	for reproducible data acquisition. - advanced image analysis using ai: employing
	artificial intelligence-assisted features for sample finding, setup optimization,
	and image analysis.'
	- source_sentence: In Arabidopsis thaliana, the asymmetric cell division (ACD) of
	the zygote gives rise to the embryo proper and an extraembryonic suspensor, respectively.
	This process is controlled by the ERECTA-YODA-MPK3/6 receptor kinase-MAP kinase-signaling
	pathway, which also orchestrates ACDs in the epidermis. In this context, the bHLH
	transcription factor ICE1/SCRM is negatively controlled by MPK3/6-directed phosphorylation.
	However, it is unknown whether this regulatory module is similarly involved in
	the zygotic ACD. We investigated the function of SCRM in zygote polarization by
	analyzing the effect of loss-of-function alleles and variants that cannot be phosphorylated
	by MPK3/6, protein accumulation, and target gene expression. Our results show
	that SCRM has a critical function in zygote polarization and acts in parallel
	with the known MPK3/6 target WRKY2 in activating WOX8. Our work further demonstrates
	that SCRM activity in the early embryo is positively controlled by MPK3/6-mediated
	phosphorylation. Therefore, the effect of MAP kinase-directed phosphorylation
	of the same target protein fundamentally differs between the embryo and the epidermis,
	shedding light on cell type-specific, differential gene regulation by common signaling
	pathways.
	sentences:
	- 'the zeiss evo family of scanning electron microscopes offers a modular and versatile
	platform for a wide range of scientific and industrial investigations, combining
	high-performance imaging and analysis with intuitive operation for users of varying
	experience levels. key research and application areas: - materials science: characterizing
	the morphology, structure, and composition of diverse materials, including metals,
	composites, polymers, ceramics, and coatings, for research and development. this
	includes investigating surface structures, fractures, inclusions, and grain boundaries.
	the evo supports advanced material analysis through techniques like energy dispersive
	spectroscopy (eds) and electron backscatter diffraction (ebsd). - life sciences:
	enabling the examination of biological specimens in their native or near-native
	hydrated states using variable and extended pressure modes. applications include
	imaging cells, tissues, plants, and microorganisms for structural and morphological
	studies. the system facilitates correlative light and electron microscopy for
	comprehensive biological investigations. - industrial quality assurance and failure
	analysis: providing solutions for routine inspection, quality control, and failure
	analysis across various industries. this includes cleanliness inspection, morphological
	and chemical analysis of particles, and the examination of electronic components.
	automated workflows and reporting tools enhance efficiency in industrial settings.
	- semiconductors and electronics: supporting the visual inspection and analysis
	of electronic components, integrated circuits, and mems devices. the evo''s capabilities
	include high-contrast imaging of non-conductive semiconductor materials and cross-sectional
	failure analysis. - raw materials and earth sciences: facilitating the morphological,
	mineralogical, and compositional analysis of geological samples and raw chemicals.
	this includes imaging core samples and performing automated mineral analysis for
	resource characterization. - forensics: providing tools for the analysis of forensic
	evidence such as gunshot residue, paint, glass, fibers, and biological traces
	with minimal sample preparation. the system supports consistent imaging and high-throughput
	chemical analysis. typical sample types: - conductive materials: metals, alloys,
	and coated samples examined under high vacuum. - non-conductive materials: polymers,
	ceramics, composites, uncoated geological samples, and biological tissues imaged
	using variable pressure modes to neutralize charging. - hydrated and contaminated
	samples: biological specimens, wet materials, and uncleaned industrial parts imaged
	in extended pressure mode with water vapor to maintain their native state and
	prevent contamination of the electron column. - large and challenging samples:
	industrial parts and geological cores accommodated by various chamber sizes and
	stage options, with weight capacities up to 5 kg and dimensions up to 300 mm wide
	and 210 mm high. - coated and uncoated samples: the evo offers imaging capabilities
	for both prepared and unprepared samples, catering to diverse analytical needs.
	commonly performed tasks: - high-resolution imaging: acquiring detailed images
	of sample surfaces and microstructures using secondary electrons (se) and backscattered
	electrons (bse) detectors in various vacuum modes. the lab6 emitter enhances resolution
	and contrast. - elemental analysis: determining the chemical composition of specimens
	using integrated energy dispersive spectroscopy (eds) systems. - automated workflows:
	implementing predefined or user-defined automated routines for image acquisition,
	particle analysis, and routine inspections, enhancing throughput and reproducibility.
	- variable pressure imaging: investigating non-conductive samples without coating
	by utilizing gas ionization to dissipate charge build-up. - extended pressure
	imaging: examining hydrated and sensitive samples in a water vapor environment
	to preserve their natural state and prevent artifacts. - correlative microscopy:
	combining data from the evo with light microscopes or other analytical techniques
	to gain multi-modal insights into samples. - particle analysis: automatically
	detecting, characterizing, and classifying particles based on morphology and chemical
	composition for applications in industrial cleanliness, material analysis, and
	environmental monitoring. - automated mineralogy: performing quantitative mineral
	analysis on geological samples for geometallurgy, ore characterization, and reservoir
	analysis. - beam deceleration imaging: enhancing surface sensitivity and reducing
	charging artifacts on delicate non-conductive samples by controlling the electron
	landing energy. - navigation and sample management: using navigation cameras and
	software tools to easily locate regions of interest and manage large sample arrays.
	- data management and reporting: utilizing software like zeiss zen core for image
	processing, analysis, data connectivity, and generating reports, including options
	for gxp compliance in regulated industries.'
	- 'the zeiss crossbeam family of focused ion beam scanning electron microscopes
	(fib-sems) provides a powerful platform for high-throughput 3d analysis and advanced
	sample preparation across diverse scientific and industrial fields. combining
	the high-resolution imaging of a field emission sem with the precise processing
	of a next-generation fib, crossbeam instruments enable intricate manipulation
	and detailed characterization of materials. key research and application areas:
	- high-resolution imaging and surface analysis: - applications: obtaining detailed
	2d and 3d images of various samples, including conductive and non-conductive specimens.
	investigating surface details and material contrast. - sample types: a wide range
	of materials, including metals, ceramics, polymers, biological samples, and electronic
	components. - commonly performed tasks: high-resolution sem imaging at various
	accelerating voltages, including low voltage for surface sensitivity and beam-sensitive
	samples. utilizing inlens detectors (se and esb) for topographical and material
	contrast. imaging non-conductive samples using variable pressure or local charge
	compensation. large area mapping. surface sensitive imaging using tandem decel.
	- 3d volume analysis and tomography: - applications: reconstructing the 3d microstructure
	and composition of materials. morphological analysis of biological samples. correlative
	multi-scale, multi-modal imaging using atlas 5. - sample types: diverse materials
	requiring volumetric analysis, including solid oxide fuel cells, metallic alloys,
	biological tissues (cells, organisms, brain sections), and geological samples.
	- commonly performed tasks: serial sectioning using the fib for 3d reconstruction.
	automated tomography data acquisition. 3d eds and 3d ebsd analysis during tomography
	runs. precise and reliable results with leading isotropic voxel size. tracking
	voxel sizes and automated image quality control. - focused ion beam milling and
	nanofabrication: - applications: precise cross-sectioning to reveal subsurface
	information. preparation of specimens for further analysis (e.g., tem lamellae).
	nanopatterning and creation of micro/nanostructures. fast material removal for
	accessing buried structures. - sample types: wide variety of materials requiring
	targeted modification, including semiconductors, metals, ceramics, polymers, and
	biological samples. - commonly performed tasks: high-precision milling with the
	ion-sculptor fib column, minimizing sample damage. fast and precise material removal
	with high beam currents (up to 100 na). low voltage fib performance for delicate
	samples. automated milling of cross-sections and user-defined patterns. fastmill
	strategy for enhanced milling speed. utilizing a femtosecond laser for rapid ablation
	of large volumes to access deeply buried regions. - tem sample preparation: -
	applications: preparing high-quality, ultra-thin lamellae for transmission electron
	microscopy (tem) and scanning transmission electron microscopy (stem) analysis.
	preparing batches of tem lamellae automatically. - sample types: diverse materials
	requiring tem analysis, including semiconductors, metals, polymers, and biological
	tissues. - commonly performed tasks: guided, semi-automated tem lamella preparation
	workflows. automated chunk milling, in situ lift-out, and thinning. utilizing
	the low voltage performance of the ion-sculptor fib for high-quality lamellae
	with minimal amorphization. live monitoring of lamella thinning using sem. quantitative
	thickness determination with smartepd. preparation of ultra-thin lamellae using
	the x2-holder for challenging samples. fully automated tem preparation with crossbeam
	550 samplefab. - advanced analytical techniques: - applications: analyzing the
	elemental and isotopic composition of surfaces. performing analytical mapping
	and depth profiling. correlating structural and chemical information. - sample
	types: various solid surfaces requiring detailed compositional analysis, including
	batteries, polymers, and semiconductors. - commonly performed tasks: time-of-flight
	secondary ion mass spectrometry (tof-sims) for parallel detection of atomic and
	molecular ions. 3d eds and ebsd analysis integrated with tomography. the zeiss
	crossbeam family offers modularity and customization options, including various
	detectors, gas injection systems (gis), manipulators, and software packages like
	atlas 5, enabling researchers to tailor the instrument to their specific application
	needs and achieve high-impact results. the gemini electron optics ensure excellent
	image quality and long-term stability, while the ion-sculptor fib column provides
	superior processing capabilities with minimal sample damage.'
	- ZEISS Airyscan is an advanced imaging technology that enhances traditional confocal
	microscopy by using a 32-channel detector to capture more light with higher resolution
	and sensitivity. Unlike standard confocal systems that rely on a single pinhole,
	Airyscan collects the entire Airy disk pattern and reconstructs images for super-resolution
	clarityâ down to 120 nm laterally. This results in significantly improved signal-to-noise
	ratio and reduced photodamage, making it ideal for detailed imaging of live cells
	and biological samples. It's compatible with ZEISS LSM systems like the LSM 880
	and 900, offering researchers a powerful tool for high-precision fluorescence
	microscopy
	- source_sentence: 'The identity and source of flexible, semi-transparent, vascular-like
	components recovered from non-avian dinosaur bone are debated, because: (1) such
	preservation is not predicted by degradation models; (2) taphonomic mechanisms
	for this type of preservation are not well defined; and (3) although support for
	molecular endogeneity has been demonstrated in select specimens, comparable data
	are lacking on a broader scale. Here, we use a suite of micromorphological and
	molecular techniques to examine vessel-like material recovered from the skeletal
	remains of six non-avian dinosaurs, representing different taxa, depositional
	environments and geological ages, and we compare the data obtained from our analyses
	against vessels liberated from extant ostrich bone. The results of this in-depth,
	multi-faceted study present strong support for endogeneity of the fossil-derived
	vessels, although we also detect evidence of invasive microorganisms.'
	sentences:
	- 'ZEISS ZEN is a comprehensive microscopy software platform designed to streamline
	the entire imaging workflow from acquisition to analysis and data management.
	It offers a modular structure with specialized toolkits for image acquisition,
	processing, and analysis, allowing users to tailor the software to their specific
	experimental needs. ZEN supports advanced features such as smart microscopy with
	feedback experiments, GPU-powered 3D visualization, and machine learning-based
	image analysis, facilitating efficient handling of complex, multidimensional datasets.
	The software''s intuitive interface ensures ease of use across various microscopy
	modalities, especially in light microscopy, making it suitable for both routine
	laboratory tasks and advanced research applications. '
	- 'ZEISS ZEN is a comprehensive microscopy software platform designed to streamline
	the entire imaging workflow from acquisition to analysis and data management.
	It offers a modular structure with specialized toolkits for image acquisition,
	processing, and analysis, allowing users to tailor the software to their specific
	experimental needs. ZEN supports advanced features such as smart microscopy with
	feedback experiments, GPU-powered 3D visualization, and machine learning-based
	image analysis, facilitating efficient handling of complex, multidimensional datasets.
	The software''s intuitive interface ensures ease of use across various microscopy
	modalities, especially in light microscopy, making it suitable for both routine
	laboratory tasks and advanced research applications. '
	- 'the zeiss lsm 910 is a compact confocal microscope designed for innovative imaging
	and smart analysis, enabling a broad spectrum of biological research applications.
	its core capabilities facilitate the detailed visualization and analysis of diverse
	biological specimens, ranging from subcellular structures to dynamic processes
	in living organisms. key research and application areas: - high-resolution structural
	imaging: achieving super-resolution down to 90 nm laterally using airyscan technology
	to resolve fine details of cellular and molecular structures. this enables the
	investigation of intricate biological organization. - live cell and high-speed
	imaging: capturing dynamic processes in living samples with high temporal resolution,
	including 4d imaging at up to 80 volumes per second using lightfield 4d. this
	allows for the study of rapid biological events such as zebrafish heartbeats and
	intracellular movements. - advanced spectral analysis: employing spectral flexibility
	with nanometer precision for multi-color imaging and efficient spectral unmixing
	of multiple fluorescent labels, facilitating the detailed study of spatial biology.
	- gentle imaging for sensitive samples: utilizing an efficient beam path and sensitive
	detectors (gaasp-pmts and ma-pmts) to achieve high signal-to-noise ratios while
	minimizing phototoxicity, crucial for long-term live cell imaging. - quantitative
	molecular dynamics studies: investigating molecular concentration, diffusion,
	and flow dynamics in living samples using the dynamics profiler based on airyscan.
	this allows for the analysis of molecular behavior in various biological contexts.
	- deep tissue imaging with clearing: integrating with clearing techniques and
	specialized objectives to significantly increase optical penetration depth in
	samples like brains, organoids, and tissues, enabling the visualization of structures
	in deeper layers. - correlative cryo microscopy: facilitating workflows that combine
	light and electron microscopy under cryogenic conditions to study cellular structures
	in a near-to-native state, bridging the gap between functional and ultrastructural
	information. typical sample types: - cells and cell cultures: including various
	cell lines for studying subcellular structures and dynamics. - tissues and tissue
	sections: allowing for the investigation of cellular organization and molecular
	distribution within complex environments. - organoids and spheroids: enabling
	the study of 3d tissue models and their development using various imaging modalities,
	including high-speed volume acquisition. - whole organisms and embryos: such as
	zebrafish embryos, for observing developmental processes and physiological functions
	in vivo with high spatiotemporal resolution. - cleared biological samples: including
	whole brains, tissue sections, organoids, and spheroids made transparent to enable
	deep optical imaging. - microfluidic devices: for controlled studies of flow and
	molecular dynamics. - plant tissues: such as arabidopsis thaliana stems, for investigating
	protein behavior in response to environmental stimuli. commonly performed tasks:
	- confocal imaging: high-resolution optical sectioning to visualize specific planes
	within a sample and generate 3d reconstructions. - super-resolution microscopy:
	resolving structures beyond the diffraction limit to visualize nanoscale details
	of cellular components. - live cell imaging: capturing time-series data of living
	cells and organisms to study dynamic processes and cellular behaviors over time.
	- high-speed volumetric imaging: acquiring 3d datasets at rapid frame rates to
	visualize fast biological events in their entirety. - spectral imaging and unmixing:
	separating the contributions of multiple fluorescent probes based on their emission
	spectra to allow for simultaneous multi-target analysis. - fluorescence recovery
	after photobleaching (frap): investigating molecular mobility and dynamics within
	cellular compartments. - fluorescence correlation spectroscopy (fcs) and dynamics
	profiling: measuring molecular concentrations, diffusion coefficients, and flow
	velocities in living samples. - image processing and analysis: utilizing software
	tools like zen and arivis pro for image enhancement, quantification, segmentation,
	tracking, and 3d visualization of complex datasets. - correlative light and electron
	microscopy (clem): combining light microscopy for functional identification with
	electron microscopy for ultrastructural details. - imaging of large volumes and
	tiled acquisitions: acquiring data from large samples or multiple regions of interest
	and stitching them together for comprehensive analysis. - automated imaging workflows:
	setting up and executing complex imaging experiments with automation features
	for reproducible data acquisition. - advanced image analysis using ai: employing
	artificial intelligence-assisted features for sample finding, setup optimization,
	and image analysis.'
	- source_sentence: We previously demonstrated that neural stem/progenitor cells (NSPCs)
	were induced within and around the ischemic areas in a mouse model of ischemic
	stroke. These injury/ischemia-induced NSPCs (iNSPCs) differentiated to electrophysiologically
	functional neurons in vitro, indicating the presence of a self-repair system following
	injury. However, during the healing process after stroke, ischemic areas were
	gradually occupied by inflammatory cells, mainly microglial cells/macrophages
	(MGs/MΦs), and neurogenesis rarely occurred within and around the ischemic areas.
	Therefore, to achieve neural regeneration by utilizing endogenous iNSPCs, regulation
	of MGs/MΦs after an ischemic stroke might be necessary. To test this hypothesis,
	we used iNSPCs isolated from the ischemic areas after a stroke in our mouse model
	to investigate the role of MGs/MΦs in iNSPC regulation. In coculture experiments,
	we show that the presence of MGs/MΦs significantly reduces not only the proliferation
	but also the differentiation of iNSPCs toward neuronal cells, thereby preventing
	neurogenesis. These effects, however, are mitigated by MG/MΦ depletion using clodronate
	encapsulated in liposomes. Additionally, gene ontology analysis reveals that proliferation
	and neuronal differentiation are negatively regulated in iNSPCs cocultured with
	MGs/MΦs. These results indicate that MGs/MΦs negatively impact neurogenesis via
	iNSPCs, suggesting that the regulation of MGs/MΦs is essential to achieve iNSPC-based
	neural regeneration following an ischemic stroke.
	sentences:
	- ZEISS Airyscan is an advanced imaging technology that enhances traditional confocal
	microscopy by using a 32-channel detector to capture more light with higher resolution
	and sensitivity. Unlike standard confocal systems that rely on a single pinhole,
	Airyscan collects the entire Airy disk pattern and reconstructs images for super-resolution
	clarityâ down to 120 nm laterally. This results in significantly improved signal-to-noise
	ratio and reduced photodamage, making it ideal for detailed imaging of live cells
	and biological samples. It's compatible with ZEISS LSM systems like the LSM 880
	and 900, offering researchers a powerful tool for high-precision fluorescence
	microscopy
	- 'the zeiss geminisem family of field emission scanning electron microscopes (fesems)
	provides versatile solutions for advanced imaging and analysis across a wide range
	of scientific and industrial disciplines. these instruments are designed to meet
	the highest demands in sub-nanometer imaging, analytics, and sample flexibility.
	key research and application areas: - advancing nanoscience and nanomaterials:
	enabling the visualization, characterization, and manipulation of nanoscale structures
	and materials for applications in electronics, catalysis, sensing, and medicine.
	this includes analyzing the structure and integrity of nanoelectronic and photonic
	devices, imaging sensitive 2d materials, and investigating nanomagnetism and nanomechanics.
	- innovating energy materials: providing insights into the microstructure of materials
	and devices critical for batteries, solar cells, and fuel cells, aiding in the
	development of more efficient energy solutions. this encompasses microstructure
	and device evaluation, defect analysis, and the quantification of phases, pores,
	and fractures. - engineering next-generation materials: supporting the development
	and improvement of advanced alloys, composites, coatings, and additively manufactured
	parts by detailed characterization of their properties. this involves high-resolution
	imaging with superior contrast, metallography, fracture analysis, and in situ
	material behavior studies. - exploring bio-inspired materials, polymers, and catalysts:
	facilitating the design, optimization, and functional characterization of these
	often non-conductive and beam-sensitive materials for diverse applications. key
	tasks include surface evaluation, structural analysis, correlative multiscale
	characterization, and failure analysis. - ensuring industrial quality and reliability:
	serving as a crucial tool for failure analysis in mechanical, optical, and electronic
	components, helping to identify root causes and improve manufacturing processes.
	- driving innovation in electronics and semiconductors: addressing the increasing
	complexity of semiconductor devices by providing high-resolution imaging and analysis
	techniques essential for process control and failure analysis of nanoscale features.
	this includes construction analysis, passive voltage contrast imaging, and subsurface
	analysis. - unveiling the complexity of life sciences: enabling detailed characterization
	of biological samples, from ultrastructural investigations of cells and tissues
	to large-area imaging for statistical analysis in various fields like neuroscience,
	cell biology, and developmental biology. typical sample types: - a wide array
	of nanostructured materials, including nanoparticles, nanowires, thin films, and
	2d materials. - components and materials used in energy storage and conversion,
	such as battery electrodes and separators, solar cell layers, and fuel cell membranes.
	- various engineering materials, including metals, alloys, ceramics, polymers,
	composites, and coatings, often analyzed in cross-section or after mechanical
	failure. - bio-inspired and soft materials, such as polymer scaffolds, biological
	tissues, and catalysts, often imaged without conductive coatings. - industrial
	components from diverse sectors, including electronics, mechanics, and optics,
	analyzed for defects, composition, and structural integrity. - semiconductor devices
	at various stages of fabrication, including transistors, interconnects, and integrated
	circuits. - a broad spectrum of biological samples, including cells, tissues,
	bacteria, viruses, and whole organisms, prepared using various techniques like
	fixation, staining, and embedding. commonly performed tasks: - high-resolution
	imaging to reveal nanoscale details of material surfaces and internal structures,
	often utilizing low accelerating voltages to minimize sample damage. - detailed
	surface characterization to understand topography, roughness, and the presence
	of specific features or defects. - compositional analysis using various detectors
	to identify and map different material phases and elemental distributions. - crystallographic
	investigations to determine grain orientations and crystalline structures within
	materials. - correlative microscopy by integrating data from multiple imaging
	modalities (e.g., light and electron microscopy) to obtain a more comprehensive
	understanding of samples. - automated large-area imaging and data acquisition
	to enable statistical analysis and the study of heterogeneous samples. - three-dimensional
	reconstruction of sample volumes using techniques like serial sectioning and tomography
	to visualize internal structures in detail. - in situ experimentation to observe
	dynamic processes and material behavior under controlled environmental conditions
	such as temperature changes, mechanical stress, or vacuum levels. - analysis of
	challenging samples, including non-conductive and beam-sensitive materials, using
	specialized modes like variable pressure to mitigate charging artifacts and beam
	damage. - failure analysis to identify the root causes of material and device
	malfunctions in industrial and research settings. - subsurface imaging and electronic
	property analysis of semiconductor devices to aid in design and failure diagnostics.'
	- ZEISS Airyscan is an advanced imaging technology that enhances traditional confocal
	microscopy by using a 32-channel detector to capture more light with higher resolution
	and sensitivity. Unlike standard confocal systems that rely on a single pinhole,
	Airyscan collects the entire Airy disk pattern and reconstructs images for super-resolution
	clarityâ down to 120 nm laterally. This results in significantly improved signal-to-noise
	ratio and reduced photodamage, making it ideal for detailed imaging of live cells
	and biological samples. It's compatible with ZEISS LSM systems like the LSM 880
	and 900, offering researchers a powerful tool for high-precision fluorescence
	microscopy
	pipeline_tag: sentence-similarity
	library_name: sentence-transformers
	metrics:
	- cosine_accuracy@1
	- cosine_accuracy@3
	- cosine_accuracy@5
	- cosine_accuracy@10
	- cosine_precision@1
	- cosine_precision@3
	- cosine_precision@5
	- cosine_precision@10
	- cosine_recall@1
	- cosine_recall@3
	- cosine_recall@5
	- cosine_recall@10
	- cosine_ndcg@10
	- cosine_mrr@10
	- cosine_map@100
	model-index:
	- name: SentenceTransformer based on allenai/specter2_base
	results:
	- task:
	type: information-retrieval
	name: Information Retrieval
	dataset:
	name: ir eval
	type: ir-eval
	metrics:
	- type: cosine_accuracy@1
	value: 0.0
	name: Cosine Accuracy@1
	- type: cosine_accuracy@3
	value: 0.0
	name: Cosine Accuracy@3
	- type: cosine_accuracy@5
	value: 0.0
	name: Cosine Accuracy@5
	- type: cosine_accuracy@10
	value: 0.0
	name: Cosine Accuracy@10
	- type: cosine_precision@1
	value: 0.0
	name: Cosine Precision@1
	- type: cosine_precision@3
	value: 0.0
	name: Cosine Precision@3
	- type: cosine_precision@5
	value: 0.0
	name: Cosine Precision@5
	- type: cosine_precision@10
	value: 0.0
	name: Cosine Precision@10
	- type: cosine_recall@1
	value: 0.0
	name: Cosine Recall@1
	- type: cosine_recall@3
	value: 0.0
	name: Cosine Recall@3
	- type: cosine_recall@5
	value: 0.0
	name: Cosine Recall@5
	- type: cosine_recall@10
	value: 0.0
	name: Cosine Recall@10
	- type: cosine_ndcg@10
	value: 0.0
	name: Cosine Ndcg@10
	- type: cosine_mrr@10
	value: 0.0
	name: Cosine Mrr@10
	- type: cosine_map@100
	value: 0.0
	name: Cosine Map@100
	- type: cosine_accuracy@1
	value: 0.14206268958543983
	name: Cosine Accuracy@1
	- type: cosine_accuracy@3
	value: 0.31243680485338726
	name: Cosine Accuracy@3
	- type: cosine_accuracy@5
	value: 0.4524772497472194
	name: Cosine Accuracy@5
	- type: cosine_accuracy@10
	value: 0.6698685540950455
	name: Cosine Accuracy@10
	- type: cosine_precision@1
	value: 0.14206268958543983
	name: Cosine Precision@1
	- type: cosine_precision@3
	value: 0.10414560161779575
	name: Cosine Precision@3
	- type: cosine_precision@5
	value: 0.09049544994944388
	name: Cosine Precision@5
	- type: cosine_precision@10
	value: 0.06698685540950455
	name: Cosine Precision@10
	- type: cosine_recall@1
	value: 0.14206268958543983
	name: Cosine Recall@1
	- type: cosine_recall@3
	value: 0.31243680485338726
	name: Cosine Recall@3
	- type: cosine_recall@5
	value: 0.4524772497472194
	name: Cosine Recall@5
	- type: cosine_recall@10
	value: 0.6698685540950455
	name: Cosine Recall@10
	- type: cosine_ndcg@10
	value: 0.36473696593145394
	name: Cosine Ndcg@10
	- type: cosine_mrr@10
	value: 0.2722448922271969
	name: Cosine Mrr@10
	- type: cosine_map@100
	value: 0.29173778100425013
	name: Cosine Map@100
	---

	# SentenceTransformer based on allenai/specter2_base

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [allenai/specter2_base](https://huggingface.co/allenai/specter2_base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

	## Model Details

	### Model Description
	- Model Type: Sentence Transformer
	- Base model: [allenai/specter2_base](https://huggingface.co/allenai/specter2_base) <!-- at revision 3447645e1def9117997203454fa4495937bfbd83 -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 768 dimensions
	- Similarity Function: Cosine Similarity
	<!-- - Training Dataset: Unknown -->
	<!-- - Language: Unknown -->
	<!-- - License: Unknown -->

	### Model Sources

	- Documentation: [Sentence Transformers Documentation](https://sbert.net)
	- Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
	- Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)

	### Full Model Architecture

	```
	SentenceTransformer(
	(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
	(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
	)
	```

	## Usage

	### Direct Usage (Sentence Transformers)

	First install the Sentence Transformers library:

	```bash
	pip install -U sentence-transformers
	```

	Then you can load this model and run inference.
	```python
	from sentence_transformers import SentenceTransformer

	# Download from the 🤗 Hub
	model = SentenceTransformer("jagadeesh/zeiss-re-1757437055")
	# Run inference
	sentences = [
	'We previously demonstrated that neural stem/progenitor cells (NSPCs) were induced within and around the ischemic areas in a mouse model of ischemic stroke. These injury/ischemia-induced NSPCs (iNSPCs) differentiated to electrophysiologically functional neurons in vitro, indicating the presence of a self-repair system following injury. However, during the healing process after stroke, ischemic areas were gradually occupied by inflammatory cells, mainly microglial cells/macrophages (MGs/MΦs), and neurogenesis rarely occurred within and around the ischemic areas. Therefore, to achieve neural regeneration by utilizing endogenous iNSPCs, regulation of MGs/MΦs after an ischemic stroke might be necessary. To test this hypothesis, we used iNSPCs isolated from the ischemic areas after a stroke in our mouse model to investigate the role of MGs/MΦs in iNSPC regulation. In coculture experiments, we show that the presence of MGs/MΦs significantly reduces not only the proliferation but also the differentiation of iNSPCs toward neuronal cells, thereby preventing neurogenesis. These effects, however, are mitigated by MG/MΦ depletion using clodronate encapsulated in liposomes. Additionally, gene ontology analysis reveals that proliferation and neuronal differentiation are negatively regulated in iNSPCs cocultured with MGs/MΦs. These results indicate that MGs/MΦs negatively impact neurogenesis via iNSPCs, suggesting that the regulation of MGs/MΦs is essential to achieve iNSPC-based neural regeneration following an ischemic stroke.',
	"ZEISS Airyscan is an advanced imaging technology that enhances traditional confocal microscopy by using a 32-channel detector to capture more light with higher resolution and sensitivity. Unlike standard confocal systems that rely on a single pinhole, Airyscan collects the entire Airy disk pattern and reconstructs images for super-resolution clarityâ down to 120 nm laterally. This results in significantly improved signal-to-noise ratio and reduced photodamage, making it ideal for detailed imaging of live cells and biological samples. It's compatible with ZEISS LSM systems like the LSM 880 and 900, offering researchers a powerful tool for high-precision fluorescence microscopy",
	"ZEISS Airyscan is an advanced imaging technology that enhances traditional confocal microscopy by using a 32-channel detector to capture more light with higher resolution and sensitivity. Unlike standard confocal systems that rely on a single pinhole, Airyscan collects the entire Airy disk pattern and reconstructs images for super-resolution clarityâ down to 120 nm laterally. This results in significantly improved signal-to-noise ratio and reduced photodamage, making it ideal for detailed imaging of live cells and biological samples. It's compatible with ZEISS LSM systems like the LSM 880 and 900, offering researchers a powerful tool for high-precision fluorescence microscopy",
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 768]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities)
	# tensor([[1.0000, 0.6165, 0.6165],
	# [0.6165, 1.0000, 1.0000],
	# [0.6165, 1.0000, 1.0000]])
	```

	<!--
	### Direct Usage (Transformers)

	<details><summary>Click to see the direct usage in Transformers</summary>

	</details>
	-->

	<!--
	### Downstream Usage (Sentence Transformers)

	You can finetune this model on your own dataset.

	<details><summary>Click to expand</summary>

	</details>
	-->

	<!--
	### Out-of-Scope Use

	List how the model may foreseeably be misused and address what users ought not to do with the model.
	-->

	## Evaluation

	### Metrics

	#### Information Retrieval

	* Dataset: `ir-eval`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:--------\|
	\| cosine_accuracy@1 \| 0.0 \|
	\| cosine_accuracy@3 \| 0.0 \|
	\| cosine_accuracy@5 \| 0.0 \|
	\| cosine_accuracy@10 \| 0.0 \|
	\| cosine_precision@1 \| 0.0 \|
	\| cosine_precision@3 \| 0.0 \|
	\| cosine_precision@5 \| 0.0 \|
	\| cosine_precision@10 \| 0.0 \|
	\| cosine_recall@1 \| 0.0 \|
	\| cosine_recall@3 \| 0.0 \|
	\| cosine_recall@5 \| 0.0 \|
	\| cosine_recall@10 \| 0.0 \|
	\| cosine_ndcg@10 \| 0.0 \|
	\| cosine_mrr@10 \| 0.0 \|
	\| cosine_map@100 \| 0.0 \|

	#### Information Retrieval

	* Dataset: `ir-eval`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| cosine_accuracy@1 \| 0.1421 \|
	\| cosine_accuracy@3 \| 0.3124 \|
	\| cosine_accuracy@5 \| 0.4525 \|
	\| cosine_accuracy@10 \| 0.6699 \|
	\| cosine_precision@1 \| 0.1421 \|
	\| cosine_precision@3 \| 0.1041 \|
	\| cosine_precision@5 \| 0.0905 \|
	\| cosine_precision@10 \| 0.067 \|
	\| cosine_recall@1 \| 0.1421 \|
	\| cosine_recall@3 \| 0.3124 \|
	\| cosine_recall@5 \| 0.4525 \|
	\| cosine_recall@10 \| 0.6699 \|
	\| cosine_ndcg@10 \| 0.3647 \|
	\| cosine_mrr@10 \| 0.2722 \|
	\| cosine_map@100 \| 0.2917 \|

	<!--
	## Bias, Risks and Limitations

	What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.
	-->

	<!--
	### Recommendations

	What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.
	-->

	## Training Details

	### Training Dataset

	#### Unnamed Dataset

	* Size: 17,793 training samples
	* Columns: <code>anchor</code> and <code>positive</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| anchor \| positive \|
	\|:--------\|:-----------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------\|
	\| type \| string \| string \|
	\| details \| <ul><li>min: 2 tokens</li><li>mean: 283.9 tokens</li><li>max: 512 tokens</li></ul> \| <ul><li>min: 91 tokens</li><li>mean: 355.19 tokens</li><li>max: 512 tokens</li></ul> \|
	* Samples:
	\| anchor \| positive \|
	\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>Nutrition and resilience are linked, though it is not yet clear how diet confers stress resistance or the breadth of stressors that it can protect against. We have previously shown that transiently restricting an essential amino acid can protect Drosophila melanogaster against nicotine poisoning. Here, we sought to characterize the nature of this dietary-mediated protection and determine whether it was sex, amino acid and/or nicotine specific. When we compared between sexes, we found that isoleucine deprivation increases female, but not male, nicotine resistance. Surprisingly, we found that this protection afforded to females was not replicated by dietary protein restriction and was instead specific to individual amino acid restriction. To understand whether these beneficial effects of diet were specific to nicotine or were generalizable across stressors, we pre-treated flies with amino acid restriction diets and exposed them to other types of stress. We found that some of the diets th...</code> \| <code>the zeiss stemi 508 is an apochromatic stereo microscope with an 8:1 zoom range, designed for high-contrast, color-accurate three-dimensional observation and documentation of diverse samples. its ergonomic design and robust mechanics support demanding applications in laboratory and industrial settings. key research and application areas: - biological research: suitable for observing the development and growth of model organisms like spider crabs, chicken, mouse, or zebrafish, including the evaluation, sorting, selection, or dissection of eggs, larvae, or embryos. it is also used in botany to observe changes in plant organs, diseases, and root development, in entomology for insect observation, documentation, and identification, in marine biology to study the life and reproduction of fish, and in parasitology for detecting and identifying the spread of parasites. the microscope is valuable for forensic analysis of ammunition parts, tool marks, documents, fibers, coatings, glass, textiles...</code> \|
	\| <code>The controlled supply of bioactive molecules is a subject of debate in animal nutrition. The release of bioactive molecules in the target organ, in this case the intestine, results in improved feed, as well as having a lower environmental impact. However, the degradation of bioactive molecules' in transit in the gastrointestinal passage is still an unresolved issue. This paper discusses the feasibility of a simple and cost-effective procedure to bypass the degradation problem. A solid/liquid adsorption procedure was applied, and the operating parameters (pH, reaction time, and LY initial concentration) were studied. Lysozyme is used in this work as a representative bioactive molecule, while Adsorbo ® , a commercial mixture of clay minerals and zeolites which meets current feed regulations, is used as the carrier. A maximum LY loading of 32 mg LY /g AD (LY(32)-AD) was obtained, with fixing pH in the range 7.5-8, initial LY content at 37.5 mg LY /g AD , and reaction time at 30 min. A ful...</code> \| <code>the zeiss evo family of scanning electron microscopes offers a modular and versatile platform for a wide range of scientific and industrial investigations, combining high-performance imaging and analysis with intuitive operation for users of varying experience levels. key research and application areas: - materials science: characterizing the morphology, structure, and composition of diverse materials, including metals, composites, polymers, ceramics, and coatings, for research and development. this includes investigating surface structures, fractures, inclusions, and grain boundaries. the evo supports advanced material analysis through techniques like energy dispersive spectroscopy (eds) and electron backscatter diffraction (ebsd). - life sciences: enabling the examination of biological specimens in their native or near-native hydrated states using variable and extended pressure modes. applications include imaging cells, tissues, plants, and microorganisms for structural and morpholog...</code> \|
	\| <code>Amorphous potassium sodium niobate (KNN) films were synthesized at 300 °C through the radio frequency magnetron sputtering method and subsequently crystallized by post-annealing at 700 °C in various alkali element atmospheres (Na and K). The as-deposited film is notably deficient in alkali metal elements, particularly K, whereas the loss of alkali elements in the films can be replenished through annealing in an alkali element atmosphere. By adjusting the molar ratio of Na and K in the annealing atmosphere, the ratio of Na/K in the resultant film varied, consequently suggesting the efficiency of this method on composition regulation of KNN films. Meanwhile, we also found that the physical characteristics of the films also underwent differences with the change of an annealing atmosphere. The films annealed in a high Na atmosphere exhibit large dielectric losses with limited piezoelectric vibration behavior, while annealing in a high K atmosphere reduces the dielectric losses and enhances...</code> \| <code>the zeiss sigma family of field emission scanning electron microscopes (fe-sems) offers versatile solutions for high-quality imaging and advanced analytical microscopy across a multitude of scientific and industrial domains. these instruments are engineered for reliable, high-end nano-analysis, combining fe-sem technology with an intuitive user experience to enhance productivity. key research and application areas: - advancing materials science: facilitating the development and understanding of novel materials by enabling the investigation of micro- and nanoscale structures. this includes characterizing metals, alloys, polymers, catalysts, and coatings for various applications such as electronics and energy. - driving innovation in nanoscience and nanomaterials: providing capabilities for the analysis of nanoparticles, thin films, 2d materials (like graphene and mos2), and other nanostructures to understand their properties and potential applications. - supporting energy research: enab...</code> \|
	* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "cos_sim",
	"gather_across_devices": false
	}
	```

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 16
	- `per_device_eval_batch_size`: 16
	- `learning_rate`: 1e-05
	- `num_train_epochs`: 5
	- `warmup_ratio`: 0.1
	- `fp16`: True
	- `batch_sampler`: no_duplicates

	#### All Hyperparameters
	<details><summary>Click to expand</summary>

	- `overwrite_output_dir`: False
	- `do_predict`: False
	- `eval_strategy`: steps
	- `prediction_loss_only`: True
	- `per_device_train_batch_size`: 16
	- `per_device_eval_batch_size`: 16
	- `per_gpu_train_batch_size`: None
	- `per_gpu_eval_batch_size`: None
	- `gradient_accumulation_steps`: 1
	- `eval_accumulation_steps`: None
	- `torch_empty_cache_steps`: None
	- `learning_rate`: 1e-05
	- `weight_decay`: 0.0
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 5
	- `max_steps`: -1
	- `lr_scheduler_type`: linear
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.1
	- `warmup_steps`: 0
	- `log_level`: passive
	- `log_level_replica`: warning
	- `log_on_each_node`: True
	- `logging_nan_inf_filter`: True
	- `save_safetensors`: True
	- `save_on_each_node`: False
	- `save_only_model`: False
	- `restore_callback_states_from_checkpoint`: False
	- `no_cuda`: False
	- `use_cpu`: False
	- `use_mps_device`: False
	- `seed`: 42
	- `data_seed`: None
	- `jit_mode_eval`: False
	- `use_ipex`: False
	- `bf16`: False
	- `fp16`: True
	- `fp16_opt_level`: O1
	- `half_precision_backend`: auto
	- `bf16_full_eval`: False
	- `fp16_full_eval`: False
	- `tf32`: None
	- `local_rank`: 0
	- `ddp_backend`: None
	- `tpu_num_cores`: None
	- `tpu_metrics_debug`: False
	- `debug`: []
	- `dataloader_drop_last`: False
	- `dataloader_num_workers`: 0
	- `dataloader_prefetch_factor`: None
	- `past_index`: -1
	- `disable_tqdm`: False
	- `remove_unused_columns`: True
	- `label_names`: None
	- `load_best_model_at_end`: False
	- `ignore_data_skip`: False
	- `fsdp`: []
	- `fsdp_min_num_params`: 0
	- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
	- `fsdp_transformer_layer_cls_to_wrap`: None
	- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
	- `parallelism_config`: None
	- `deepspeed`: None
	- `label_smoothing_factor`: 0.0
	- `optim`: adamw_torch_fused
	- `optim_args`: None
	- `adafactor`: False
	- `group_by_length`: False
	- `length_column_name`: length
	- `ddp_find_unused_parameters`: None
	- `ddp_bucket_cap_mb`: None
	- `ddp_broadcast_buffers`: False
	- `dataloader_pin_memory`: True
	- `dataloader_persistent_workers`: False
	- `skip_memory_metrics`: True
	- `use_legacy_prediction_loop`: False
	- `push_to_hub`: False
	- `resume_from_checkpoint`: None
	- `hub_model_id`: None
	- `hub_strategy`: every_save
	- `hub_private_repo`: None
	- `hub_always_push`: False
	- `hub_revision`: None
	- `gradient_checkpointing`: False
	- `gradient_checkpointing_kwargs`: None
	- `include_inputs_for_metrics`: False
	- `include_for_metrics`: []
	- `eval_do_concat_batches`: True
	- `fp16_backend`: auto
	- `push_to_hub_model_id`: None
	- `push_to_hub_organization`: None
	- `mp_parameters`:
	- `auto_find_batch_size`: False
	- `full_determinism`: False
	- `torchdynamo`: None
	- `ray_scope`: last
	- `ddp_timeout`: 1800
	- `torch_compile`: False
	- `torch_compile_backend`: None
	- `torch_compile_mode`: None
	- `include_tokens_per_second`: False
	- `include_num_input_tokens_seen`: False
	- `neftune_noise_alpha`: None
	- `optim_target_modules`: None
	- `batch_eval_metrics`: False
	- `eval_on_start`: False
	- `use_liger_kernel`: False
	- `liger_kernel_config`: None
	- `eval_use_gather_object`: False
	- `average_tokens_across_devices`: False
	- `prompts`: None
	- `batch_sampler`: no_duplicates
	- `multi_dataset_batch_sampler`: proportional
	- `router_mapping`: {}
	- `learning_rate_mapping`: {}

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| ir-eval_cosine_ndcg@10 \|
	\|:------:\|:----:\|:-------------:\|:----------------------:\|
	\| 0.0898 \| 100 \| 2.488 \| 0.0 \|
	\| 0.1797 \| 200 \| 2.321 \| 0.0 \|
	\| 0.2695 \| 300 \| 2.0777 \| 0.0 \|
	\| 0.3594 \| 400 \| 1.833 \| 0.0 \|
	\| 0.4492 \| 500 \| 1.7474 \| 0.0 \|
	\| -1 \| -1 \| - \| 0.2969 \|
	\| 0.0898 \| 100 \| 2.2378 \| 0.3023 \|
	\| 0.1797 \| 200 \| 2.1268 \| 0.3196 \|
	\| 0.2695 \| 300 \| 1.8964 \| 0.3541 \|
	\| 0.3594 \| 400 \| 1.6197 \| 0.3123 \|
	\| 0.4492 \| 500 \| 1.493 \| 0.3086 \|
	\| 0.5391 \| 600 \| 1.4507 \| 0.3146 \|
	\| 0.6289 \| 700 \| 1.6187 \| 0.2985 \|
	\| 0.7188 \| 800 \| 1.4818 \| 0.3412 \|
	\| 0.8086 \| 900 \| 1.3241 \| 0.2945 \|
	\| 0.8985 \| 1000 \| 1.3055 \| 0.2161 \|
	\| 0.9883 \| 1100 \| 1.2704 \| 0.2712 \|
	\| 1.0782 \| 1200 \| 2.009 \| 0.3143 \|
	\| 1.1680 \| 1300 \| 2.0103 \| 0.3403 \|
	\| 1.2579 \| 1400 \| 1.8953 \| 0.3408 \|
	\| 1.3477 \| 1500 \| 1.662 \| 0.3409 \|
	\| 1.4376 \| 1600 \| 1.656 \| 0.3073 \|
	\| 1.5274 \| 1700 \| 1.537 \| 0.2792 \|
	\| 1.6173 \| 1800 \| 1.4893 \| 0.2730 \|
	\| 1.7071 \| 1900 \| 1.3447 \| 0.2537 \|
	\| 1.7969 \| 2000 \| 1.2444 \| 0.2496 \|
	\| 1.8868 \| 2100 \| 1.1493 \| 0.2314 \|
	\| 1.9766 \| 2200 \| 1.26 \| 0.2753 \|
	\| 2.0665 \| 2300 \| 1.7302 \| 0.3514 \|
	\| 2.1563 \| 2400 \| 1.7719 \| 0.3546 \|
	\| 2.2462 \| 2500 \| 1.7208 \| 0.3366 \|
	\| 2.3360 \| 2600 \| 1.4715 \| 0.3387 \|
	\| 2.4259 \| 2700 \| 1.45 \| 0.2974 \|
	\| 2.5157 \| 2800 \| 1.3878 \| 0.3084 \|
	\| 2.6056 \| 2900 \| 1.3184 \| 0.2915 \|
	\| 2.6954 \| 3000 \| 1.2562 \| 0.2917 \|
	\| 2.7853 \| 3100 \| 1.119 \| 0.2940 \|
	\| 2.8751 \| 3200 \| 1.1307 \| 0.2989 \|
	\| 2.9650 \| 3300 \| 1.1421 \| 0.3081 \|
	\| 3.0548 \| 3400 \| 1.4917 \| 0.3402 \|
	\| 3.1447 \| 3500 \| 1.5628 \| 0.3392 \|
	\| 3.2345 \| 3600 \| 1.4621 \| 0.3684 \|
	\| 3.3243 \| 3700 \| 1.342 \| 0.3601 \|
	\| 3.4142 \| 3800 \| 1.3052 \| 0.3222 \|
	\| 3.5040 \| 3900 \| 1.2133 \| 0.3566 \|
	\| 3.5939 \| 4000 \| 1.248 \| 0.3631 \|
	\| 3.6837 \| 4100 \| 1.2261 \| 0.3558 \|
	\| 3.7736 \| 4200 \| 0.978 \| 0.3428 \|
	\| 3.8634 \| 4300 \| 0.9916 \| 0.3545 \|
	\| 3.9533 \| 4400 \| 1.0824 \| 0.3492 \|
	\| 4.0431 \| 4500 \| 1.2055 \| 0.3418 \|
	\| 4.1330 \| 4600 \| 1.404 \| 0.3481 \|
	\| 4.2228 \| 4700 \| 1.3775 \| 0.3613 \|
	\| 4.3127 \| 4800 \| 1.2128 \| 0.3579 \|
	\| 4.4025 \| 4900 \| 1.168 \| 0.3625 \|
	\| 4.4924 \| 5000 \| 1.1061 \| 0.3600 \|
	\| 4.5822 \| 5100 \| 1.1213 \| 0.3658 \|
	\| 4.6721 \| 5200 \| 1.0396 \| 0.3603 \|
	\| 4.7619 \| 5300 \| 0.9766 \| 0.3702 \|
	\| 4.8518 \| 5400 \| 0.9143 \| 0.3618 \|
	\| 4.9416 \| 5500 \| 0.9728 \| 0.3647 \|


	### Framework Versions
	- Python: 3.11.11
	- Sentence Transformers: 5.1.0
	- Transformers: 4.56.1
	- PyTorch: 2.8.0.dev20250319+cu128
	- Accelerate: 1.10.1
	- Datasets: 3.6.0
	- Tokenizers: 0.22.0

	## Citation

	### BibTeX

	#### Sentence Transformers
	```bibtex
	@inproceedings{reimers-2019-sentence-bert,
	title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
	author = "Reimers, Nils and Gurevych, Iryna",
	booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
	month = "11",
	year = "2019",
	publisher = "Association for Computational Linguistics",
	url = "https://arxiv.org/abs/1908.10084",
	}
	```

	#### MultipleNegativesRankingLoss
	```bibtex
	@misc{henderson2017efficient,
	title={Efficient Natural Language Response Suggestion for Smart Reply},
	author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
	year={2017},
	eprint={1705.00652},
	archivePrefix={arXiv},
	primaryClass={cs.CL}
	}
	```

	<!--
	## Glossary

	Clearly define terms in order to be accessible across audiences.
	-->

	<!--
	## Model Card Authors

	Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.
	-->

	<!--
	## Model Card Contact

	Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.
	-->