Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation | Paper Citation Record

Observation de7e5b77-c7d2-43e8-ab13-264a93b9d207 · outbound

This paper cites Repro- ducibility in chemistry research.Heliyon, 10(14), 2024.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Repro- ducibility in chemistry research.Heliyon, 10(14), 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:25.806789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d820df6c-35d6-41a4-9254-cdda3a6ec3db · outbound

This paper cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:25.909553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f30eca69-2696-422e-a7bc-d315160b51e4 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.063566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510fb988-be28-4e61-8e36-33f8ae899c88 · outbound

This paper cites Language agents achieve superhuman synthesis of scientific knowledge.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Language agents achieve superhuman synthesis of scientific knowledge

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.148486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e56b05f-953b-4410-91c4-14d3d31bb2e6 · outbound

This paper cites Chemlit-qa: a human evaluated dataset for chemistry rag tasks.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Chemlit-qa: a human evaluated dataset for chemistry rag tasks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.357438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35765250-b9e4-40ad-b401-b8632cd1c0ed · outbound

This paper cites Benchmarking retrieval-augmented generation for chemistry.arXiv preprint arXiv:2505.07671, 2025.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Benchmarking retrieval-augmented generation for chemistry.arXiv preprint arXiv:2505.07671, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.516513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9a31e13-b41f-4a16-b25e-34e1b7e37c5b · outbound

This paper cites Rag-enhanced collaborative llm agents for drug discovery.arXiv preprint arXiv:2502.17506, 2025.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Rag-enhanced collaborative llm agents for drug discovery.arXiv preprint arXiv:2502.17506, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.692752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 244ee73f-754b-44d7-8eae-2f8737fd3626 · outbound

This paper cites Kragen: a knowledge graph-enhanced rag framework for biomedical problem solving using large language models.Bioinfor- matics, 40(6):btae353, 2024.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Kragen: a knowledge graph-enhanced rag framework for biomedical problem solving using large language models.Bioinfor- matics, 40(6):btae353, 2024

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.854549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5714205-d2d2-4e5e-9bd6-42508ae27c3e · outbound

This paper cites Financial Report Chunking for Effective Retrieval Augmented Generation.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Financial Report Chunking for Effective Retrieval Augmented Generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.017320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6625bbf3-7d60-4ea5-9ba7-8234eb8ddc50 · outbound

This paper cites A survey of text representation and embedding techniques in nlp.IEEE Access, 11:36120–36146, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation A survey of text representation and embedding techniques in nlp.IEEE Access, 11:36120–36146, 2023

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.175022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ad979c3-fb73-4689-ba8c-a315d0abe048 · outbound

This paper cites Evaluating chunking strategies for retrieval.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Evaluating chunking strategies for retrieval

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.285777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 101f03a4-2e83-4016-b345-dbdd8681f6c3 · outbound

This paper cites ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.372188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1da7e520-1cc1-4b8c-be4e-573238ae7ef7 · outbound

This paper cites Natural questions: a benchmark for question answering research.Transactions of the Association for Computational Linguistics, 7:453–466, 2019.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Natural questions: a benchmark for question answering research.Transactions of the Association for Computational Linguistics, 7:453–466, 2019

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.474775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c42e34e-bbd9-45c4-a808-62f5d5f9ef7b · outbound

This paper cites Ms marco: A human-generated machine reading comprehension dataset.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Ms marco: A human-generated machine reading comprehension dataset

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.557395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 731c0646-b868-4cfd-9091-22628e0ef5f8 · outbound

This paper cites an unresolved cited work.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Unresolved cited work

Reference 15

Resolution: malformed identifier; no resolver link, observed 2026-08-07T04:09:27.677321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3de4ad7-35db-4c90-b3b1-ec19958ccbc4 · outbound

This paper cites Mmteb: Massive multilingual text embedding benchmark.arXiv preprint arXiv:2502.13595, 2025.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Mmteb: Massive multilingual text embedding benchmark.arXiv preprint arXiv:2502.13595, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.763439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9e9cfc4-24da-4dcf-97ee-3481b29c5a01 · outbound

This paper cites MTEB: Massive Text Embedding Benchmark.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation MTEB: Massive Text Embedding Benchmark

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.850983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1431ce9-1a4f-45a5-bcad-bedf85d0439a · outbound

This paper cites ChemQuests: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv papers.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation ChemQuests: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv papers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.929724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b9f2767-0e8f-4cf3-8e79-117d4ca5ad8c · outbound

This paper cites A comprehensive survey of evaluation techniques for recommendation systems.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation A comprehensive survey of evaluation techniques for recommendation systems

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.054411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d04989e-66c1-4068-93ca-23376f261222 · outbound

This paper cites Langchain: Building applications with llms through composability.https://github.com/langchain-ai/langchain,.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Langchain: Building applications with llms through composability.https://github.com/langchain-ai/langchain,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.172794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83207bb7-c340-471f-bad2-bdc99ccb55be · outbound

This paper cites 5 levels of text splitting.https://github.com/ FullStackRetrieval-com/RetrievalTutorials/blob/main/ tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_ Splitting.ipynb, 2024.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation 5 levels of text splitting.https://github.com/ FullStackRetrieval-com/RetrievalTutorials/blob/main/ tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_ Splitting.ipynb, 2024

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.362380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be8f4eed-0492-433c-bb96-8e23793a9f3b · outbound

This paper cites all-minilm-l6-v2.https://huggingface.co/ sentence-transformers/all-MiniLM-L6-v2, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation all-minilm-l6-v2.https://huggingface.co/ sentence-transformers/all-MiniLM-L6-v2, 2021

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.515759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deb57c65-68a6-4270-a963-5fc8b88745b2 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.695946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8cc89f3-633d-4a47-be0a-de1bd77ff1c3 · outbound

This paper cites all-minilm-l12-v2.https://huggingface.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation all-minilm-l12-v2.https://huggingface

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.943885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe8c14ad-8c70-4c71-a48a-f7c913b2bb2b · outbound

This paper cites all-mpnet-base-v2.https://huggingface.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation all-mpnet-base-v2.https://huggingface

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:29.108964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 481f1250-eff8-454b-9e10-402316c14d2b · outbound

This paper cites gtr-t5-base.https://huggingface.co/ sentence-transformers/gtr-t5-base, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation gtr-t5-base.https://huggingface.co/ sentence-transformers/gtr-t5-base, 2021

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:29.309300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79fa579a-7428-4798-8755-661f8aea9c32 · outbound

This paper cites gtr-t5-large.https://huggingface.co/ sentence-transformers/gtr-t5-large, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation gtr-t5-large.https://huggingface.co/ sentence-transformers/gtr-t5-large, 2021

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:29.465020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e1613d4-3eb2-43dd-93dc-e051d0d066cf · outbound

This paper cites gtr-t5-xl.https://huggingface.co/ sentence-transformers/gtr-t5-xl, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation gtr-t5-xl.https://huggingface.co/ sentence-transformers/gtr-t5-xl, 2021

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:29.606549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f681670b-c7e7-4021-a864-2a875baadce0 · outbound

This paper cites bert-base-nli-mean-tokens.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation bert-base-nli-mean-tokens

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:29.745414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0edc9174-cc3b-4241-a5c0-926a2a7b07aa · outbound

This paper cites multi-qa-mpnet-base-dot- v1.https://huggingface.co/sentence-transformers/ multi-qa-mpnet-base-dot-v1, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation multi-qa-mpnet-base-dot- v1.https://huggingface.co/sentence-transformers/ multi-qa-mpnet-base-dot-v1, 2021

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:29.805158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04968a2d-cb1e-43fc-87e2-a1df1b338aad · outbound

This paper cites paraphrase-multilingual-minilm-l12- v2.https://huggingface.co/sentence-transformers/ paraphrase-multilingual-MiniLM-L12-v2, 2020.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation paraphrase-multilingual-minilm-l12- v2.https://huggingface.co/sentence-transformers/ paraphrase-multilingual-MiniLM-L12-v2, 2020

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:29.879899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e6e9192-aa51-439f-a83a-d58adc4728e9 · outbound

This paper cites paraphrase-multilingual-mpnet-base- v2.https://huggingface.co/sentence-transformers/ paraphrase-multilingual-mpnet-base-v2, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation paraphrase-multilingual-mpnet-base- v2.https://huggingface.co/sentence-transformers/ paraphrase-multilingual-mpnet-base-v2, 2021

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:29.983107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f88c0d-2a86-49f0-8929-0499475da741 · outbound

This paper cites Domain-specific language model pretrain- ing for biomedical natural language processing.ACM Transactions on Computing for Healthcare (HEALTH), 3(1):1–23, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Domain-specific language model pretrain- ing for biomedical natural language processing.ACM Transactions on Computing for Healthcare (HEALTH), 3(1):1–23, 2021

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.039846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96954d4-d048-4624-a579-76ff84546281 · outbound

This paper cites Biomednlp-biomedbert- base-uncased-abstract-fulltext.https://huggingface.co/microsoft/ BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Biomednlp-biomedbert- base-uncased-abstract-fulltext.https://huggingface.co/microsoft/ BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext, 2021

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.099139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92b3ed91-a05c-499e-b5f7-c5dd2a7cfe52 · outbound

This paper cites Biomednlp- biomedbert-base-uncased-abstract.https://huggingface.co/microsoft/ BiomedNLP-BiomedBERT-base-uncased-abstract, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Biomednlp- biomedbert-base-uncased-abstract.https://huggingface.co/microsoft/ BiomedNLP-BiomedBERT-base-uncased-abstract, 2021

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.191628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27da451f-55f3-4f23-baa6-c10f8803d85a · outbound

This paper cites Biomednlp-pubmedbert- base-uncased-abstract-fulltext.https://huggingface.co/microsoft/ BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Biomednlp-pubmedbert- base-uncased-abstract-fulltext.https://huggingface.co/microsoft/ BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext, 2021

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.272789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 388ef7af-1db5-4b09-adb4-5bcf0e8ef5d9 · outbound

This paper cites Biomednlp- pubmedbert-base-uncased-abstract.https://huggingface.co/microsoft/ BiomedNLP-PubMedBERT-base-uncased-abstract, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Biomednlp- pubmedbert-base-uncased-abstract.https://huggingface.co/microsoft/ BiomedNLP-PubMedBERT-base-uncased-abstract, 2021

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.379005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca7d48ed-a04f-405d-a930-cbe5aa57af15 · outbound

This paper cites MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.457890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f50cebc-cf51-4cd3-a232-6dc6c9918fd7 · outbound

This paper cites Minilm-l12-h384-uncased.https://huggingface.co/microsoft/ MiniLM-L12-H384-uncased, 2020.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Minilm-l12-h384-uncased.https://huggingface.co/microsoft/ MiniLM-L12-H384-uncased, 2020

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.534864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf117d2-6cc5-41bf-b138-87976062c478 · outbound

This paper cites MPNet: Masked and Permuted Pre-training for Language Understanding.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation MPNet: Masked and Permuted Pre-training for Language Understanding

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.635814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f7e0e7b-7554-4895-aaf4-cd71d709f9c2 · outbound

This paper cites mpnet-base.https: //huggingface.co/microsoft/mpnet-base, 2020.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation mpnet-base.https: //huggingface.co/microsoft/mpnet-base, 2020

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.692717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ed3c0eb-c66a-4cc1-b8bc-1bff32b0fb6e · outbound

This paper cites Text Embeddings by Weakly-Supervised Contrastive Pre-training.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Text Embeddings by Weakly-Supervised Contrastive Pre-training

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.755264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d79a3c28-5a46-424b-9aab-a4151fe36e55 · outbound

This paper cites e5-small.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation e5-small

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.811918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e46e96-c900-435c-a8e8-5a29ca91dba2 · outbound

This paper cites e5-small-v2.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation e5-small-v2

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.869382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29587c95-312e-4cc4-a1f4-effecece5e72 · outbound

This paper cites e5-base.https: //huggingface.co/intfloat/e5-base, 2022.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation e5-base.https: //huggingface.co/intfloat/e5-base, 2022

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:30.925949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb8f1293-a4d5-4ec1-8cc6-7e1d775c9bd3 · outbound

This paper cites e5-base-v2.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation e5-base-v2

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.000826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54fad084-d534-4530-a9e2-c758b93d549c · outbound

This paper cites e5-large.https: //huggingface.co/intfloat/e5-large, 2022.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation e5-large.https: //huggingface.co/intfloat/e5-large, 2022

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.102309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1569da7-d2ca-4cf5-a556-b8e7b799d266 · outbound

This paper cites e5-large-v2.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation e5-large-v2

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.171414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b496ec84-dbe3-44d9-a75c-9aa9b3de4a1f · outbound

This paper cites multilingual- e5-base.https://huggingface.co/intfloat/multilingual-e5-base, 2022.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation multilingual- e5-base.https://huggingface.co/intfloat/multilingual-e5-base, 2022

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.262099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c8bd98a-9bfa-4fa5-8319-7fd698f8b1a9 · outbound

This paper cites multilingual-e5- large.https://huggingface.co/intfloat/multilingual-e5-large, 2022.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation multilingual-e5- large.https://huggingface.co/intfloat/multilingual-e5-large, 2022

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.323130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05b6808d-2ff6-460c-97f3-141beeac5f04 · outbound

This paper cites multilingual-e5- small.https://huggingface.co/intfloat/multilingual-e5-small, 2022.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation multilingual-e5- small.https://huggingface.co/intfloat/multilingual-e5-small, 2022

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.377788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5af3439d-1701-46f2-a09a-af613f0d7b43 · outbound

This paper cites C-pack: Packaged resources to advance general chinese embedding, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation C-pack: Packaged resources to advance general chinese embedding, 2023

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.448927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 259467dd-eaa4-4a95-8f32-7c7ac85b18d7 · outbound

This paper cites bge-small-en.https://huggingface.co/BAAI/bge-small-en, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation bge-small-en.https://huggingface.co/BAAI/bge-small-en, 2023

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.466640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f42f09d8-2b70-483b-8262-21827d7daeb3 · outbound

This paper cites bge-small-en-v1.5.https://huggingface.co/BAAI/bge-small-en-v1.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation bge-small-en-v1.5.https://huggingface.co/BAAI/bge-small-en-v1

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.486479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 226288d1-4191-406e-80af-4925aa6c75ed · outbound

This paper cites bge-base-en.https://huggingface.co/BAAI/bge-base-en, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation bge-base-en.https://huggingface.co/BAAI/bge-base-en, 2023

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.593239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b038756a-9ae7-4fe8-b7e3-2af13d4178dc · outbound

This paper cites bge-base-en-v1.5.https://huggingface.co/BAAI/bge-base-en-v1.5, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation bge-base-en-v1.5.https://huggingface.co/BAAI/bge-base-en-v1.5, 2023

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.704193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1bd9907-5f0a-4290-bb3a-5d3faad91749 · outbound

This paper cites bge-large-en.https://huggingface.co/BAAI/bge-large-en, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation bge-large-en.https://huggingface.co/BAAI/bge-large-en, 2023

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.816154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73a1a2e6-6c85-4362-ab74-4f518a984ec3 · outbound

This paper cites bge-large-en-v1.5.https://huggingface.co/BAAI/bge-large-en-v1.5, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation bge-large-en-v1.5.https://huggingface.co/BAAI/bge-large-en-v1.5, 2023

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:45.331859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5840602f-18da-4e05-bd15-54be2bc7ec1d · outbound

This paper cites Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation, 2024.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation, 2024

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:31.923017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76f0bd3d-78e8-4f3d-9159-6124b0b868cc · outbound

This paper cites bge-m3.https://huggingface.co/BAAI/bge-m3, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation bge-m3.https://huggingface.co/BAAI/bge-m3, 2023

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:45.069213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1f5f7254-42d5-4f8a-8690-4865d57a1b09 · outbound

This paper cites nomic-embed-text-v1.https://huggingface.co/nomic-ai/ nomic-embed-text-v1, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation nomic-embed-text-v1.https://huggingface.co/nomic-ai/ nomic-embed-text-v1, 2023

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:44.948166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c1e88d07-96a8-4037-9d83-e4c17d244011 · outbound

This paper cites Morris, Brandon Duderstadt, and Andriy Mulyar.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Morris, Brandon Duderstadt, and Andriy Mulyar

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:44.656152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e0cdfb0c-633b-412c-804d-a217645f3187 · outbound

This paper cites nomic-embed-text-v1.5.https://huggingface.co/nomic-ai/ nomic-embed-text-v1.5, 2024.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation nomic-embed-text-v1.5.https://huggingface.co/nomic-ai/ nomic-embed-text-v1.5, 2024

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:44.418378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2b2b39c3-22fa-422a-b699-850c9fbd6408 · outbound

This paper cites nomic-bert-2048.https://huggingface.co/nomic-ai/ nomic-bert-2048, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation nomic-bert-2048.https://huggingface.co/nomic-ai/ nomic-bert-2048, 2023

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:44.220706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b35952ff-0833-45b6-b3ce-5cb68faa6b31 · outbound

This paper cites GLU Variants Improve Transformer.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation GLU Variants Improve Transformer

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:32.234616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6feec32c-e004-4a6c-981d-f40c2ef472c8 · outbound

This paper cites Unsupervised Dense Information Retrieval with Contrastive Learning.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Unsupervised Dense Information Retrieval with Contrastive Learning

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:32.274746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58649bae-3c38-444d-b43a-7f7f7932dd08 · outbound

This paper cites contriever.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation contriever

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:43.958974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f4ddd95f-ec02-4140-8385-a3c62c80da3e · outbound

This paper cites contriever- msmarco.https://huggingface.co/facebook/contriever-msmarco, 2022.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation contriever- msmarco.https://huggingface.co/facebook/contriever-msmarco, 2022

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:43.650190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 84ca7869-27a9-45ec-9d0a-d02c4e89d005 · outbound

This paper cites ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:32.480545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4897b1b3-edbb-4dd9-a04c-5d434587944a · outbound

This paper cites Chemberta-77m-mtr.https://huggingface.co/DeepChem/ ChemBERTa-77M-MTR, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Chemberta-77m-mtr.https://huggingface.co/DeepChem/ ChemBERTa-77M-MTR, 2023

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:43.403496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2c4c965d-ae9c-4b36-ba0f-7045e6337ce9 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:32.638059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b71aa27-bc03-485b-902a-13070ba3cd35 · outbound

This paper cites jina-embeddings-v2-base-en.https://huggingface.co/jinaai/ jina-embeddings-v2-base-en, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation jina-embeddings-v2-base-en.https://huggingface.co/jinaai/ jina-embeddings-v2-base-en, 2023

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:43.245536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 771612ef-3334-433a-a786-f1418285be34 · outbound

This paper cites Jina embeddings 2: 8192-token general-purpose text embeddings for long documents, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Jina embeddings 2: 8192-token general-purpose text embeddings for long documents, 2023

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:32.793196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f830af-e48c-40be-b259-a3b5a5f32288 · outbound

This paper cites jina-embeddings-v2-small-en.https://huggingface.co/jinaai/ jina-embeddings-v2-small-en, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation jina-embeddings-v2-small-en.https://huggingface.co/jinaai/ jina-embeddings-v2-small-en, 2023

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:43.116760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 27ee20d7-d428-4f61-8760-3d90ebdf8efb · outbound

This paper cites Matscibert: A materials domain lan- guage model.https://huggingface.co/m3rg-iitd/matscibert, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Matscibert: A materials domain lan- guage model.https://huggingface.co/m3rg-iitd/matscibert, 2021

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:42.959540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 44e455b7-9ddb-4041-88e7-662f46c4fa2b · outbound

This paper cites Gemini: General embeddings from mixed-initiative instruction.https: //huggingface.co/describeai/gemini, 2024.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Gemini: General embeddings from mixed-initiative instruction.https: //huggingface.co/describeai/gemini, 2024

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:42.779459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2faf3a45-76bc-4247-aea3-3d44444c42c0 · outbound

This paper cites Instructor-xl: Teaching models with instruction and feedback.https://huggingface.co/hkunlp/ instructor-xl, 2022.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Instructor-xl: Teaching models with instruction and feedback.https://huggingface.co/hkunlp/ instructor-xl, 2022

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:42.618788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6c5b92c1-e38f-47bf-8f80-221fcf8972c8 · outbound

This paper cites One Embedder, Any Task: Instruction-Finetuned Text Embeddings.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:33.302508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 053e752f-67d4-485b-ab22-1b62f259ec2a · outbound

This paper cites SciBERT: A Pretrained Language Model for Scientific Text.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation SciBERT: A Pretrained Language Model for Scientific Text

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:33.438166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70ae23e-376d-4565-9f82-3633205d1332 · outbound

This paper cites Scibert: A pretrained language model for scientific text.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Scibert: A pretrained language model for scientific text

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:42.504264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c31b73c0-1f83-4753-870a-b5008fa2c3d1 · outbound

This paper cites Specter: Document-level representation learning using citation-informed transformers.ACL, 2020.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Specter: Document-level representation learning using citation-informed transformers.ACL, 2020

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:42.388097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 077beffc-8edf-4aa2-95a8-f470f95c8857 · outbound

This paper cites allenai-specter.https://huggingface.co/sentence-transformers/ allenai-specter, 2020.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation allenai-specter.https://huggingface.co/sentence-transformers/ allenai-specter, 2020

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:42.283132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2c55463e-3915-4c8a-9cb9-f63d99392a6e · outbound

This paper cites Chemicalbert: Pretrained transformers for chemistry.https:// huggingface.co/recobo/chemical-bert-uncased, 2023.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Chemicalbert: Pretrained transformers for chemistry.https:// huggingface.co/recobo/chemical-bert-uncased, 2023

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:42.170397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d310291f-ae08-49be-a513-31a6d9791b5f · outbound

This paper cites paraphrase-multilingual-mpnet-base- v2.https://huggingface.co/sentence-transformers/ paraphrase-multilingual-mpnet-base-v2, 2021.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation paraphrase-multilingual-mpnet-base- v2.https://huggingface.co/sentence-transformers/ paraphrase-multilingual-mpnet-base-v2, 2021

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:41.995927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation acc93a78-e720-401d-a9db-b8799ea24488 · outbound

This paper cites New embedding models and api updates.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation New embedding models and api updates

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:41.761891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3184666b-5950-4af8-b2a6-7574bb7172f5 · outbound

This paper cites Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:33.983507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 552996b7-02f9-4885-afe2-dcc9b5113c25 · outbound

This paper cites Multi-paragraph segmentation of expository text.arXiv preprint cmp- lg/9406037, 1994.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Multi-paragraph segmentation of expository text.arXiv preprint cmp- lg/9406037, 1994

Reference 88

Resolution: verified exact; raw_fallback, observed 2026-08-07T04:09:38.754478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bc839944-4582-430a-ad6e-ba662282bcf0 · outbound

This paper cites Linear text segmentation: approaches, advances and applications.Proc.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Linear text segmentation: approaches, advances and applications.Proc

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:41.552165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5dd1ca90-30b1-4f72-9abe-bfa186f73ea1 · outbound

This paper cites A statistical model for domain-independent text segmentation.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation A statistical model for domain-independent text segmentation

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:41.333054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 555e8759-cc40-4b3e-b9b6-915b7ed11fb4 · outbound

This paper cites Modeling local coherence: An entity-based ap- proach.Computational Linguistics, 34(1):1–34, 2008.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Modeling local coherence: An entity-based ap- proach.Computational Linguistics, 34(1):1–34, 2008

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:41.086398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e12e4eae-45cf-4f8f-904f-eaba92ad9aa4 · outbound

This paper cites Text segmentation: A topic modeling perspective.Information Processing & Management, 47(4):528–544, 2011.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Text segmentation: A topic modeling perspective.Information Processing & Management, 47(4):528–544, 2011

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:40.892073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8e8ac78f-1d71-4042-b1fa-2844ad4b7f8e · outbound

This paper cites Text segmentation with topic models.Journal for Language Technology and Computational Linguistics, 27(1):47–69, 2012.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Text segmentation with topic models.Journal for Language Technology and Computational Linguistics, 27(1):47–69, 2012

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:40.696574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7f1076ed-6dfc-4a19-9a4e-05d3030c07ac · outbound

This paper cites Unsupervised text segmen- tation using semantic relatedness graphs.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Unsupervised text segmen- tation using semantic relatedness graphs

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:40.520510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cefbe3bc-220b-4ee6-b285-6b9836a11600 · outbound

This paper cites Unsupervised Topic Segmentation of Meetings with BERT Embeddings.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Unsupervised Topic Segmentation of Meetings with BERT Embeddings

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:34.577048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16fe214c-8e3a-444e-b221-8884a737b744 · outbound

This paper cites Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study

Reference 96

Resolution: verified exact; local_arxiv, observed 2026-08-07T04:09:38.497461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 418b5d2e-13e7-4e5a-aaa9-95e37a680ed1 · outbound

This paper cites SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation

Reference 97

Resolution: verified exact; local_arxiv, observed 2026-08-07T04:09:38.348223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5d59506c-791a-44e7-9e5b-7db4c648893b · outbound

This paper cites Text Segmentation as a Supervised Learning Task.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Text Segmentation as a Supervised Learning Task

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:34.846309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422a2608-aaa3-4cf4-91d2-1234401a2764 · outbound

This paper cites Text Segmentation by Cross Segment Attention.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Text Segmentation by Cross Segment Attention

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:34.925572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406d11e6-52b1-4648-9ba8-8689a745ab18 · outbound

This paper cites Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:35.026270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f74e37f-901c-4086-ab01-63c1027a5395 · outbound

This paper cites Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence.

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:35.123189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers