{"as_of":"2026-08-23T07:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cce3814d1951d129435c81ab9cd7390cd8a8ba3d756ffbd51db003358f7b89c0","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":88,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":88,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":88,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":88,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:41:27.852160Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":48,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-14T13:38:43.185685Z","title":"Scibert: Pretrained contextualized embeddings for scientific text","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.05760","last_updated":"2019-08-13T13:55:48Z","snapshot_observed_at":"2026-08-18T12:39:29.964282Z","submitted_at":"2019-08-13T13:55:48Z","title":"BioFLAIR: Pretrained Pooled Contextualized Embeddings for Biomedical Sequence Labeling Tasks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T13:38:43.185685Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/1908.05760"},"observation_digest":"sha256:7a338bdc02e20f71b7e91007d2ac2805ca370ea5aca2928a0a468b591bea5481","observation_id":"657007c8-fc95-49dd-8a89-21d3d3f8233b","resolution":{"observed_at":"2026-08-14T13:38:43.185685Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2211.09085","last_updated":"2022-11-16T18:06:33Z","snapshot_observed_at":"2026-08-17T08:35:32.078396Z","submitted_at":"2022-11-16T18:06:33Z","title":"Galactica: A Large Language Model for Science","version":1},"reference_index":144,"source":"arxiv_source","source_observed_at":"2026-05-13T05:53:21.810346Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2211.09085"},"observation_digest":"sha256:99ee12d1bd3e23a582baaae131700292a8639ac05ba4aece504aeb04576077d2","observation_id":"7ecbf4cc-d812-41c1-af62-53cb53b46057","resolution":{"observed_at":"2026-05-13T05:53:22.095267Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2302.12039","last_updated":"2026-05-11T20:32:53Z","snapshot_observed_at":"2026-08-14T02:22:52.103069Z","submitted_at":"2023-02-23T14:02:47Z","title":"Natural Language Processing in the Legal Domain","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-24T09:30:10.020006Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2302.12039"},"observation_digest":"sha256:ee55b290d8b09177ededbdbb34b6f0bfab7d2c329964f50f3ff6513911946173","observation_id":"ba989ca6-e50e-4a96-b782-de613534bf3b","resolution":{"observed_at":"2026-05-24T09:34:17.037599Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2401.02458","last_updated":"2026-04-29T07:43:10Z","snapshot_observed_at":"2026-08-21T07:29:41.199429Z","submitted_at":"2024-01-04T08:00:32Z","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-24T04:13:05.328492Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2401.02458"},"observation_digest":"sha256:0d497024c3ddeb47d3d89c58bfd22911e25c5e01b599cabef25d61d944919bb8","observation_id":"59c4aff1-17f0-4da9-b1a9-34cfdf6b08e9","resolution":{"observed_at":"2026-05-24T04:13:52.902011Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-12T18:51:31.663773Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.11266","last_updated":"2025-05-19T14:51:44Z","snapshot_observed_at":"2026-08-20T03:09:21.820083Z","submitted_at":"2024-11-18T03:45:34Z","title":"VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs","version":5},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T18:51:31.663773Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2411.11266"},"observation_digest":"sha256:d3bc7e7a07e96b24e889c777df87add2c053756cdcb2c0dd8dfbe27402447144","observation_id":"86a18418-fb82-412c-ac11-5c5dd432d218","resolution":{"observed_at":"2026-08-12T18:51:31.663773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-12T15:37:30.930594Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.14073","last_updated":"2024-11-21T12:38:23Z","snapshot_observed_at":"2026-08-18T18:04:23.055546Z","submitted_at":"2024-11-21T12:38:23Z","title":"Meaning at the Planck scale? Contextualized word embeddings for doing history, philosophy, and sociology of science","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T15:37:30.930594Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2411.14073"},"observation_digest":"sha256:f1a2dbb3bbd75044eaf21fb35a3f69bb3dc98576a0cbdea35b41d9235ec94383","observation_id":"ee5d7881-6030-4be6-81c1-1b84b929c81c","resolution":{"observed_at":"2026-08-12T15:37:30.930594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-12T14:50:03.058748Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.14877","last_updated":"2024-11-22T11:59:15Z","snapshot_observed_at":"2026-08-21T07:14:53.442972Z","submitted_at":"2024-11-22T11:59:15Z","title":"Astro-HEP-BERT: A bidirectional language model for studying the meanings of concepts in astrophysics and high energy physics","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T14:50:03.058748Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2411.14877"},"observation_digest":"sha256:38d9ce9d0ef1784b93ea69926d2498cfcf80b54bdcd3edc6e72dd26aaccef3b3","observation_id":"2b0f3784-c062-41d1-b7df-1ed6060dbfd1","resolution":{"observed_at":"2026-08-12T14:50:03.058748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-12T11:38:42.185962Z","title":"SciBERT: A pretrained language model for scientific text,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2411.18021","last_updated":"2024-11-27T03:31:14Z","snapshot_observed_at":"2026-08-16T17:03:44.830823Z","submitted_at":"2024-11-27T03:31:14Z","title":"Can bidirectional encoder become the ultimate winner for downstream applications of foundation models?","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T11:38:42.185962Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2411.18021"},"observation_digest":"sha256:a9ee4be022b78d857410b2aadecd9078b49aa8408a2ac9b3bb8fb5daa66de78d","observation_id":"2eefadff-e079-4f97-9a15-0a08510731a6","resolution":{"observed_at":"2026-08-12T11:38:42.185962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-12T11:29:40.169984Z","title":"arXiv preprint arXiv:1903.10676 (2019)","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.18157","last_updated":"2024-11-27T09:04:47Z","snapshot_observed_at":"2026-08-21T17:43:18.701712Z","submitted_at":"2024-11-27T09:04:47Z","title":"A survey on cutting-edge relation extraction techniques based on language models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T11:29:40.169984Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2411.18157"},"observation_digest":"sha256:496bb37d14576576bdcaf33bcbb6403fa4a8a71d27c5debddd1889802c245f0c","observation_id":"40e5d3a5-e2a1-4bcb-8871-5dee9e9f57dc","resolution":{"observed_at":"2026-08-12T11:29:40.169984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-12T11:05:09.545177Z","title":"Scibert: A pretrained language model for scientific text,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.00098","last_updated":"2025-09-07T23:58:18Z","snapshot_observed_at":"2026-08-18T18:04:12.217497Z","submitted_at":"2024-11-27T18:58:53Z","title":"Fine-Tuning Large Language Models for Scientific Text Classification: A Comparative Study","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T11:05:09.545177Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.00098"},"observation_digest":"sha256:8baa18bdd43856bfd893b4a2bfd2064f46c7d4bc2a8a9b26f7347b2079dda1b5","observation_id":"5caf9eef-3df4-4708-8200-9878a773aadf","resolution":{"observed_at":"2026-08-12T11:05:09.545177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-12T05:22:24.816351Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.00532","last_updated":"2025-01-23T20:59:08Z","snapshot_observed_at":"2026-08-18T08:12:15.203630Z","submitted_at":"2024-11-30T16:45:31Z","title":"ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:24.816351Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.00532"},"observation_digest":"sha256:c7a15c8d0df3205b42c7862e331527015433b4670bc82b25b2ee469f05f83555","observation_id":"d8aa25d9-bd59-4951-955d-64d2aea52f28","resolution":{"observed_at":"2026-08-12T05:22:24.816351Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T18:18:17.870512Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.08087","last_updated":"2024-12-16T02:37:34Z","snapshot_observed_at":"2026-08-18T17:05:00.140592Z","submitted_at":"2024-12-11T04:09:35Z","title":"From Division to Unity: A Large-Scale Study on the Emergence of Computational Social Science, 1990-2021","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T18:18:17.870512Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.08087"},"observation_digest":"sha256:2b0b5b507494b8646a6a91c5a496e7d0de9d8a77b1a5289ac7ce55aa8873c5ba","observation_id":"a9aa4ae9-1d47-42a8-82fe-24556afdec3d","resolution":{"observed_at":"2026-08-11T18:18:17.870512Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T18:05:02.223515Z","title":"SciBERT: A pretrained language model for scientific text,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.08255","last_updated":"2024-12-11T10:06:57Z","snapshot_observed_at":"2026-08-18T08:17:02.974303Z","submitted_at":"2024-12-11T10:06:57Z","title":"Accurate Medical Named Entity Recognition Through Specialized NLP Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T18:05:02.223515Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.08255"},"observation_digest":"sha256:e1308fd88f76602978a806fd5d3812da94b5518349c580ccae9196ed76900dd5","observation_id":"00723568-2033-4000-8df3-62858c0acbb8","resolution":{"observed_at":"2026-08-11T18:05:02.223515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T16:23:59.878852Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.10105","last_updated":"2025-05-25T12:05:44Z","snapshot_observed_at":"2026-08-14T20:41:07.235165Z","submitted_at":"2024-12-13T12:46:33Z","title":"MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T16:23:59.878852Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.10105"},"observation_digest":"sha256:475cd30a075732d2973bcbc874bc4c701621216361dae188e753c4df20f4b9a3","observation_id":"1e7d7eed-6af0-47d0-8509-116345e415bf","resolution":{"observed_at":"2026-08-11T16:23:59.878852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T15:00:19.891811Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11427","last_updated":"2024-12-21T19:22:53Z","snapshot_observed_at":"2026-08-20T14:19:00.340305Z","submitted_at":"2024-12-16T03:52:20Z","title":"Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T15:00:19.891811Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.11427"},"observation_digest":"sha256:a3514f92238700e0eadf1ca30df3600c9d9d12049782beab73d8d06806910e5a","observation_id":"e6ad23fc-be91-4e2d-ae8f-ba765c09f4cf","resolution":{"observed_at":"2026-08-11T15:00:19.891811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T14:46:50.587219Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.11671","last_updated":"2024-12-16T11:24:54Z","snapshot_observed_at":"2026-08-17T09:24:04.625367Z","submitted_at":"2024-12-16T11:24:54Z","title":"BioBridge: Unified Bio-Embedding with Bridging Modality in Code-Switched EMR","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T14:46:50.587219Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.11671"},"observation_digest":"sha256:07cad3ba3f6eafc474d6d3839398537aeca91a54167f74aa00df1a969388eb96","observation_id":"217b51ed-d92c-4dd3-820e-c1c721d7c53b","resolution":{"observed_at":"2026-08-11T14:46:50.587219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T13:50:04.602231Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.12744","last_updated":"2024-12-17T10:08:57Z","snapshot_observed_at":"2026-08-18T12:32:25.056334Z","submitted_at":"2024-12-17T10:08:57Z","title":"Your Next State-of-the-Art Could Come from Another Domain: A Cross-Domain Analysis of Hierarchical Text Classification","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T13:50:04.602231Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.12744"},"observation_digest":"sha256:034fbaa9729a7b4fa5438b2d5e3a32f98c3540d4502669913e5d4243f320a031","observation_id":"f1f75f92-2582-4e75-9721-4baca55d6483","resolution":{"observed_at":"2026-08-11T13:50:04.602231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T11:42:49.726298Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.15060","last_updated":"2024-12-19T17:08:11Z","snapshot_observed_at":"2026-08-19T06:04:18.235494Z","submitted_at":"2024-12-19T17:08:11Z","title":"ConfliBERT: A Language Model for Political Conflict","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T11:42:49.726298Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.15060"},"observation_digest":"sha256:1badee0df19ce86f2640ec9caa4ab00e3c075242d536f34d26716a8793a61062","observation_id":"ad153f14-6016-4419-8c46-f0ef5132db66","resolution":{"observed_at":"2026-08-11T11:42:49.726298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T15:01:44.519386Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.15256","last_updated":"2024-12-16T02:57:00Z","snapshot_observed_at":"2026-08-20T10:51:02.982077Z","submitted_at":"2024-12-16T02:57:00Z","title":"Structured Extraction of Real World Medical Knowledge using LLMs for Summarization and Search","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T15:01:44.519386Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.15256"},"observation_digest":"sha256:20986e5cff9492b09a4a6911da49ab01da508a30bbd7fc66a21caff9abeb92dd","observation_id":"9448b9ae-9805-4342-a45e-e57d6e6dc5cc","resolution":{"observed_at":"2026-08-11T15:01:44.519386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T14:43:49.673164Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.15258","last_updated":"2024-12-16T12:04:22Z","snapshot_observed_at":"2026-08-16T00:54:29.694936Z","submitted_at":"2024-12-16T12:04:22Z","title":"DisEmbed: Transforming Disease Understanding through Embeddings","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T14:43:49.673164Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.15258"},"observation_digest":"sha256:89fd961defbb50b0e2e025bf3f7f408b2598db99a78a3c44010c3cf457887407","observation_id":"1bf5fce4-5c88-4a5f-a63b-20499fd2f74a","resolution":{"observed_at":"2026-08-11T14:43:49.673164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T10:25:34.313611Z","title":"SciBERT: A pre-trained language model for scientific text","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.16701","last_updated":"2025-08-30T16:41:13Z","snapshot_observed_at":"2026-08-17T16:25:56.761099Z","submitted_at":"2024-12-21T16:59:00Z","title":"AlzheimerRAG: Multimodal Retrieval Augmented Generation for Clinical Use Cases using PubMed articles","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T10:25:34.313611Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.16701"},"observation_digest":"sha256:1ba9caeb73ab05aea11aaad0b307225363efd6e5a6b49cba2a1c0353c64bb531","observation_id":"c16fe41c-bdc4-45a8-8409-20ee1f44b2b5","resolution":{"observed_at":"2026-08-11T10:25:34.313611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T01:03:27.888954Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.19048","last_updated":"2025-01-23T16:01:22Z","snapshot_observed_at":"2026-08-19T17:13:32.469261Z","submitted_at":"2024-12-26T04:05:28Z","title":"Jasper and Stella: distillation of SOTA embedding models","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T01:03:27.888954Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.19048"},"observation_digest":"sha256:5658039d0ad463af433ec3ba063c6979f7a11ba8fb91a4107e791eab615bfc9b","observation_id":"ee8758b2-86f9-4d4d-aa65-b74daace655e","resolution":{"observed_at":"2026-08-11T01:03:27.888954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-11T00:45:00.227530Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.19346","last_updated":"2024-12-26T20:24:35Z","snapshot_observed_at":"2026-08-19T07:44:25.365271Z","submitted_at":"2024-12-26T20:24:35Z","title":"Semi-Supervised Learning from Small Annotated Data and Large Unlabeled Data for Fine-grained PICO Entity Recognition","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T00:45:00.227530Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.19346"},"observation_digest":"sha256:ac39f3b57fa5ef7b09330b69a74fd528d8eb4482d0cf317387157d1c3fe6d39a","observation_id":"9d44ee08-c664-4993-8bba-865df878b4a1","resolution":{"observed_at":"2026-08-11T00:45:00.227530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2412.19363","last_updated":"2026-04-17T16:20:32Z","snapshot_observed_at":"2026-08-15T12:54:50.211728Z","submitted_at":"2024-12-26T22:06:29Z","title":"Large Language Models for Market Research: A Data-augmentation Approach","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-05-23T07:10:49.774832Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2412.19363"},"observation_digest":"sha256:fa95119d82111213b9b16d48d4e8c66c47a61135fbc08443ece220bbff7c1c47","observation_id":"4f3a9073-0f28-47aa-b451-4cec9787877f","resolution":{"observed_at":"2026-05-23T07:12:41.404585Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-10T22:56:55.796835Z","title":"& Cohan, A","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.00367","last_updated":"2024-12-31T09:42:53Z","snapshot_observed_at":"2026-08-13T15:07:50.003288Z","submitted_at":"2024-12-31T09:42:53Z","title":"Who Gets Recommended? Investigating Gender, Race, and Country Disparities in Paper Recommendations from Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T22:56:55.796835Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2501.00367"},"observation_digest":"sha256:a9887ded752f46f25609f5816e947aea580d4cc6c84f70b8fea5f3230a6d22a3","observation_id":"0dffc77d-2f53-449e-8b4a-9f6ee3b2e8b7","resolution":{"observed_at":"2026-08-10T22:56:55.796835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-10T19:19:28.324065Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2501.10282","last_updated":"2025-01-25T12:33:22Z","snapshot_observed_at":"2026-08-14T19:06:56.404781Z","submitted_at":"2025-01-17T16:21:18Z","title":"Computational Protein Science in the Era of Large Language Models (LLMs)","version":2},"reference_index":186,"source":"pdf_text","source_observed_at":"2026-08-10T19:19:28.324065Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2501.10282"},"observation_digest":"sha256:49ae0c0e2e81dc3403726a0528cee0026fb14a927169886a7a398d799e8bfffb","observation_id":"f2d32d8c-752d-4003-b57f-999666950387","resolution":{"observed_at":"2026-08-10T19:19:28.324065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-10T15:17:36.546427Z","title":"Beltagy, K","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2501.14288","last_updated":"2025-01-31T02:10:36Z","snapshot_observed_at":"2026-08-18T12:42:34.603904Z","submitted_at":"2025-01-24T07:07:37Z","title":"A Comprehensive Framework for Semantic Similarity Analysis of Human and AI-Generated Text Using Transformer Architectures and Ensemble Techniques","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T15:17:36.546427Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2501.14288"},"observation_digest":"sha256:8f4f04079e8ee40bb9b108c8c2afdb23728698b98efd6e809e66f85d6a6e6ad8","observation_id":"74fe20e1-69f1-4ae5-a7df-309b86279615","resolution":{"observed_at":"2026-08-10T15:17:36.546427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-08T11:58:12.399103Z","title":"arXiv preprint arXiv:1903.10676 (2019)","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.07683","last_updated":"2025-02-11T16:35:04Z","snapshot_observed_at":"2026-08-18T12:43:24.207532Z","submitted_at":"2025-02-11T16:35:04Z","title":"exHarmony: Authorship and Citations for Benchmarking the Reviewer Assignment Problem","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T11:58:12.399103Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2502.07683"},"observation_digest":"sha256:c2d5410925961e4829e7bc6222fbcf97c4025b56e3657c075ce5aed64f99a0b8","observation_id":"c4e8bc32-a1e1-4b65-a07a-ef1a398132ed","resolution":{"observed_at":"2026-08-08T11:58:12.399103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T11:41:27.852160Z","title":"& Cohan, A","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.14849","last_updated":"2025-04-21T04:03:32Z","snapshot_observed_at":"2026-08-19T00:13:49.153392Z","submitted_at":"2025-04-21T04:03:32Z","title":"Language Models for Materials Discovery and Sustainability: Progress, Challenges, and Opportunities","version":1},"reference_index":108,"source":"pdf_text","source_observed_at":"2026-08-16T11:41:27.852160Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2504.14849"},"observation_digest":"sha256:959d8905fadaf0cb6d5d40ba9882025f91d3b339095a3e5b90de589bdf6af440","observation_id":"8726683a-2a1e-4eab-9e4f-c681d3b4b659","resolution":{"observed_at":"2026-08-16T11:41:27.852160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T10:07:10.085524Z","title":"Scibert: A pretrained language model for scientific text,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2504.19021","last_updated":"2025-09-07T23:37:16Z","snapshot_observed_at":"2026-08-18T12:33:54.715065Z","submitted_at":"2025-04-26T21:06:49Z","title":"Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Voting","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T10:07:10.085524Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2504.19021"},"observation_digest":"sha256:af2b9ceb468e47758b1cb143908ef22833ec8406cbda46e2bd1c9f9fa23b2815","observation_id":"e63ce8fc-9cae-4d27-967c-41af186cd381","resolution":{"observed_at":"2026-08-16T10:07:10.085524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T05:00:11.684213Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.00061","last_updated":"2025-04-30T14:53:09Z","snapshot_observed_at":"2026-08-16T04:53:21.760035Z","submitted_at":"2025-04-30T14:53:09Z","title":"Enhancing Security and Strengthening Defenses in Automated Short-Answer Grading Systems","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T05:00:11.684213Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.00061"},"observation_digest":"sha256:aa9c0882d5767e52de0541d19bf974017fdba7e267c4eb4f670ec3b681113f56","observation_id":"f79d4e17-475e-49ae-80ac-3c9da2881f56","resolution":{"observed_at":"2026-08-16T05:00:11.684213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T10:53:48.764963Z","title":"Scibert: A pre- trained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.01435","last_updated":"2025-04-23T18:38:41Z","snapshot_observed_at":"2026-08-18T12:15:41.407160Z","submitted_at":"2025-04-23T18:38:41Z","title":"AdaParse: An Adaptive Parallel PDF Parsing and Resource Scaling Engine","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-16T10:53:48.764963Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.01435"},"observation_digest":"sha256:6d9bdefec9497c24d92243495ad5233a680e1fc683751984cef35343fb986156","observation_id":"c9d77782-fb47-4c3c-8239-334c159af668","resolution":{"observed_at":"2026-08-16T10:53:48.764963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T04:11:57.257600Z","title":"Scibert: A pre- trained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.01823","last_updated":"2025-05-03T14:03:42Z","snapshot_observed_at":"2026-08-18T12:36:11.773985Z","submitted_at":"2025-05-03T14:03:42Z","title":"PhytoSynth: Leveraging Multi-modal Generative Models for Crop Disease Data Generation with Novel Benchmarking and Prompt Engineering Approach","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T04:11:57.257600Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.01823"},"observation_digest":"sha256:c30b3f469ec71a5eff1d15295d33864d671dde93f18d9cbde6048d5cfc772ff9","observation_id":"3469bb69-ce48-477c-868b-726342036078","resolution":{"observed_at":"2026-08-16T04:11:57.257600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T00:01:40.690344Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.03147","last_updated":"2025-05-06T03:43:12Z","snapshot_observed_at":"2026-08-18T12:41:47.278965Z","submitted_at":"2025-05-06T03:43:12Z","title":"Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports using Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:40.690344Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.03147"},"observation_digest":"sha256:2c7a1f62c887dfb62265d3410b0ce5a35ca984dce3db984054088c6108036d17","observation_id":"a67bef2e-2cb3-4743-969c-b8755fc0477f","resolution":{"observed_at":"2026-08-16T00:01:40.690344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-15T23:56:01.750771Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.03418","last_updated":"2025-05-06T10:53:58Z","snapshot_observed_at":"2026-08-19T05:02:57.764918Z","submitted_at":"2025-05-06T10:53:58Z","title":"Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:56:01.750771Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.03418"},"observation_digest":"sha256:ad4036149b22a9d9e685edc17e70bdd3652235f177d94c8e6e89e956bdde3046","observation_id":"699a9726-c4ce-4fb9-840a-6ac88aeb1e3d","resolution":{"observed_at":"2026-08-15T23:56:01.750771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T05:06:38.802873Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.04634","last_updated":"2025-04-30T09:26:28Z","snapshot_observed_at":"2026-08-18T12:41:02.503766Z","submitted_at":"2025-04-30T09:26:28Z","title":"MatMMFuse: Multi-Modal Fusion model for Material Property Prediction","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T05:06:38.802873Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.04634"},"observation_digest":"sha256:1d77e5357e05dd2dd82da1c7c25c067c86722ebd19020449abd3919dfc4d70b8","observation_id":"a0d3820e-bca3-43dc-bbc5-e3e41a8bdc7b","resolution":{"observed_at":"2026-08-16T05:06:38.802873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T00:50:20.303709Z","title":"SciBERT: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.04643","last_updated":"2025-05-05T16:39:24Z","snapshot_observed_at":"2026-08-19T15:45:33.050411Z","submitted_at":"2025-05-05T16:39:24Z","title":"Prediction-powered estimators for finite population statistics in highly imbalanced textual data: Public hate crime estimation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T00:50:20.303709Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.04643"},"observation_digest":"sha256:8e5560863e8b1b5f936a464480b4ee5e8eeb568e5fdc52647e240dc9068082cc","observation_id":"446b101f-9130-488d-9bad-43690a80bd3d","resolution":{"observed_at":"2026-08-16T00:50:20.303709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-16T00:48:47.485309Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.05494","last_updated":"2025-05-05T15:17:27Z","snapshot_observed_at":"2026-08-21T06:20:26.571975Z","submitted_at":"2025-05-05T15:17:27Z","title":"An Automated LLM-based Pipeline for Asset-Level Database Creation to Assess Deforestation Impact","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T00:48:47.485309Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.05494"},"observation_digest":"sha256:a6c5ffe633fe844c54a208bf2ff96fb37244a4853111ab603dd44779b01a5a77","observation_id":"c5ad8b71-ae8e-43bd-9a0f-72d279e928b6","resolution":{"observed_at":"2026-08-16T00:48:47.485309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-15T22:31:28.392192Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.06964","last_updated":"2025-05-17T05:08:12Z","snapshot_observed_at":"2026-08-17T11:43:49.709641Z","submitted_at":"2025-05-11T12:32:57Z","title":"Bridging AI and Carbon Capture: A Dataset for LLMs in Ionic Liquids and CBE Research","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T22:31:28.392192Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.06964"},"observation_digest":"sha256:f8c342d926c674243aad9afe5f099747a66e5eaffc67f40a6fec46ec0be44dba","observation_id":"58e167e7-b519-42a5-849e-1a791def3ecc","resolution":{"observed_at":"2026-08-15T22:31:28.392192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-15T23:00:37.934146Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.07865","last_updated":"2025-05-09T06:47:23Z","snapshot_observed_at":"2026-08-18T12:44:07.256085Z","submitted_at":"2025-05-09T06:47:23Z","title":"CellVerse: Do Large Language Models Really Understand Cell Biology?","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:00:37.934146Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.07865"},"observation_digest":"sha256:99ce089cd2c31a88acf8fe5186e5ef6eeb159d8193304166c66037e579c962f3","observation_id":"6aec26ff-f336-4e51-bc90-53093af342f2","resolution":{"observed_at":"2026-08-15T23:00:37.934146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-15T21:26:50.243073Z","title":"(77) Wan, Y.; Xie, T.; Wu, N.; Zhang, W.; Kit, C.; Hoex, B","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.13494","last_updated":"2025-05-15T00:20:42Z","snapshot_observed_at":"2026-08-21T20:26:40.206607Z","submitted_at":"2025-05-15T00:20:42Z","title":"Polymer Data Challenges in the AI Era: Bridging Gaps for Next-Generation Energy Materials","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T21:26:50.243073Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.13494"},"observation_digest":"sha256:bf3d2032624dcec9b1f14065e5fdd65722a420ec981be9169329311c55de8036","observation_id":"6d8ea04b-9be1-4ad1-9169-0dfd7b62e93e","resolution":{"observed_at":"2026-08-15T21:26:50.243073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-07T14:16:32.723398Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.19501","last_updated":"2025-06-02T21:31:08Z","snapshot_observed_at":"2026-08-19T14:21:57.125518Z","submitted_at":"2025-05-26T04:28:46Z","title":"Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:16:32.723398Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.19501"},"observation_digest":"sha256:0dbec32041c89b3a15c91f07c32c2613d4ffd1e1a432858982062aabd3acfed2","observation_id":"ec5f7560-c4fe-4f4e-b909-30935d26a96c","resolution":{"observed_at":"2026-08-07T14:16:32.723398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-07T13:21:18.036986Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.22068","last_updated":"2025-05-28T07:47:46Z","snapshot_observed_at":"2026-08-22T10:56:31.135813Z","submitted_at":"2025-05-28T07:47:46Z","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:18.036986Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2505.22068"},"observation_digest":"sha256:7ad129482b6b4b36bbae3ec66427569e1d8d8c33717979e132ca6371fb4febb9","observation_id":"7ca393dc-3240-484f-820c-5427b2b5b067","resolution":{"observed_at":"2026-08-07T13:21:18.036986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-07T12:00:30.973587Z","title":"A., McDermott, M","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.06340","last_updated":"2025-06-01T05:07:51Z","snapshot_observed_at":"2026-08-16T22:40:28.413539Z","submitted_at":"2025-06-01T05:07:51Z","title":"Structured Semantics from Unstructured Notes: Language Model Approaches to EHR-Based Decision Support","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T12:00:30.973587Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.06340"},"observation_digest":"sha256:963f82b3d853a13a95642ffd97dd2f4d9dff92414d752e2979933d2640bedb62","observation_id":"9c03f72f-9f90-45a9-8b70-7fa1f185de35","resolution":{"observed_at":"2026-08-07T12:00:30.973587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-07T05:38:22.044497Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.11115","last_updated":"2025-06-09T04:59:13Z","snapshot_observed_at":"2026-08-15T02:58:15.508213Z","submitted_at":"2025-06-09T04:59:13Z","title":"Incorporating Domain Knowledge into Materials Tokenization","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T05:38:22.044497Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.11115"},"observation_digest":"sha256:0fe146db4844a529a7fa9093a3b10c049f57b9526775051107ad6c0554e616c3","observation_id":"0422650f-48fa-460f-92c6-99381e1523cc","resolution":{"observed_at":"2026-08-07T05:38:22.044497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-07T04:07:41.978556Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.11478","last_updated":"2025-06-13T06:00:03Z","snapshot_observed_at":"2026-08-20T16:26:11.694835Z","submitted_at":"2025-06-13T06:00:03Z","title":"ImmunoFOMO: Are Language Models missing what oncologists see?","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T04:07:41.978556Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.11478"},"observation_digest":"sha256:e4d6f42810ca936cd9f106b2b093da4686c5f54b35b75453fc3317ef208da335","observation_id":"e451e210-4863-414d-8d53-769a157316d0","resolution":{"observed_at":"2026-08-07T04:07:41.978556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-07T04:09:33.438166Z","title":"Scibert: A pretrained language model for scientific text.arXiv preprint arXiv:1903.10676, 2019","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.17277","last_updated":"2025-06-13T07:44:53Z","snapshot_observed_at":"2026-08-17T05:06:27.338886Z","submitted_at":"2025-06-13T07:44:53Z","title":"Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T04:09:33.438166Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.17277"},"observation_digest":"sha256:b652475b4b2583d303dde3620953af32a246fd9ec1c210d5e84b0594144b78f8","observation_id":"053e752f-67d4-485b-ab22-1b62f259ec2a","resolution":{"observed_at":"2026-08-07T04:09:33.438166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T23:09:33.297646Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.19613","last_updated":"2025-06-24T13:31:44Z","snapshot_observed_at":"2026-08-12T21:57:54.607669Z","submitted_at":"2025-06-24T13:31:44Z","title":"Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:09:33.297646Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.19613"},"observation_digest":"sha256:ecfd8f20b65ec82b42dfde6593b850517affbe0ddaa95bb65bb7bc8363953c8b","observation_id":"a1fc38bb-16e7-4ee7-9e94-45a8c056856a","resolution":{"observed_at":"2026-08-06T23:09:33.297646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T22:24:46.635272Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.21763","last_updated":"2025-07-21T06:49:51Z","snapshot_observed_at":"2026-08-18T23:59:41.516632Z","submitted_at":"2025-06-26T20:44:51Z","title":"THE-Tree: Can Tracing Historical Evolution Enhance Scientific Verification and Reasoning?","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:24:46.635272Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.21763"},"observation_digest":"sha256:964d025db441e1bbddd991daf65f545c1305d6bd195345604465a64cbe80e865","observation_id":"b8b38c0d-a142-4908-a7ff-d2cfcc0c91b6","resolution":{"observed_at":"2026-08-06T22:24:46.635272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T23:00:37.010057Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.22497","last_updated":"2025-06-25T03:57:40Z","snapshot_observed_at":"2026-08-18T12:32:51.094341Z","submitted_at":"2025-06-25T03:57:40Z","title":"Peer Review as Structured Commentary: Immutable Identity, Public Dialogue, and Reproducible Scholarship","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T23:00:37.010057Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.22497"},"observation_digest":"sha256:10b26f769848d0ab7b813bbc202d58882ac3b3fdaf07d175a56b23d0cf12e607","observation_id":"f3c921be-2e92-4c52-a3af-98748209927d","resolution":{"observed_at":"2026-08-06T23:00:37.010057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T21:54:43.482841Z","title":"Scibert: Pretrained contextualized embed- dings for scientific text.CoRR, abs/1903.10676, 2019","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.23145","last_updated":"2025-06-29T08:53:23Z","snapshot_observed_at":"2026-08-18T12:49:10.552054Z","submitted_at":"2025-06-29T08:53:23Z","title":"Forget-MI: Machine Unlearning for Forgetting Multimodal Information in Healthcare Settings","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:54:43.482841Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.23145"},"observation_digest":"sha256:c03623957f5043656a9d88e3bafbc3ede17d1ff49fb785d0f5ba6a30f317b17c","observation_id":"feac2450-003e-4caa-8bfb-55e0957f5b2c","resolution":{"observed_at":"2026-08-06T21:54:43.482841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T21:51:16.984180Z","title":"SciBERT: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.23366","last_updated":"2025-06-29T18:55:04Z","snapshot_observed_at":"2026-08-18T12:44:49.806006Z","submitted_at":"2025-06-29T18:55:04Z","title":"Density, asymmetry and citation dynamics in scientific literature","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T21:51:16.984180Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2506.23366"},"observation_digest":"sha256:76a004f199e0c6afda4279136c7322fa3bb3e42997212ce4179479830b7517d0","observation_id":"403f2c30-fc03-436c-bc16-337d98474cd1","resolution":{"observed_at":"2026-08-06T21:51:16.984180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2507.03674","last_updated":"2026-05-20T21:34:02Z","snapshot_observed_at":"2026-08-06T11:13:03.059687Z","submitted_at":"2025-07-04T15:51:07Z","title":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-22T12:39:27.803077Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2507.03674"},"observation_digest":"sha256:ef2803aa6a1c878da72b24c5af96738b97193d66228f209b62ca8bc2247dce1a","observation_id":"7fb93583-64c4-4dba-bd7e-1587b4bc9089","resolution":{"observed_at":"2026-05-22T12:41:33.494485Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T15:53:50.300656Z","title":"& Cohan, A","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.14741","last_updated":"2025-07-19T20:19:21Z","snapshot_observed_at":"2026-08-18T12:32:20.899540Z","submitted_at":"2025-07-19T20:19:21Z","title":"Disparities in Peer Review Tone and the Role of Reviewer Anonymity","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T15:53:50.300656Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2507.14741"},"observation_digest":"sha256:6216fbb3b1e388c5a2a9cfe1299fa555ec2bec6afd7bf80e6ebf07071d62af20","observation_id":"635b7062-a728-4c37-9f92-b4bb027a9797","resolution":{"observed_at":"2026-08-06T15:53:50.300656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T15:36:37.692524Z","title":"Beltagy, K","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.16852","last_updated":"2025-07-21T09:22:39Z","snapshot_observed_at":"2026-08-21T09:44:18.396552Z","submitted_at":"2025-07-21T09:22:39Z","title":"SynthCTI: LLM-Driven Synthetic CTI Generation to enhance MITRE Technique Mapping","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T15:36:37.692524Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2507.16852"},"observation_digest":"sha256:9496affabc5054c7341b60d27e64c2c8a7921aa2ad9d877f9b16f1b728bf551d","observation_id":"5e59ef9f-cd2b-4602-b7c2-8c88bd6250f2","resolution":{"observed_at":"2026-08-06T15:36:37.692524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T14:25:56.586406Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2507.19407","last_updated":"2025-08-06T10:08:06Z","snapshot_observed_at":"2026-08-16T23:35:15.240031Z","submitted_at":"2025-07-25T16:15:00Z","title":"Towards Domain Specification of Embedding Models in Medicine","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T14:25:56.586406Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2507.19407"},"observation_digest":"sha256:ae921afb9dceebcc0d5dcc9a31cd5b748b17cdc420eb5d1201f7f65523e34c02","observation_id":"c622b0d3-9c1a-437c-b815-2929d87380f9","resolution":{"observed_at":"2026-08-06T14:25:56.586406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T11:48:01.510730Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.22387","last_updated":"2025-07-30T05:17:35Z","snapshot_observed_at":"2026-08-20T08:33:54.130993Z","submitted_at":"2025-07-30T05:17:35Z","title":"PATENTWRITER: A Benchmarking Study for Patent Drafting with LLMs","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T11:48:01.510730Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2507.22387"},"observation_digest":"sha256:36a291bd267b72c83809b47358c37ed9181b9e5f8b37b235f1858d75aae2f8c2","observation_id":"5444c1bf-4636-4d55-9f13-1aaa8508bbf9","resolution":{"observed_at":"2026-08-06T11:48:01.510730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-06T15:55:33.059775Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2507.22913","last_updated":"2025-07-19T15:32:46Z","snapshot_observed_at":"2026-08-21T01:03:44.371076Z","submitted_at":"2025-07-19T15:32:46Z","title":"A Hybrid Framework for Subject Analysis: Integrating Embedding-Based Regression Models with Large Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:33.059775Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2507.22913"},"observation_digest":"sha256:8e211a713dd76d4b6f7587d8086d9286d5fdb24348e4eeb2912c6d621f27d678","observation_id":"872ded3f-143f-410f-ba5f-443ab29760f9","resolution":{"observed_at":"2026-08-06T15:55:33.059775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T15:32:33.933828Z","title":"arXiv preprint arXiv:1903.10676 (2019)","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2509.02581","last_updated":"2026-06-18T10:35:57Z","snapshot_observed_at":"2026-08-06T21:17:50.512643Z","submitted_at":"2025-08-27T09:46:50Z","title":"Charting the Future of Scholarly Knowledge with AI: A Community Perspective","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T15:32:33.933828Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2509.02581"},"observation_digest":"sha256:a68f5e8b2a8352641d8b5725edaa29721e4524dc1df820f4648ebeae69fb9c50","observation_id":"6d257a51-9334-4934-85f5-2fd5952f22e8","resolution":{"observed_at":"2026-08-05T15:32:33.933828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-04T23:02:46.486628Z","title":"Scibert: A pretrained language model for scientific text","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2509.06855","last_updated":"2025-09-08T16:23:44Z","snapshot_observed_at":"2026-08-06T11:22:19.306837Z","submitted_at":"2025-09-08T16:23:44Z","title":"Seeing the Forest Through the Trees: Knowledge Retrieval for Streamlining Particle Physics Analysis","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-04T23:02:46.486628Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2509.06855"},"observation_digest":"sha256:1cb8940066b8e7d6df2793d80aaca9b4403b15df4b0cb76e285da9bebf1897e5","observation_id":"1348b25f-c1d6-4e51-9932-c6d0cc80c0ce","resolution":{"observed_at":"2026-08-04T23:02:46.486628Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-04T19:24:52.985321Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09272","last_updated":"2025-09-11T09:02:15Z","snapshot_observed_at":"2026-08-20T17:33:20.364005Z","submitted_at":"2025-09-11T09:02:15Z","title":"Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T19:24:52.985321Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2509.09272"},"observation_digest":"sha256:fec518d30f4c58a3e48867dad43cd21d8e5b27d36caed83be05ec60be9236989","observation_id":"01f02e82-cc7e-40ac-8c46-6d5016308cb4","resolution":{"observed_at":"2026-08-04T19:24:52.985321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-04T19:27:04.819129Z","title":"Beltagy , author K","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2509.09303","last_updated":"2025-09-11T09:44:16Z","snapshot_observed_at":"2026-08-18T01:53:23.029281Z","submitted_at":"2025-09-11T09:44:16Z","title":"From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-04T19:27:04.819129Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2509.09303"},"observation_digest":"sha256:c377948f7f29ddfbcc3505200511dac66972e72767412132874cfe5c40a1406a","observation_id":"ac93bb96-ecda-4576-9775-28db84625cb8","resolution":{"observed_at":"2026-08-04T19:27:04.819129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2509.20374","last_updated":"2026-04-26T17:39:58Z","snapshot_observed_at":"2026-08-13T19:20:38.694867Z","submitted_at":"2025-09-19T22:21:26Z","title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-18T15:05:37.519850Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2509.20374"},"observation_digest":"sha256:83644b9fb77efaceeb05d7febea0fb86afe6c14d0ae986b77721be5c220b45c0","observation_id":"11690c7c-d8fb-4952-98ca-d058edc52e8b","resolution":{"observed_at":"2026-05-18T15:06:32.081448Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-04T07:36:28.435311Z","title":"Scibert: Pretrained language model for scientific text, in: EMNLP","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.25370","last_updated":"2026-07-08T11:43:10Z","snapshot_observed_at":"2026-08-19T03:25:17.347209Z","submitted_at":"2025-10-29T10:41:03Z","title":"Monitoring Transformative Technological Convergence Through LLM-Extracted Semantic Entity Triple Graphs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T07:36:28.435311Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2510.25370"},"observation_digest":"sha256:ee81eff254ccfcb994f09470d0ee991e0da4b8df67b5f6c2a866bfb16dfec72b","observation_id":"913d57e9-ee50-4532-8596-39830f5c6ad9","resolution":{"observed_at":"2026-08-04T07:36:28.435311Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-03T23:50:33.804685Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.04068","last_updated":"2026-07-14T03:46:15Z","snapshot_observed_at":"2026-08-18T12:42:36.154558Z","submitted_at":"2025-11-06T05:19:18Z","title":"TXL Fusion: A Hybrid Machine Learning Framework Integrating Chemical Heuristics and Large Language Models for Topological Materials Discovery","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T23:50:33.804685Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2511.04068"},"observation_digest":"sha256:3508448bd02aa9a74dbb286a35b1b6ca8b2909c0c2763c38118ace1cdb80a586","observation_id":"cc86ade8-8555-46a6-a996-a4f005064688","resolution":{"observed_at":"2026-08-03T23:50:33.804685Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-03T22:24:05.453477Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.10887","last_updated":"2026-06-19T10:45:44Z","snapshot_observed_at":"2026-08-17T20:05:32.097748Z","submitted_at":"2025-11-14T01:49:24Z","title":"MedPath: Multi-Domain Cross-Vocabulary Hierarchical Paths for Biomedical Entity Linking","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-03T22:24:05.453477Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2511.10887"},"observation_digest":"sha256:e1d8ebe29d3ca20fd759e13c812871288c7d3fbfb3f327daf98dbd25af4e7c64","observation_id":"5433cdbf-35ad-42af-8748-63833e403901","resolution":{"observed_at":"2026-08-03T22:24:05.453477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2601.00264","last_updated":"2026-05-06T07:55:20Z","snapshot_observed_at":"2026-08-19T22:55:04.741258Z","submitted_at":"2026-01-01T08:54:51Z","title":"S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text Understanding","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-16T18:16:45.825451Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2601.00264"},"observation_digest":"sha256:fcff57a1d40b5430a0520571ee7760cb5335ad8a4cc71b9f0967d98203567b14","observation_id":"87c2ce51-4664-493b-ab96-b67b3fb0580c","resolution":{"observed_at":"2026-05-16T18:18:14.434515Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2604.06208","last_updated":"2026-03-16T05:09:20Z","snapshot_observed_at":"2026-07-06T22:54:44.656835Z","submitted_at":"2026-03-16T05:09:20Z","title":"Extracting Breast Cancer Phenotypes from Clinical Notes: Comparing LLMs with Classical Ontology Methods","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-15T11:04:52.642119Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2604.06208"},"observation_digest":"sha256:d9dc6cb7e98e61a53f8fad3ecea12d28a25e95d3041b9186ef828fe7817d06fc","observation_id":"a0cf17bb-5c31-4078-bc1f-76de6cd466bc","resolution":{"observed_at":"2026-05-15T11:05:29.211427Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2604.10895","last_updated":"2026-07-21T11:47:58Z","snapshot_observed_at":"2026-08-21T09:11:14.985533Z","submitted_at":"2026-04-13T01:56:00Z","title":"Teaching Robots to Interpret Social Interactions through Lexically-guided Dynamic Graph Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T16:35:50.922789Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2604.10895"},"observation_digest":"sha256:eb68cf028c1c4473173bd2e8da79b1a9a4009f33e743c114faf03f4d18bc8fac","observation_id":"37ba0337-b1ef-48ff-9d5d-cefb6e8ae250","resolution":{"observed_at":"2026-05-11T08:30:57.930434Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2604.10895","last_updated":"2026-07-21T11:47:58Z","snapshot_observed_at":"2026-08-21T09:11:14.985533Z","submitted_at":"2026-04-13T01:56:00Z","title":"Teaching Robots to Interpret Social Interactions through Lexically-guided Dynamic Graph Learning","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-21T00:46:23.177416Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2604.10895"},"observation_digest":"sha256:a17a10480b0390f3b2af43d1e09d1743568ebb307e32d2a75a00bf00a442f2ec","observation_id":"8e626888-4148-49c1-945c-322f2833ced4","resolution":{"observed_at":"2026-05-21T00:49:18.758097Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-02T16:25:42.584602Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2604.10895","last_updated":"2026-07-21T11:47:58Z","snapshot_observed_at":"2026-08-21T09:11:14.985533Z","submitted_at":"2026-04-13T01:56:00Z","title":"Teaching Robots to Interpret Social Interactions through Lexically-guided Dynamic Graph Learning","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T16:25:42.584602Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2604.10895"},"observation_digest":"sha256:252271c763859c97979536fa3d2387918593d39e0c4fde62fb8ffcb0ef57972a","observation_id":"7943c962-11b7-4411-9bc5-fa14130c823a","resolution":{"observed_at":"2026-08-02T16:25:42.584602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2604.17393","last_updated":"2026-04-21T16:02:36Z","snapshot_observed_at":"2026-08-02T19:33:57.564794Z","submitted_at":"2026-04-19T11:42:55Z","title":"Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-05-10T06:07:15.198716Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2604.17393"},"observation_digest":"sha256:05c4754b5f309cbdb4498f5d6a303697a08f2497dbcb19c226fbf948768266d2","observation_id":"b1c7b138-c1a2-4b67-adf8-f38130826222","resolution":{"observed_at":"2026-05-10T06:11:20.434017Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2604.17680","last_updated":"2026-04-20T00:34:28Z","snapshot_observed_at":"2026-08-17T15:05:05.252260Z","submitted_at":"2026-04-20T00:34:28Z","title":"MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-05-10T04:38:42.497109Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2604.17680"},"observation_digest":"sha256:042f21d9156f45c9c02534c03cbed72c2517256a3256a9a056a972a2829527fb","observation_id":"c1b6a574-d962-4263-b1d2-9e7e65f038a2","resolution":{"observed_at":"2026-05-10T12:10:22.251577Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2604.23820","last_updated":"2026-04-26T17:51:44Z","snapshot_observed_at":"2026-08-17T05:53:53.131038Z","submitted_at":"2026-04-26T17:51:44Z","title":"The software space of science","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-08T04:57:35.005471Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2604.23820"},"observation_digest":"sha256:f579c2be8f149653a83c23a0c75e117f90b41c4dfd1a1f70c7754a2d15b27a0b","observation_id":"d14b88e1-cb0e-4d80-af87-8a521bf9f314","resolution":{"observed_at":"2026-05-11T21:36:14.763477Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2605.03861","last_updated":"2026-05-05T15:23:37Z","snapshot_observed_at":"2026-08-12T15:56:48.562903Z","submitted_at":"2026-05-05T15:23:37Z","title":"Aspect-Aware Content-Based Recommendations for Mathematical Research Papers","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-07T14:19:18.282566Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2605.03861"},"observation_digest":"sha256:920c6ca06de1ad0f5e3af37fca376bbbece65ad1ad88a36cbed44282c7b44afa","observation_id":"7a9c7730-6ca2-48b1-a63a-787a97c3c29b","resolution":{"observed_at":"2026-05-12T00:46:12.980398Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2605.17762","last_updated":"2026-05-18T02:29:25Z","snapshot_observed_at":"2026-08-14T14:13:04.342042Z","submitted_at":"2026-05-18T02:29:25Z","title":"Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-20T11:18:05.199634Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2605.17762"},"observation_digest":"sha256:d0a37b5393af3ebb5d2f5bc58e2a96fbb89ccbd9d2fbf6ef81f7121a6c3475eb","observation_id":"2a8e0b12-dc51-44e4-b0ba-ff3aae722d0e","resolution":{"observed_at":"2026-05-20T11:18:13.671344Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2605.18752","last_updated":"2026-05-18T17:59:45Z","snapshot_observed_at":"2026-08-12T18:45:41.726709Z","submitted_at":"2026-05-18T17:59:45Z","title":"Traditional statistical representations outperform generative AI in identifying expert peer reviewers","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-05-20T07:45:50.470698Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2605.18752"},"observation_digest":"sha256:df35e3291b6877b0cb37d3b75861740cf47737e9bf54a7a34bac749870d58ed9","observation_id":"803f7955-6be7-43b1-9bce-9d51d6500af4","resolution":{"observed_at":"2026-05-20T07:48:07.493482Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2605.30247","last_updated":"2026-05-28T17:12:48Z","snapshot_observed_at":"2026-08-16T07:06:52.769628Z","submitted_at":"2026-05-28T17:12:48Z","title":"OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T08:36:52.151369Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2605.30247"},"observation_digest":"sha256:51d30ac6f8612f5b1d8d75282a21a8dffe6355526b2230fdcc3ef56b98a7666a","observation_id":"afd85ea9-9196-4a2d-b47c-488a4aa17442","resolution":{"observed_at":"2026-06-29T08:43:15.518387Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2606.08497","last_updated":"2026-06-07T07:54:49Z","snapshot_observed_at":"2026-08-16T20:39:20.918116Z","submitted_at":"2026-06-07T07:54:49Z","title":"Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T18:33:27.016996Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2606.08497"},"observation_digest":"sha256:7d9aa1a07ab36d2915cfd82a162331d3828fed2246632f8b9a871e953521c52f","observation_id":"6a8964c6-39e0-4af6-9d85-b4eecdbe234e","resolution":{"observed_at":"2026-07-02T22:57:26.399475Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2606.13452","last_updated":"2026-06-11T15:11:24Z","snapshot_observed_at":"2026-08-19T11:29:28.458890Z","submitted_at":"2026-06-11T15:11:24Z","title":"Examining the Cognitive Gap Between Authors and Peer Reviewers on Academic Paper Novelty","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-27T04:58:48.038729Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2606.13452"},"observation_digest":"sha256:9679c4875a31e56c76ab3dae48e45a34c48017724b6737685301fe25d2943959","observation_id":"9f05dfe4-5c04-41a6-8673-2961fd80504c","resolution":{"observed_at":"2026-06-27T05:00:34.501626Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2606.19345","last_updated":"2026-04-24T21:42:39Z","snapshot_observed_at":"2026-08-16T17:23:43.070073Z","submitted_at":"2026-04-24T21:42:39Z","title":"Ensembles of Large Language Models for Identifying EQ-5D Studies in PubMed Based on Their Abstracts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-04T16:18:08.975467Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2606.19345"},"observation_digest":"sha256:5bfad2c50fda5da0523c8e70578595e242f058221eae12934c42883dc39226ca","observation_id":"dea44338-6201-4134-8b66-3ff7abbfde65","resolution":{"observed_at":"2026-07-04T16:19:56.212374Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2606.20553","last_updated":"2026-06-18T17:58:25Z","snapshot_observed_at":"2026-08-16T06:58:07.806823Z","submitted_at":"2026-06-18T17:58:25Z","title":"From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-26T16:51:07.028013Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2606.20553"},"observation_digest":"sha256:12f2b856dc0dc832792154434ce6f5517edc41347c0ede6ea12d8ff531134106","observation_id":"b7a2992d-e47c-41f1-a940-bcca6d3329ee","resolution":{"observed_at":"2026-07-04T04:39:35.032128Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2606.21908","last_updated":"2026-06-20T07:06:18Z","snapshot_observed_at":"2026-08-19T12:20:12.548476Z","submitted_at":"2026-06-20T07:06:18Z","title":"Gender Differences in Research Topic and Method Convergence among Collaborating Scholars in Library and Information Science","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-26T11:14:24.732411Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2606.21908"},"observation_digest":"sha256:8b2cda70fb975dfa709661d76cde4749ce30f3df579807ee9d4d5f8c6c679bb4","observation_id":"7c860b1a-b0c1-4c47-9930-e7edd5707a0b","resolution":{"observed_at":"2026-07-04T08:39:42.079623Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":"1903.10676","doi":"10.48550/arxiv.1903.10676","metadata_source":"arxiv_reference","pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Cohan, A","venue":"arXiv (Cornell University)","work_id":"c5c1ab20-6ac9-4ccc-b34e-037ae077f1ea","year":1903},"citing_paper":{"arxiv_id":"2606.31058","last_updated":"2026-06-30T02:49:34Z","snapshot_observed_at":"2026-08-08T05:35:47.898228Z","submitted_at":"2026-06-30T02:49:34Z","title":"Exploring the relationship between team institutional composition and novelty in academic papers based on fine-grained knowledge entities","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-01T06:03:08.755134Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2606.31058"},"observation_digest":"sha256:2568d9b626d15a26937bdc9bed08a84bb6dea03e589d833cefba61782351b47a","observation_id":"86da967b-7a05-481e-a947-472161da95a0","resolution":{"observed_at":"2026-07-01T09:55:40.948979Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-07-12T05:30:32.163273Z","title":"SciBERT: A pretrained language model for scientific text.arXiv preprint arXiv:1903.10676, 2019","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2607.03006","last_updated":"2026-07-03T06:39:56Z","snapshot_observed_at":"2026-08-13T19:25:15.693203Z","submitted_at":"2026-07-03T06:39:56Z","title":"PosterHarness: Turning Scientific Poster Generation into an Auditable Instruction-Following Benchmark","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-12T05:30:32.163273Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2607.03006"},"observation_digest":"sha256:911db9bb2952e0752c1bcdb396c397ae46750827d85a6aef2a26d21a9d6d6baa","observation_id":"26377379-9840-4dff-b019-080cab05e66b","resolution":{"observed_at":"2026-07-12T05:30:32.163273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-01T20:16:16.951772Z","title":"Scibert: A pretrained language model for scientific text.arXiv preprint arXiv:1903.10676, 2019","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2607.16704","last_updated":"2026-07-18T08:38:19Z","snapshot_observed_at":"2026-08-14T15:37:45.098289Z","submitted_at":"2026-07-18T08:38:19Z","title":"Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T20:16:16.951772Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2607.16704"},"observation_digest":"sha256:73ccf122e674b226efc16123b9de33d0f3805702efbc4f9add88cd92eaf71cb3","observation_id":"0df91f20-051c-41bf-9ccf-119ff9677167","resolution":{"observed_at":"2026-08-01T20:16:16.951772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-07-30T22:49:43.520082Z","title":"arXiv preprint arXiv:1903.10676 , year=","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2607.23420","last_updated":"2026-07-26T02:35:47Z","snapshot_observed_at":"2026-08-22T01:15:30.699662Z","submitted_at":"2026-07-26T02:35:47Z","title":"LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction","version":1},"reference_index":183,"source":"arxiv_source","source_observed_at":"2026-07-30T22:49:43.520082Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2607.23420"},"observation_digest":"sha256:f3d0e19e36cf34456e042f1a180f47cab2ddca0298b47aac8593e73e526e7d0d","observation_id":"d3d12d4c-7913-4c65-8a27-099e1b4e8ac2","resolution":{"observed_at":"2026-07-30T22:49:43.520082Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10676","snapshot_observed_at":"2026-08-15T14:50:55.975471Z","title":"doi:10.48550/arXiv.1903.10676 , abstract =","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2608.03855","last_updated":"2026-08-06T12:23:11Z","snapshot_observed_at":"2026-08-19T19:34:57.374004Z","submitted_at":"2026-08-04T15:57:38Z","title":"Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T14:50:55.975471Z"},"links":{"cited_paper":"/paper/1903.10676","citing_paper":"/paper/2608.03855"},"observation_digest":"sha256:fc18c853624e708bf860e615780930956d20a3aa2694ad7426f501caf75577fc","observation_id":"0f32cbad-170f-42ee-b6bb-aeba8d371d7a","resolution":{"observed_at":"2026-08-15T14:50:55.975471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1903.10676/citation-record","integrity":"/paper/1903.10676/integrity","json":"/paper/1903.10676/citation-record.json","paper":"/paper/1903.10676"},"outbound":[],"paper":{"arxiv_id":"1903.10676","last_updated":"2019-09-10T18:10:35Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-20T05:17:47.499333Z","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 88 inbound Pith citation observations for arXiv:1903.10676."}