{"as_of":"2026-08-21T15:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4a61dffaf36498478261d2aa26ac8ec57512b82f7607faa408466d8e88dcb56c","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T21:05:45.252753Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:43:07.506475Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T10:45:42.826299Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"cited_work":{"arxiv_id":"2508.09494","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.09494","snapshot_observed_at":"2026-07-01T10:45:42.826299Z","title":"InProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Min- ing (KDD 2024), pages 5351–5362","venue":null,"work_id":"eaeb7988-56a1-4711-9070-d2e5df8012ca","year":2025},"citing_paper":{"arxiv_id":"2604.13071","last_updated":"2026-04-25T16:37:25Z","snapshot_observed_at":"2026-08-16T22:47:38.015717Z","submitted_at":"2026-03-20T13:35:05Z","title":"EVE: A Domain-Specific LLM Framework for Earth Intelligence","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-15T08:35:02.514458Z"},"links":{"cited_paper":"/paper/2508.09494","citing_paper":"/paper/2604.13071"},"observation_digest":"sha256:0f27b945a246c29ecd9c1165b6311d2ff81e7e18ad1356834663486b15687744","observation_id":"f2f332c9-99d3-46d3-8b91-ee358a3a9b2c","resolution":{"observed_at":"2026-05-15T08:35:18.264975Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"cited_work":{"arxiv_id":"2508.09494","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.09494","snapshot_observed_at":"2026-07-01T10:45:42.826299Z","title":"InProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Min- ing (KDD 2024), pages 5351–5362","venue":null,"work_id":"eaeb7988-56a1-4711-9070-d2e5df8012ca","year":2025},"citing_paper":{"arxiv_id":"2606.32002","last_updated":"2026-06-30T17:35:14Z","snapshot_observed_at":"2026-08-15T03:04:10.151243Z","submitted_at":"2026-06-30T17:35:14Z","title":"Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-01T05:07:58.441326Z"},"links":{"cited_paper":"/paper/2508.09494","citing_paper":"/paper/2606.32002"},"observation_digest":"sha256:815d8537f74ce566f725573298b1351744b6198f31e5907f1e2758703b480737","observation_id":"386956e9-1d59-4574-95cd-222a3c1b42c8","resolution":{"observed_at":"2026-07-01T10:45:42.827705Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.09494","snapshot_observed_at":"2026-08-15T14:43:07.506475Z","title":"Learning Facts at Scale with Active Reading.arXiv preprint arXiv:2508.09494, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.04505","last_updated":"2026-08-05T06:41:48Z","snapshot_observed_at":"2026-08-17T14:19:46.880387Z","submitted_at":"2026-08-05T06:41:48Z","title":"K-EXAONE 2.0 Technical Report","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T14:43:07.506475Z"},"links":{"cited_paper":"/paper/2508.09494","citing_paper":"/paper/2608.04505"},"observation_digest":"sha256:9efecf6b9f7842f560a98d948fe45797c1a3d174def33dfcb071853ddec0b189","observation_id":"3caafa8e-5deb-44a8-9844-35cb32e326d8","resolution":{"observed_at":"2026-08-15T14:43:07.506475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2508.09494/citation-record","integrity":"/paper/2508.09494/integrity","json":"/paper/2508.09494/citation-record.json","paper":"/paper/2508.09494"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.14219","last_updated":"2024-08-30T21:17:17Z","snapshot_observed_at":"2026-08-17T03:25:04.404839Z","submitted_at":"2024-04-22T14:32:33Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14219","snapshot_observed_at":"2026-08-05T21:05:45.181964Z","title":"Phi-3 technical report: A highly capable language model locally on your phone.arXiv preprint arXiv:2404.14219, 2024a","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.181964Z"},"links":{"cited_paper":"/paper/2404.14219","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:eebcf9cdbd2693931d514a364381a53452d01ed43a297412dbfb796660bdde3b","observation_id":"8f609d92-7573-4329-85a5-7cd4517ef3a1","resolution":{"observed_at":"2026-08-05T21:05:45.181964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.00106","last_updated":"2017-04-29T01:08:48Z","snapshot_observed_at":"2026-08-15T08:33:59.901958Z","submitted_at":"2017-04-29T01:08:48Z","title":"Learning to Ask: Neural Question Generation for Reading Comprehension","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.00106","snapshot_observed_at":"2026-08-05T21:05:45.197094Z","title":"Xinya Du, Junru Shao, and Claire Cardie","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.197094Z"},"links":{"cited_paper":"/paper/1705.00106","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:b3ebf967da4892c8b3a0d74e0362b4e8e5fb7d5efba76454d6310c38cb64f0d3","observation_id":"12e98aea-f85e-49c3-8d3b-948ec0f483a3","resolution":{"observed_at":"2026-08-05T21:05:45.197094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14785","last_updated":"2024-06-20T23:27:06Z","snapshot_observed_at":"2026-08-19T20:37:02.420992Z","submitted_at":"2024-06-20T23:27:06Z","title":"Understanding Finetuning for Factual Knowledge Extraction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14785","snapshot_observed_at":"2026-08-05T21:05:45.205525Z","title":"Neel Guha, Julian Nyarko, Daniel Ho, Christopher Ré, Adam Chilton, Alex Chohlas-Wood, Austin Peters, Brandon Waldon, Daniel Rockmore, Diego Zambrano, et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.205525Z"},"links":{"cited_paper":"/paper/2406.14785","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:d4763e20ba3d0a2728d57a40a024fa4ed0c358230ce81fc05aa9fcc0a44f2333","observation_id":"ec96c355-dd7b-4620-804a-31a247acf53c","resolution":{"observed_at":"2026-08-05T21:05:45.205525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11944","last_updated":"2023-11-20T17:28:02Z","snapshot_observed_at":"2026-08-13T18:35:52.271946Z","submitted_at":"2023-11-20T17:28:02Z","title":"FinanceBench: A New Benchmark for Financial Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11944","snapshot_observed_at":"2026-08-05T21:05:45.211008Z","title":"Financebench: A new benchmark for financial question answering.arXiv preprint arXiv:2311.11944,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.211008Z"},"links":{"cited_paper":"/paper/2311.11944","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:f1c8f35deecea0a38ee6e242d212ee2d80446e7c9b74c5cb34f79c5af5556567","observation_id":"063cf6d4-af7f-49ec-9ad4-7839538bfae2","resolution":{"observed_at":"2026-08-05T21:05:45.211008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:05:45.214048Z","title":"doi: 10.18653/v1/P17-1147","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.214048Z"},"links":{"citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:6fd9cd197d902c9f5bfe8d888a6915ce30c29349264d5b4722e1d7b3f55cea39","observation_id":"85fbef7c-f222-49e0-bc85-fb83c265ee90","resolution":{"observed_at":"2026-08-05T21:05:45.214048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05612","last_updated":"2024-05-28T23:56:14Z","snapshot_observed_at":"2026-08-16T21:17:58.141312Z","submitted_at":"2024-03-08T18:28:13Z","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05612","snapshot_observed_at":"2026-08-05T21:05:45.219566Z","title":"Jiyeon Kim, Hyunji Lee, Hyowon Cho, Joel Jang, Hyeonbin Hwang, Seungpil Won, Youbin Ahn, Dohaeng Lee, and Minjoon Seo","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.219566Z"},"links":{"cited_paper":"/paper/2403.05612","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:a85c83f4428fa2597b24d878afac5fc6777e3ad6597def9d0383a99d1268a3eb","observation_id":"d15bf24f-e233-40de-ae03-f749b7432737","resolution":{"observed_at":"2026-08-05T21:05:45.219566Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.05463","last_updated":"2023-09-11T14:01:45Z","snapshot_observed_at":"2026-08-02T22:47:03.212781Z","submitted_at":"2023-09-11T14:01:45Z","title":"Textbooks Are All You Need II: phi-1.5 technical report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.05463","snapshot_observed_at":"2026-08-05T21:05:45.221888Z","title":"Large language models in finance: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.221888Z"},"links":{"cited_paper":"/paper/2309.05463","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:e1a5215d6fee18cc9704691b1577ef3da5713bd221551b13c441127dc6de820c","observation_id":"88882ea9-09af-4b26-ac12-0481483d251a","resolution":{"observed_at":"2026-08-05T21:05:45.221888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15720","last_updated":"2024-06-22T03:32:09Z","snapshot_observed_at":"2026-08-16T13:40:34.788208Z","submitted_at":"2024-06-22T03:32:09Z","title":"Scaling Laws for Fact Memorization of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15720","snapshot_observed_at":"2026-08-05T21:05:45.224515Z","title":"Fingpt: Democratizing internet-scale data for financial large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.224515Z"},"links":{"cited_paper":"/paper/2406.15720","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:06df351c1cc6bcefdec8ab0d14145fcc31e2cd2cd9c55bf53d3089b6c094c4ee","observation_id":"fab2e529-8271-4bb6-a0c2-cd32c520b693","resolution":{"observed_at":"2026-08-05T21:05:45.224515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.24832","last_updated":"2025-06-18T15:27:03Z","snapshot_observed_at":"2026-08-15T05:45:43.601041Z","submitted_at":"2025-05-30T17:34:03Z","title":"How much do language models memorize?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.24832","snapshot_observed_at":"2026-08-05T21:05:45.227099Z","title":"How much do language models memorize?arXiv preprint arXiv:2505.24832,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.227099Z"},"links":{"cited_paper":"/paper/2505.24832","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:2ed0bcd8e6aa86858213b4aa418550981ed2ecb035b578691e16f7ca5c9c28ec","observation_id":"b1a3b514-908e-41b2-bf0d-6014ddfc61f0","resolution":{"observed_at":"2026-08-05T21:05:45.227099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:05:45.418060Z","title":"Transfer learning in biomedical natural language processing: An evaluation of bert and elmo on ten benchmarking datasets.BioNLP 2019, page 58,","venue":null,"work_id":"8036bf4c-a920-4ca2-89ad-4d64b32e5db6","year":2019},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.232072Z"},"links":{"citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:7b4c7bcd09957247e68293e8d9d6431cf3423107aa3c175d9b24a50c4ad310f7","observation_id":"a403f49a-9b0f-4978-bb53-d8a239f7d57e","resolution":{"observed_at":"2026-08-05T21:05:45.421804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.09924","last_updated":"2022-05-24T18:16:24Z","snapshot_observed_at":"2026-08-19T18:59:19.253207Z","submitted_at":"2021-12-18T13:15:34Z","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.09924","snapshot_observed_at":"2026-08-05T21:05:45.234867Z","title":"The web is your oyster - knowledge-intensive nlp against a very large web corpus, 2022.https://arxiv.org/abs/2112.09924","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.234867Z"},"links":{"cited_paper":"/paper/2112.09924","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:e600709f7449f396692ce4f67ca828fe45a7f3ea7778691e1e8b1b8c61105eb3","observation_id":"5c53a816-0e25-4b9e-a815-8295b0d6db31","resolution":{"observed_at":"2026-08-05T21:05:45.234867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09522","last_updated":"2025-04-13T11:25:04Z","snapshot_observed_at":"2026-08-16T12:41:39.287409Z","submitted_at":"2025-04-13T11:25:04Z","title":"How new data permeates LLM knowledge and how to dilute it","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09522","snapshot_observed_at":"2026-08-05T21:05:45.240391Z","title":"Kai Sun, Yifan Xu, Hanwen Zha, Yue Liu, and Xin Luna Dong","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.240391Z"},"links":{"cited_paper":"/paper/2504.09522","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:3ffa6f501c0a8a2613fa3b9882407f396fa50caaa65292fb5baca576cd408598","observation_id":"84407bae-5299-4641-afc2-84184bf6f362","resolution":{"observed_at":"2026-08-05T21:05:45.240391Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.07431","last_updated":"2024-10-03T13:07:25Z","snapshot_observed_at":"2026-08-21T11:56:48.149295Z","submitted_at":"2024-09-11T17:21:59Z","title":"Synthetic continued pretraining","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.07431","snapshot_observed_at":"2026-08-05T21:05:45.245212Z","title":"Crag-comprehensive rag benchmark.Advances in Neural Information Processing Systems, 37: 10470–10490, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.245212Z"},"links":{"cited_paper":"/paper/2409.07431","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:739054a37915208f57e13f4f41d083d375541f9ba60e5d7dc7be7e9e546c772c","observation_id":"20334309-0999-4ca0-b5f4-bfca4de70b75","resolution":{"observed_at":"2026-08-05T21:05:45.245212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.05919","last_updated":"2025-03-07T20:35:31Z","snapshot_observed_at":"2026-08-18T16:01:00.383524Z","submitted_at":"2025-03-07T20:35:31Z","title":"From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.05919","snapshot_observed_at":"2026-08-05T21:05:45.250462Z","title":"Yaoming Zhu, Sidi Lu, Lei Zheng, Jiaxian Guo, Weinan Zhang, Jun Wang, and Yong Yu","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.250462Z"},"links":{"cited_paper":"/paper/2503.05919","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:ea504ad16463ddce6424d3188a710120447b59245e8f0b9b1f22f36f4a423d5d","observation_id":"2dcc3f8c-7f3e-47c9-b762-910a6871fae3","resolution":{"observed_at":"2026-08-05T21:05:45.250462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:05:45.191545Z","title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.191545Z"},"links":{"citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:2128737f7e2bd010f2f4cc6492902d3113bbe037052c14b63559029713a751bf","observation_id":"0b12f30b-9014-437a-a952-196d579dbd1b","resolution":{"observed_at":"2026-08-05T21:05:45.191545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:05:45.436168Z","title":null,"venue":null,"work_id":"cf863794-aabc-41a2-b14d-292f25d2af6a","year":2024},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.200025Z"},"links":{"citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:77b5e296d18ee10482adff14433d66d5a1944e4389abb9fdcd977278975a16f9","observation_id":"3c49f388-f4a5-4b09-88d0-ec1d2df9ff6b","resolution":{"observed_at":"2026-08-05T21:05:45.438914Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:05:45.407909Z","title":"Here ’ s t h e p a r a g r a p h","venue":null,"work_id":"e7d56600-90b3-49d1-995a-6c76b785666d","year":2024},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.252753Z"},"links":{"citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:24d159001e22e1709c67f0a5e1c214b95ba72cf7fd5cc53ca3a48d70f4f9fb83","observation_id":"0e856678-5cc3-4674-92c1-0586552b2389","resolution":{"observed_at":"2026-08-05T21:05:45.412137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09764","last_updated":"2024-12-20T17:36:52Z","snapshot_observed_at":"2026-08-17T03:24:42.718431Z","submitted_at":"2024-12-12T23:56:57Z","title":"Memory Layers at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09764","snapshot_observed_at":"2026-08-05T21:05:45.188392Z","title":"Memory layers at scale","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.188392Z"},"links":{"cited_paper":"/paper/2412.09764","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:1b5336d1109a49028ec6242ae6b22fd00c26c4cc87da9233dfb7b5b6539dd4e5","observation_id":"4b3655e1-a9bd-4695-b72f-48ff463a6ddf","resolution":{"observed_at":"2026-08-05T21:05:45.188392Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:05:45.444346Z","title":"Legal-bert: The muppets straight out of law school","venue":null,"work_id":"8996abc0-f4d5-4612-88f4-794fa13335ed","year":2020},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.194256Z"},"links":{"citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:45a4ccb2591d7787d8a85f85b5473211727a9cdc39fb5106f60e00ef676db8da","observation_id":"d31fa017-f06c-4b72-937f-bf5855fc4693","resolution":{"observed_at":"2026-08-05T21:05:45.447498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.04325","last_updated":"2024-06-04T22:09:46Z","snapshot_observed_at":"2026-08-18T12:09:18.268408Z","submitted_at":"2022-10-26T00:28:40Z","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.04325","snapshot_observed_at":"2026-08-05T21:05:45.242496Z","title":"Will we run out of data? limits of llm scaling based on human-generated data, 2024.https://arxiv.org/abs/2211.04325","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.242496Z"},"links":{"cited_paper":"/paper/2211.04325","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:45c2e41811db89232742d95a04bdfff13e740a34315799f058238cccb4f797ce","observation_id":"7fbcc309-8d5e-43df-b604-0813db2ba0a9","resolution":{"observed_at":"2026-08-05T21:05:45.242496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11644","last_updated":"2023-10-02T06:12:30Z","snapshot_observed_at":"2026-08-13T11:19:55.436754Z","submitted_at":"2023-06-20T16:14:25Z","title":"Textbooks Are All You Need","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11644","snapshot_observed_at":"2026-08-05T21:05:45.207996Z","title":"Textbooks are all you need.arXiv preprint arXiv:2306.11644,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.207996Z"},"links":{"cited_paper":"/paper/2306.11644","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:6c2a25ec8ab524df8b2f4ac0e66cef6ddb66fbfe730047b5e499f333b76b635e","observation_id":"aef74e22-1d56-459b-8b5e-7e5779a29714","resolution":{"observed_at":"2026-08-05T21:05:45.207996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10063","last_updated":"2019-08-27T07:40:48Z","snapshot_observed_at":"2026-07-30T05:49:50.660286Z","submitted_at":"2019-08-27T07:40:48Z","title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10063","snapshot_observed_at":"2026-08-05T21:05:45.185403Z","title":"Finbert: Financial sentiment analysis with pre-trained language models","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.185403Z"},"links":{"cited_paper":"/paper/1908.10063","citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:d520d65421768115af962a6101bb7b90252e881307e120615572ff1ef7245158","observation_id":"20361a5b-48e5-4052-b8b8-d99679b980a4","resolution":{"observed_at":"2026-08-05T21:05:45.185403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:05:45.427507Z","title":"Fine-tuning or retrieval? comparing knowledge injection in llms","venue":null,"work_id":"bc4789d6-5551-45c8-905f-af59b58b4d0c","year":2024},"citing_paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:45.229628Z"},"links":{"citing_paper":"/paper/2508.09494"},"observation_digest":"sha256:5d602585fcdca9ee7b5e56469198f80c70980148ad52015ff2e19534423d0926","observation_id":"45f8727d-a35f-4c40-a319-2a471a41046f","resolution":{"observed_at":"2026-08-05T21:05:45.430571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.09494","last_updated":"2025-08-13T04:54:43Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T20:46:12.089547Z","submitted_at":"2025-08-13T04:54:43Z","title":"Learning Facts at Scale with Active Reading"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":23},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 3 inbound Pith citation observations for arXiv:2508.09494."}