{"as_of":"2026-08-08T09:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:236baa4719e7e7c0ddfea89a5bced2c375bb765ef959c7a4ba7696376ca29eee","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:16:55.294429Z","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":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T23:42:00.965554Z","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":"2026-06-30T23:45:08.008153Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"cited_work":{"arxiv_id":"2506.17264","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.17264","snapshot_observed_at":"2026-06-30T23:45:08.008153Z","title":null,"venue":null,"work_id":"e8d85ca3-60ff-42f8-98dc-f62c2887322a","year":2025},"citing_paper":{"arxiv_id":"2605.07053","last_updated":"2026-05-26T07:47:31Z","snapshot_observed_at":"2026-08-02T22:34:50.237073Z","submitted_at":"2026-05-08T00:02:39Z","title":"GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-05-11T00:57:55.616036Z"},"links":{"cited_paper":"/paper/2506.17264","citing_paper":"/paper/2605.07053"},"observation_digest":"sha256:5c5992e6b0727918464f1d74ee4e8ce23077ade2e245c22ddd56b4f1acc69fde","observation_id":"8ca090d3-cee8-4db1-a80d-c5edde7115be","resolution":{"observed_at":"2026-05-11T04:55:59.870666Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"cited_work":{"arxiv_id":"2506.17264","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.17264","snapshot_observed_at":"2026-06-30T23:45:08.008153Z","title":null,"venue":null,"work_id":"e8d85ca3-60ff-42f8-98dc-f62c2887322a","year":2025},"citing_paper":{"arxiv_id":"2605.07053","last_updated":"2026-05-26T07:47:31Z","snapshot_observed_at":"2026-08-02T22:34:50.237073Z","submitted_at":"2026-05-08T00:02:39Z","title":"GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-06-30T23:42:00.965554Z"},"links":{"cited_paper":"/paper/2506.17264","citing_paper":"/paper/2605.07053"},"observation_digest":"sha256:52744d7778aec168d1ffb0eaebe697935a347735a7cd178e4a677c54687eddad","observation_id":"0a5acafd-25a2-4b7a-b792-4a7196602a4c","resolution":{"observed_at":"2026-06-30T23:45:08.009788Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.17264/citation-record","integrity":"/paper/2506.17264/integrity","json":"/paper/2506.17264/citation-record.json","paper":"/paper/2506.17264"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:16:55.217026Z","title":"Languagemodels are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.217026Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:8358c41a496e66c2fa6c9041b8a8afb52850a25f9ffbdd7a7afad667c8a05eff","observation_id":"29082aa9-fec8-49a7-8b4d-32360ecd7a35","resolution":{"observed_at":"2026-08-07T05:16:55.217026Z","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":"2026-08-07T05:16:55.498079Z","title":"Boolq: Exploring the surprising difficulty of natural yes/no questions","venue":null,"work_id":"8185b68f-4adc-463a-802b-d1d7297cd3db","year":2019},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.221485Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:09391b4b20f936eba56cb8f7e4874fb829a4777c02f77ed050ad77733bdcd756","observation_id":"e5f55efd-4a1c-45dc-90e4-869f19ac5ce4","resolution":{"observed_at":"2026-08-07T05:16:55.501530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-07T05:16:55.224774Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.224774Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:fe12e9cce345e356836b165578d0edab04d5226c43ccd4b8a9a240e4883d2fca","observation_id":"84413e3d-e249-441c-8327-1ab3f5c2b89e","resolution":{"observed_at":"2026-08-07T05:16:55.224774Z","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":"2026-08-07T05:16:55.488857Z","title":"The commitmentbank: Investigating projection in naturally occurring discourse","venue":null,"work_id":"9ee98081-fd14-4b85-a7bf-de0d3719e49b","year":2019},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.229133Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:0f57dad908c834f4988482558a8f339d1cc3530d0af82a84e3bb535ad65ee3ef","observation_id":"950d3682-8089-4fa9-9dfd-320d7ee3072f","resolution":{"observed_at":"2026-08-07T05:16:55.491889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T05:16:55.479850Z","title":"Data augmentation using llms: Data per- spectives, learning paradigms and challenges","venue":null,"work_id":"543da14c-d148-4e07-b2db-cf6fb9464986","year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.233338Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:433e244e91f04604b1f5beeef82a0cccb13f06596282ec00ebc07d388cd60c71","observation_id":"aeee722d-0e85-4577-b483-048cb84c3b7e","resolution":{"observed_at":"2026-08-07T05:16:55.483478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:16:55.237162Z","title":"Parameter-efficient fine-tuning of large-scale pre-trained language models.Nature Machine Intelligence, 5(3):220–235, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.237162Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:8afd74a01201b2dedc0c0edcd7cac1eb827cbad98730b36db03a91f696f48a8b","observation_id":"4e500435-d1df-4ee1-b6bf-04cf1e042e56","resolution":{"observed_at":"2026-08-07T05:16:55.237162Z","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":"2026-08-07T05:16:55.465502Z","title":"Variance-reduced zeroth-order methods for fine-tuning language models","venue":null,"work_id":"765865e4-aa97-4580-a784-6df62a816627","year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.241320Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:4e855949a5e4b384747660f312a6bb24bcff04352ee63fd017148eaaca2a7d47","observation_id":"2b9b3438-8f48-44aa-a3d0-d2b56ef6370c","resolution":{"observed_at":"2026-08-07T05:16:55.469222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T05:16:55.244598Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.244598Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:cf00ab7fd8b39b824b970fee2a83dfa15b7d669f320a1e80273aeba9f0fd43fb","observation_id":"6e51eb9e-c793-4809-96cc-0d8364cbbe59","resolution":{"observed_at":"2026-08-07T05:16:55.244598Z","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":"2026-08-07T05:16:55.456634Z","title":"Gardner, Osbert Bastani, Christopher De Sa, Xiaodong Yu, Beidi Chen, and Zhaozhuo Xu","venue":null,"work_id":"d30c672a-d146-4bb6-825a-ea98d107c21c","year":2025},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.248760Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:97fa81f474257b48faad81b4fc2552bc94d1fccac333d6c9d9315315d809c497","observation_id":"bab63bb1-0931-4fba-a2e6-ec71b2bed79d","resolution":{"observed_at":"2026-08-07T05:16:55.460056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T05:16:55.448162Z","title":"Generate, annotate, andlearn: Nlpwithsynthetictext.Transactions of the Association for Computational Linguistics, 10:826–842, 2022","venue":null,"work_id":"6651a654-c8eb-454b-b6e1-4e23f9e2a0c7","year":2022},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.251749Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:7da6efde01c552d987c6c82bb5059b8f0008383e274e6321ce991061787b63ca","observation_id":"88d0b947-a205-4153-9c61-93eaae070cf8","resolution":{"observed_at":"2026-08-07T05:16:55.451642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T05:16:55.439319Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":"dad9c7f0-67d2-4814-bfff-163d99c4daff","year":2022},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.254484Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:06113940d4ea44e1bf0e4d45ad15b9bd0a1b0d42785314d38faf3a1a899d53d6","observation_id":"6585778f-995a-48d3-8041-87d183e2c601","resolution":{"observed_at":"2026-08-07T05:16:55.442473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21276","last_updated":"2024-10-25T17:43:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-25T17:43:01Z","title":"GPT-4o System Card","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21276","snapshot_observed_at":"2026-08-07T05:16:55.258045Z","title":"Gpt-4o system card.arXiv preprint arXiv:2410.21276, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.258045Z"},"links":{"cited_paper":"/paper/2410.21276","citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:26b289f4a5f04a147d264f46c308d0ae29996038b46ebbcc33dded6ca9b37633","observation_id":"d7a4e2ba-8237-4bc2-9854-54f4daae699a","resolution":{"observed_at":"2026-08-07T05:16:55.258045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-07T05:16:55.261718Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.261718Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:78a097b98675e868184d70d41a44ce15c35eee2d8178a8650a208e42a9613bd8","observation_id":"2270a882-0cf6-4c2e-ada6-c90d10a9b150","resolution":{"observed_at":"2026-08-07T05:16:55.261718Z","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":"2026-08-07T05:16:55.429424Z","title":"Zeroth-order stochastic variance reduction for nonconvex optimization.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":"29365a6c-83cf-436c-8bb8-29e8de37fbd7","year":2018},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.265383Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:55121f2268618cff0a8ab05026baa6954e9becc0877c8ed2d892624ca33e181b","observation_id":"ed913de2-4a81-4877-848d-6cd85a6152df","resolution":{"observed_at":"2026-08-07T05:16:55.433301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T05:16:55.418986Z","title":"Black, Adrian Weller, and Bernhard Schölkopf","venue":null,"work_id":"bb94080f-4fcc-49d6-8387-0dd59d4023e6","year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.268586Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:b70217c0128b0f7793498d1ce1244ea00e7f36dbc1f31cb04cca056815a2bb9c","observation_id":"fe3b78f3-8511-415a-9bb3-4705ad2f1ff3","resolution":{"observed_at":"2026-08-07T05:16:55.422336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T05:16:55.409009Z","title":"Winner- take-all column row sampling for memory efficient adaptation of language model.Advances in Neural Information Processing Systems, 36:3402–3424, 2023","venue":null,"work_id":"25a7366c-0b07-495e-a3a5-7b358fafcbdc","year":2023},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.271428Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:bb091fa03cbd77106c73c5fc90acbf467efb6cb8e30f489c8264cee1f78b8e8e","observation_id":"c57c6def-1e5d-4868-93e5-e17efdd5b43a","resolution":{"observed_at":"2026-08-07T05:16:55.412753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:16:55.273897Z","title":"On LLMs-driven synthetic data generation, curation, and evaluation: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.273897Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:31b26c5199bce089192e0fb43d74dab3f958e9eb8983c7d4a1a4f1baa5e7b202","observation_id":"265b6173-4459-493c-a52d-557817dc7259","resolution":{"observed_at":"2026-08-07T05:16:55.273897Z","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":"2026-08-07T05:16:55.398833Z","title":"Fine-tuning language models with just forward passes.Advances in Neural Information Processing Systems, 36:53038–53075, 2023","venue":null,"work_id":"73ce6d7e-1473-4562-8be7-1fd11afd9e52","year":2023},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.276796Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:80d139983fdcad67f4f50be91100d657cbb57c0ac5ca296814beb7e812b45b97","observation_id":"5bc461b6-d4e3-4f62-aa19-3837761d8d13","resolution":{"observed_at":"2026-08-07T05:16:55.402801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T05:16:55.389722Z","title":"Choice of plausible alterna- tives: An evaluation of commonsense causal reasoning","venue":null,"work_id":"024e2d36-446c-4d1e-a294-cc7af5b440b3","year":2011},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.279649Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:9ce0d85121d5be6b68b979628399e0cf7819873b163f28025cb5da29450ec3cd","observation_id":"8700f12f-f65d-4c49-9b1c-e7f7b3f32b62","resolution":{"observed_at":"2026-08-07T05:16:55.393131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T05:16:55.380956Z","title":"In defense of structural sparse adapters for concurrent llm serving","venue":null,"work_id":"fa7babac-9603-44cc-ab11-1f32ab1b10f3","year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.282196Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:a17e567ae4859e6985b771c82b89316e520015e1940ce2258050a84a216f64ab","observation_id":"27998da0-ea9c-4703-8ba8-ae54c32957e9","resolution":{"observed_at":"2026-08-07T05:16:55.383959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:16:55.284841Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.284841Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:44a3b423dbc017c7812d61d3df7b74abb38d30d9dd8eccb2ecb6bd123dd741f0","observation_id":"12e78dc6-eb3e-4eb4-99fd-eb3f9482a5af","resolution":{"observed_at":"2026-08-07T05:16:55.284841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08989","last_updated":"2025-07-24T16:21:10Z","snapshot_observed_at":"2026-07-06T19:31:57.906994Z","submitted_at":"2024-10-11T17:01:43Z","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","version":3},"cited_work":{"arxiv_id":"2410.08989","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.08989","snapshot_observed_at":"2026-08-07T05:16:55.335149Z","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","venue":"cs.LG","work_id":"7baed240-5fea-4508-a44d-c57b80b35fec","year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.288760Z"},"links":{"cited_paper":"/paper/2410.08989","citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:5a4f81379a78c72ca2aa233349a615e56b9d4504e9a25cd9a642ee49f4b48890","observation_id":"343e21e0-3419-4f3a-b5be-83ac377d9678","resolution":{"observed_at":"2026-08-07T05:16:55.340252Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T05:16:55.367015Z","title":"Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, and Tianlong Chen","venue":null,"work_id":"9ba65286-ef9d-4cb5-af6e-cc51e1efc4f0","year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.291710Z"},"links":{"citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:b7b792c8889ab86c60cea8b03a792c1f3ca75bb0d33e7468c412f633fe80a74d","observation_id":"77682c96-2bfa-4b79-b7dd-bb033ceed912","resolution":{"observed_at":"2026-08-07T05:16:55.370084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.15422","last_updated":"2024-03-04T16:55:15Z","snapshot_observed_at":"2026-08-03T13:07:34.950878Z","submitted_at":"2024-01-27T14:19:33Z","title":"A Survey on Data Augmentation in Large Model Era","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.15422","snapshot_observed_at":"2026-08-07T05:16:55.294429Z","title":"A survey on data augmentation in large model era.arXiv preprint arXiv:2401.15422, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T05:16:55.294429Z"},"links":{"cited_paper":"/paper/2401.15422","citing_paper":"/paper/2506.17264"},"observation_digest":"sha256:eb4642c08e514d2752e67ea831ecac7c979fabb99297320548cdfcddd66ca0e3","observation_id":"50c4f774-c729-4216-bf76-cfec8338833a","resolution":{"observed_at":"2026-08-07T05:16:55.294429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.17264","last_updated":"2025-06-10T02:53:04Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T20:46:36.319637Z","submitted_at":"2025-06-10T02:53:04Z","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":14},"total_outbound_references":24},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 2 inbound Pith citation observations for arXiv:2506.17264."}