{"as_of":"2026-08-09T10:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:005728ff4d6fb8f33403648089415d843ea6462cd0a60bab411b273f9cf1fb7d","coverage":[{"denominator":69,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":69,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T13:39:16.128206Z","state":"measured"},{"denominator":69,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":69,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.02154/citation-record","integrity":"/paper/2608.02154/integrity","json":"/paper/2608.02154/citation-record.json","paper":"/paper/2608.02154"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:39:07.337515Z","title":"Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:07.337515Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:f4835bc6d2021b1f7b7606adb45e35ecfe86acbd865aab9978d55329b8202ef6","observation_id":"3548ee4c-ad87-4bae-acd5-b8e431005e77","resolution":{"observed_at":"2026-08-04T13:39:07.337515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-04T13:39:07.415156Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:07.415156Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:fd2674e28662d2cfca9c868f60afffe8d7f6cb9f8f999d6538d3e929f9ef7c20","observation_id":"42fb93e8-391c-446d-9f07-8dc11cf8a928","resolution":{"observed_at":"2026-08-04T13:39:07.415156Z","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":"2026-08-04T13:39:07.549834Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:07.549834Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:5645b17e0dce455c830b72631b5160b53beac828cd959a70ec81a61cc0824d01","observation_id":"142a6afc-ba97-4cc6-9d3c-408644386d93","resolution":{"observed_at":"2026-08-04T13:39:07.549834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.01373","last_updated":"2023-05-31T17:54:07Z","snapshot_observed_at":"2026-08-07T23:49:29.478548Z","submitted_at":"2023-04-03T20:58:15Z","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.01373","snapshot_observed_at":"2026-08-04T13:39:07.692085Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:07.692085Z"},"links":{"cited_paper":"/paper/2304.01373","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:1b65e88056a1be4e94e2bf0698271f40da591e21a3f7903d9a6aef01d4a74f8a","observation_id":"a9e5f167-4fd7-4dcc-bfd5-72c0f00d44ea","resolution":{"observed_at":"2026-08-04T13:39:07.692085Z","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":"2026-08-04T13:39:07.889989Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:07.889989Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:8e8739c9d29d89ab15af1b4c27cf07e995c7e71d5dfa646de0d5a7860c0fa0c5","observation_id":"62ba8736-7e02-4a4a-b294-0c257e1adee9","resolution":{"observed_at":"2026-08-04T13:39:07.889989Z","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":"2026-08-04T13:39:08.007016Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:08.007016Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:2c381e2f878578b9cff5bc621ff999e7e9dba2cf75eb74a69f84723a709e35ed","observation_id":"fb8bb410-5939-420f-b896-430c3bd36619","resolution":{"observed_at":"2026-08-04T13:39:08.007016Z","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":"2026-08-04T13:39:08.150115Z","title":null,"venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:08.150115Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:19a29658427bd5f7739df9602040227e6380e253617fa0481956a6ce25c11829","observation_id":"aacf843b-b582-4983-a73d-aece9b1c9f4c","resolution":{"observed_at":"2026-08-04T13:39:08.150115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.06261","last_updated":"2025-12-19T14:25:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-07T17:36:04Z","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.06261","snapshot_observed_at":"2026-08-04T13:39:08.260977Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:08.260977Z"},"links":{"cited_paper":"/paper/2507.06261","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:efcb31c0b1f5080e84ace0c32da7924ff930576ceefc6a77790ae560fdf134f3","observation_id":"b619be2c-5978-45e2-8f7f-65e0b133ad23","resolution":{"observed_at":"2026-08-04T13:39:08.260977Z","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":"2026-08-04T13:39:08.400522Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:08.400522Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:361e8fd9a4624442ee64051ca6c17bdfaf454c6bfae68a554ca5a964165e7aee","observation_id":"6b618276-108d-4d16-afef-121dda236d8a","resolution":{"observed_at":"2026-08-04T13:39:08.400522Z","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":"2026-08-04T13:39:08.571982Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:08.571982Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:434e56cd3c1eed9feae11a1516c47eba3bd383fb9780d41546317e87e9354a38","observation_id":"fed3630a-e25a-43b4-9c9e-457a895e6454","resolution":{"observed_at":"2026-08-04T13:39:08.571982Z","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":"2026-08-04T13:39:08.805456Z","title":"2016.Deep learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:08.805456Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:e4f7a3c170d673a5afe426351324bcaff43c8036c760efff2618235f3a27876a","observation_id":"219abf91-9663-4bb7-95e4-f5cc35748d68","resolution":{"observed_at":"2026-08-04T13:39:08.805456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-04T13:39:09.033937Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:09.033937Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:758a1e785d7b4fbc92b40567f1ebf9d738d597cc77e7b29facef5207e7cd75c9","observation_id":"49327e71-3912-4296-9999-950372628ca0","resolution":{"observed_at":"2026-08-04T13:39:09.033937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08247","last_updated":"2025-03-18T21:31:51Z","snapshot_observed_at":"2026-08-07T23:01:40.564640Z","submitted_at":"2023-04-14T11:28:08Z","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08247","snapshot_observed_at":"2026-08-04T13:39:09.177448Z","title":"Adams, Jens-Michalis Papaioannou, Paul Grundmann, Tom Oberhauser, Alexei Figueroa, Alexander Löser, Daniel Truhn, and Keno K","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:09.177448Z"},"links":{"cited_paper":"/paper/2304.08247","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:82babebc806743356252f525ba402b4f0b53262390dd423a799e90227a7ba445","observation_id":"952b32cf-9998-4629-9712-61ebc2488061","resolution":{"observed_at":"2026-08-04T13:39:09.177448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14608","snapshot_observed_at":"2026-08-04T13:39:09.354441Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:09.354441Z"},"links":{"cited_paper":"/paper/2403.14608","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:e47a4343402a66977f91e399b272baca12baddbcb00108c709ccea3a02504588","observation_id":"5e06d28c-9d28-451a-a49a-7871366196bd","resolution":{"observed_at":"2026-08-04T13:39:09.354441Z","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":"2026-08-04T13:39:09.547304Z","title":null,"venue":null,"work_id":null,"year":1979},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:09.547304Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:20914332d5362e5e1285fbb450fdf33bdc683a0cf5668e5f4eb2bb92c0404eb3","observation_id":"3d23d0e0-b17c-40e2-bf9b-8d0a3ddc48c6","resolution":{"observed_at":"2026-08-04T13:39:09.547304Z","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":"2026-08-04T13:39:09.693564Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:09.693564Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:1dbf452b5391a214c19e3e53a7ad18e93b97336342d252ad1ca301aa19c44a64","observation_id":"e0fd8f00-9e9d-4844-be67-9874c5c77b3c","resolution":{"observed_at":"2026-08-04T13:39:09.693564Z","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":"2026-08-04T13:39:09.833553Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:09.833553Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:dadf7b5629bde3e1841cf58e069855cd1546dd50cb1485e5f50dc79df87d0e24","observation_id":"31e794ac-afd6-4720-8129-9e7ec35585c7","resolution":{"observed_at":"2026-08-04T13:39:09.833553Z","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":"2026-08-04T13:39:09.958701Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:09.958701Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:7aba08194608ea7baeeb7444267f93329fcbf6e0ac714170acb6d66a59df7492","observation_id":"f0e423ce-54da-4cf3-951d-6792090ecdb1","resolution":{"observed_at":"2026-08-04T13:39:09.958701Z","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":"2026-08-04T13:39:10.125831Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:10.125831Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:50962ac21cc9b6c8a88c0063105b62f76b149a4dbc6f6e4a709302a2e907780f","observation_id":"0029f0c8-1058-46dc-b08f-a55b4e700472","resolution":{"observed_at":"2026-08-04T13:39:10.125831Z","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":"2026-08-04T13:39:10.261157Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:10.261157Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:9ce5e784a5f26a118d0d4495cd911b91da449b399ef0a6cf3538820358618f94","observation_id":"9e19784a-7033-4f3a-8b31-89ad4da12b01","resolution":{"observed_at":"2026-08-04T13:39:10.261157Z","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":"2026-08-04T13:39:10.530118Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:10.530118Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:9daad329bd5335e82bfaf2374f35b1ba913c6080a36218c2fa72c1604705793b","observation_id":"b2f3d1ca-52ee-467f-b327-2675ba920852","resolution":{"observed_at":"2026-08-04T13:39:10.530118Z","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":"2026-08-04T13:39:10.725036Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:10.725036Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:a5985de729c821f736f55c13f4e9c4098fefff9d6f139f839f7572c29e3aacbb","observation_id":"01d5d13a-c1a0-4cc8-bfe5-11fda8447680","resolution":{"observed_at":"2026-08-04T13:39:10.725036Z","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":"2026-08-04T13:39:10.835199Z","title":null,"venue":null,"work_id":null,"year":1985},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:10.835199Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:281486b9acaeed489ea7210d0944035b7f8a92a6b604e2c9dff3583794d143c1","observation_id":"319be312-4e14-4063-ab98-3f4895608fad","resolution":{"observed_at":"2026-08-04T13:39:10.835199Z","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":"2026-08-04T13:39:10.947189Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:10.947189Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:2e474aa22473098bb32f7523c163137524175127881b4c7f59a9e0bcc6785bce","observation_id":"73d4db44-c64e-46e8-b917-9c81f20549af","resolution":{"observed_at":"2026-08-04T13:39:10.947189Z","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":"2026-08-04T13:39:11.075305Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.075305Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:59a6d6c3f033739a498c95c4d4e4d21635658da9a380458a90bdd068bc6a4353","observation_id":"bbf19197-72bb-4c95-a7eb-c456b9078a89","resolution":{"observed_at":"2026-08-04T13:39:11.075305Z","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":"2026-08-04T13:39:11.120070Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.120070Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:7dba13700039b14cceb28bef614230422317f9e7f3efb2a7bc09a47896e5efe1","observation_id":"5a373a6b-e448-4410-9dca-89cb7556c9ec","resolution":{"observed_at":"2026-08-04T13:39:11.120070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.07384","last_updated":"2025-03-13T12:37:37Z","snapshot_observed_at":"2026-08-07T17:16:38.006527Z","submitted_at":"2025-03-10T14:32:56Z","title":"Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.07384","snapshot_observed_at":"2026-08-04T13:39:11.179112Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.179112Z"},"links":{"cited_paper":"/paper/2503.07384","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:49e7e6476b52071a8c9d7c67ffd5eaa0be20fca3741ed193695059b706361fd0","observation_id":"bebf7a26-c40d-4a4a-81df-d19a95b58ac5","resolution":{"observed_at":"2026-08-04T13:39:11.179112Z","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":"2026-08-04T13:39:11.254251Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.254251Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:91f52c3ebc1a487a662c6556e982ecec3354a6bc6b2863a56159d407e74fffbc","observation_id":"7bea94cc-045b-4c22-944c-69236c002365","resolution":{"observed_at":"2026-08-04T13:39:11.254251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.03483","last_updated":"2017-02-27T05:47:30Z","snapshot_observed_at":"2026-07-06T05:14:15.269065Z","submitted_at":"2016-10-11T19:59:39Z","title":"Learning in Implicit Generative Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.03483","snapshot_observed_at":"2026-08-04T13:39:11.345595Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.345595Z"},"links":{"cited_paper":"/paper/1610.03483","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:34b5b54ce0a6f5d0ed66e991474dd0aa46d595c4e19a4cbc561ba16461a85289","observation_id":"bdfbad4d-b193-4a2b-8a21-6b2f52597518","resolution":{"observed_at":"2026-08-04T13:39:11.345595Z","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":"2026-08-04T13:39:11.429280Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.429280Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:329edd5f12e3acef8ce07895c9b4792176c24426de6d586770173d541cf51775","observation_id":"8f72c394-f7b9-449d-a609-16eb0e0910a5","resolution":{"observed_at":"2026-08-04T13:39:11.429280Z","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":"2026-08-04T13:39:11.581299Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.581299Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:d00f9cad13a2250b15f3d1a2a9fc094f42346c3035bda2a5a9b3ad74c41494e5","observation_id":"233cdb64-7353-4f82-83bc-d4cd8b7522a6","resolution":{"observed_at":"2026-08-04T13:39:11.581299Z","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":"2026-08-04T13:39:11.682372Z","title":"2001.Empirical likelihood","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.682372Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:acba9d7c536d5a0c11ff42aa49250231f7e91c114fe6711e4e34a81b85a87445","observation_id":"a8739356-b18a-4dc4-bfa2-6ab42531d18c","resolution":{"observed_at":"2026-08-04T13:39:11.682372Z","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":"2026-08-04T13:39:11.757288Z","title":null,"venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.757288Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:b17f87b2ffc40860b71693a45f85de6b1849bd18cdff67df3887b783c2443953","observation_id":"2a5d5b13-4194-4ea0-a71f-c04c5570125f","resolution":{"observed_at":"2026-08-04T13:39:11.757288Z","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":"2026-08-04T13:39:11.897690Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:11.897690Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:faa431d265bc438a75a2c5a5e550b2a3aae0474c8882d70605c5a7d403a3136d","observation_id":"8b447016-1d98-4bcd-883f-2047cc62778b","resolution":{"observed_at":"2026-08-04T13:39:11.897690Z","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":"2026-08-04T13:39:12.027891Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:12.027891Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:34aeafe5043e95a95fd1c7a915780379aa50707ad9477e25e531f4a5b51f9771","observation_id":"d81c8854-5fcf-4b6e-888d-eb1cbda28f17","resolution":{"observed_at":"2026-08-04T13:39:12.027891Z","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":"2026-08-04T13:39:12.205883Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:12.205883Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:7b403306cd537d96bc0cc8ffaf51381d09b31e71da5c467564ed8c3ca23af36e","observation_id":"4860c53e-cddb-4a43-9b3a-05482a3f0f8a","resolution":{"observed_at":"2026-08-04T13:39:12.205883Z","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":"10.18653/v1/2024.emnlp-main.1005","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":null,"work_id":"fd6acb1e-f923-4829-aa84-84ef18447f1c","year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:12.505200Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:f28643d3038daf22e7151fb30579662646a02a57acc6e0e89e83d769de00dcbc","observation_id":"832870fe-a96c-4164-96eb-9e938bf4e0f1","resolution":{"observed_at":"2026-08-04T13:43:34.027126Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-07-06T08:17:05.681370Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-04T13:39:12.676687Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:12.676687Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:0e404d77f6866132b248ce235592fbff3ce2410634c703672f692b84e5567d68","observation_id":"2ef5cf33-3b5d-48a6-a980-74ca2019534b","resolution":{"observed_at":"2026-08-04T13:39:12.676687Z","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":"2026-08-04T13:39:12.843436Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:12.843436Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:84a15208e7b658df2688995a89bf28ae10d89327c2ed7c151dc1122f06a765b4","observation_id":"09611f18-6378-4494-9f57-adc3500aee7b","resolution":{"observed_at":"2026-08-04T13:39:12.843436Z","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":"2026-08-04T13:39:12.988164Z","title":"2002.Learning with kernels: support vector machines, regularization, optimization, and beyond","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:12.988164Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:568b50cc034570f3815ff5cfe4351d88150cb66178cf2222514ea4e940c7ee05","observation_id":"78598176-468d-4ffa-a8ce-7fd469618114","resolution":{"observed_at":"2026-08-04T13:39:12.988164Z","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":"2026-08-04T13:39:13.121011Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.121011Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:49bea8c4f4da598d8c8e80b8db608cc017d8d95301049f01c583276a21381f2a","observation_id":"660d43e3-63ef-4249-984b-404ae4055cf2","resolution":{"observed_at":"2026-08-04T13:39:13.121011Z","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":"2026-08-04T13:39:13.198994Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.198994Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:c9fd95b6d8c2b244b3cf38373172cc9d8d94643303b8e377f35e1a5a12d9e368","observation_id":"d5d2a7ff-769b-4d32-af7e-d2ca47b490f0","resolution":{"observed_at":"2026-08-04T13:39:13.198994Z","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":"2026-08-04T13:39:13.270115Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.270115Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:528baca16e90e34ac12500534925f7fc746075afff581af7e399732bb8f11fbf","observation_id":"ab6e00c1-93e3-4546-8e2c-5c500f72d91c","resolution":{"observed_at":"2026-08-04T13:39:13.270115Z","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":"2026-08-04T13:39:13.413875Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.413875Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:77f59c73d7cf8c956b3aa471d8abcff2ac0f01356500919134784deadd01aa1f","observation_id":"86f119dc-b65e-4f53-9c7c-1b9ff2bd5ec5","resolution":{"observed_at":"2026-08-04T13:39:13.413875Z","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":"2026-08-04T13:39:13.542771Z","title":"Hashimoto","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.542771Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:a2458dd6b5a9ca3c3753d1ce1be60d43c8bc88eec175add20e8eadcf9813cac4","observation_id":"e4da1a3e-06f8-4f61-b19a-7e39e9cb61e2","resolution":{"observed_at":"2026-08-04T13:39:13.542771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"physics/0004057","last_updated":"2000-04-24T15:22:30Z","snapshot_observed_at":"2026-08-07T10:46:08.274157Z","submitted_at":"2000-04-24T15:22:30Z","title":"The information bottleneck method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"physics/0004057","snapshot_observed_at":"2026-08-04T13:39:13.661238Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.661238Z"},"links":{"cited_paper":"/paper/physics/0004057","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:4cf137e18e28c8d07018dd0772e00d88fc0f3e2780558f8065985a7050fe737c","observation_id":"cb7bcda6-f5db-482d-aa04-df8ab8eb0fe3","resolution":{"observed_at":"2026-08-04T13:39:13.661238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-04T13:39:13.752446Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.752446Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:f3efaa932bcbafd3e602dd18b0b35372f2547117e628eb9754f410302cd63137","observation_id":"1f6bce80-c38d-4182-b60b-26e7e9094355","resolution":{"observed_at":"2026-08-04T13:39:13.752446Z","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":"2026-08-04T13:39:13.829046Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.829046Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:4075b7d4e3217ecf179d8db4dddfef7d1bd466cf05c31885ccc5d029ec32357d","observation_id":"9318c42c-0535-46e0-8d76-dcdb6ba663d8","resolution":{"observed_at":"2026-08-04T13:39:13.829046Z","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":"2026-08-04T13:39:13.999270Z","title":"Smith, Daniel Khashabi, and Hannaneh Hajishirzi","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:13.999270Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:5899f943fed0e3fc91b041967df0e3de84559198e3df15318da6063b193c7815","observation_id":"7ae4df5d-6eef-4a10-be0b-84b8c19ded05","resolution":{"observed_at":"2026-08-04T13:39:13.999270Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-04T13:39:14.363460Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:14.363460Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:867e4cea2c1f8eb008e5e5c559d65c911723af08c39fbaf7aa1377c38117f9ff","observation_id":"481a8020-8ddc-42b9-83ab-ca0147beede8","resolution":{"observed_at":"2026-08-04T13:39:14.363460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-04T13:39:14.522119Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:14.522119Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:95cb33a9301390f83be86b31f2d72fa432643aa12c763b4937271a40f28b5284","observation_id":"83821a57-7033-47b2-be38-449ae417b6e7","resolution":{"observed_at":"2026-08-04T13:39:14.522119Z","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":"2026-08-04T13:39:14.633218Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:14.633218Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:b9e8cc496e737377999b7e1f812338a10d1a9cedd4970051c78f8e1ead79c17f","observation_id":"b489fe39-558e-4c2f-858b-0b3c2aa32a53","resolution":{"observed_at":"2026-08-04T13:39:14.633218Z","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":"2026-08-04T13:39:14.990571Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:14.990571Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:d5584e50a228dffa3970862afcb7ccae6a22023b1229206732697cbcf5605157","observation_id":"725eec45-992b-4d8f-80da-06767a7aeb95","resolution":{"observed_at":"2026-08-04T13:39:14.990571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.11548","last_updated":"2026-04-07T07:06:44Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-08-15T15:50:20Z","title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.11548","snapshot_observed_at":"2026-08-04T13:39:14.421278Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:14.421278Z"},"links":{"cited_paper":"/paper/2508.11548","citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:a94bc45959be18142556fe2d93efd90029e80b963d34faa458694aa0244d9b9b","observation_id":"499ba978-c049-494e-8bcb-323c666899c3","resolution":{"observed_at":"2026-08-04T13:39:14.421278Z","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":"2026-08-04T13:39:15.227075Z","title":"wiki” later) 𝜋own 𝐷_{para}0.923 0.054 0.784 0.413 0.541 0.454 𝜋ind 𝐷^{flash}0.782 0.098 0.571 0.078 0.137 0.435 ChatDoctor (compared with𝐷HCMbase, omitting superscript “HCM","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.227075Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:ba60db56b8022ecb97509b155ba4e65f2142edc93dd2f0b1d0860bb098579b3d","observation_id":"211531db-c199-4504-8e53-b35e7311e546","resolution":{"observed_at":"2026-08-04T13:39:15.227075Z","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":"2026-08-04T13:39:14.798535Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:14.798535Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:1beea67f9937363cc864166e8c8e7cf5cb8515ae888f665a3c6f30bf38476f5d","observation_id":"9e488a63-8bb6-4cd1-9ae9-f29bceb81d88","resolution":{"observed_at":"2026-08-04T13:39:14.798535Z","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":"2026-08-04T13:39:15.094662Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.094662Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:0a5d8c1702709e08cef9f44f0f8ae4dff714ccb8b4342dad6eb3fad31d833497","observation_id":"444b8df0-46ed-413f-941b-f3e648fa46fb","resolution":{"observed_at":"2026-08-04T13:39:15.094662Z","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":"2026-08-04T13:39:15.301800Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.301800Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:90a61dd8967459ecebd136d91a58f3a46f138861bd8f850c510e9038640b0e57","observation_id":"f1ff1396-dada-4f7d-8a5e-02da002a80cb","resolution":{"observed_at":"2026-08-04T13:39:15.301800Z","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":"2026-08-04T13:39:15.404714Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.404714Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:3c2798b49a921e49d4a43b3b7e9310624ff120f4cd24e5916dccfdcd2ab2b7b7","observation_id":"ba8e7c2a-2207-4923-b1cf-33f683730d68","resolution":{"observed_at":"2026-08-04T13:39:15.404714Z","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":"2026-08-04T13:39:15.459280Z","title":"sequence1","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.459280Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:a288b3aec014d1a93bb1390ddba4ce58a64921aca80dc0c6bcc8144eebce131d","observation_id":"ee63e255-04b2-4660-8017-12f3bad48da8","resolution":{"observed_at":"2026-08-04T13:39:15.459280Z","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":"2026-08-04T13:39:15.532637Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.532637Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:288ca1e5e8de949a1da128a0782c21eed9c059d82b331187b2b0cf5457237f32","observation_id":"f0222a9e-650e-408b-ae95-2f990236ed11","resolution":{"observed_at":"2026-08-04T13:39:15.532637Z","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":"2026-08-04T13:39:15.692511Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.692511Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:839a77e320f42b9c376f625a3c7b8191b42fe9b07ad9f60dc0533263f44bf381","observation_id":"0e18b612-f3e9-45e4-90ee-f1ea9582a6bd","resolution":{"observed_at":"2026-08-04T13:39:15.692511Z","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":"2026-08-04T13:39:15.878727Z","title":"DON’T LEAVE OUT ANY INFORMATION!","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.878727Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:9a48901c720ee31aa459b6af58fea37a06134c6a748725efc42a72fc39e1438b","observation_id":"6cebddef-7f63-4533-8242-97750e48849b","resolution":{"observed_at":"2026-08-04T13:39:15.878727Z","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":"2026-08-04T13:39:15.925030Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:15.925030Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:2dd8f9c1bcb1c674aa2b3939d090696408ea2eaa1cbf1839cd07ff4855d5d952","observation_id":"57e6e83c-b04e-4cf7-a9ba-febf22083d27","resolution":{"observed_at":"2026-08-04T13:39:15.925030Z","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":"2026-08-04T13:39:16.024324Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:16.024324Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:b4f449fc1f1786f532e21eeac0fc56851d4588a09842ef2db1ffda4e6e2d1bf5","observation_id":"8dc49bab-40fc-4504-b079-4837e7f38eea","resolution":{"observed_at":"2026-08-04T13:39:16.024324Z","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":"2026-08-04T13:39:16.128206Z","title":"soft gate","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:16.128206Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:88be0292a249e3b13dac0a51e055d874183915b8c54e44c384170ea5e14f0054","observation_id":"f8b9f3ed-cd84-4faa-99df-c82146f02c1c","resolution":{"observed_at":"2026-08-04T13:39:16.128206Z","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":"2026-08-04T13:39:10.401916Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:10.401916Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:71d2de8cd5d83f73ac9508ae617f061ad2449d89ded72f4c1d15a7feba3656e8","observation_id":"5d32dc43-0bad-41cf-88dc-82ed2151cb92","resolution":{"observed_at":"2026-08-04T13:39:10.401916Z","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":"2026-08-04T13:39:08.727951Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:08.727951Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:1bc660b371796d1be0d0eefc6077559ca631aaddc191d5a5ad63dde906767e9e","observation_id":"0a757e20-7014-4fce-8e9b-154b9d365c73","resolution":{"observed_at":"2026-08-04T13:39:08.727951Z","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":"2026-08-04T13:39:12.354612Z","title":"InICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-04T13:39:12.354612Z"},"links":{"citing_paper":"/paper/2608.02154"},"observation_digest":"sha256:5b2eeac61ffdcbe820321ac54e1781a8672cadd1fe776948396764df858a0381","observation_id":"b2077dc8-4b4b-456f-8cad-e48f0eb1365c","resolution":{"observed_at":"2026-08-04T13:39:12.354612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.02154","last_updated":"2026-08-03T12:35:51Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-08T13:01:04.576959Z","submitted_at":"2026-08-03T12:35:51Z","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints"},"reference_resolution":{"displayed":69,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":67,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":69},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 0 inbound Pith citation observations for arXiv:2608.02154."}