{"as_of":"2026-08-22T10:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3c62132b5116a04c40ea92af0648c5cb05fb4f1ed6b313c333d6b82e420cb32e","coverage":[{"denominator":11,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":11,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T11:50:26.030339Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T06:08:25.933242Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.01046","snapshot_observed_at":"2026-08-01T06:08:25.933242Z","title":"Learning in the fisher sub- space: A guided initialization for lora fine-tuning,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.22010","last_updated":"2026-07-24T06:15:39Z","snapshot_observed_at":"2026-08-16T03:03:40.452735Z","submitted_at":"2026-07-24T06:15:39Z","title":"How Meta-Learning Shapes LoRA Adapter Geometry in Speech Deepfake Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T06:08:25.933242Z"},"links":{"cited_paper":"/paper/2605.01046","citing_paper":"/paper/2607.22010"},"observation_digest":"sha256:ced432c453b956e5fd256bf41ae4945d44945c057cd9deee5fd6e2df03d72583","observation_id":"6462b643-34b3-4ec0-83ed-d8dea7331b61","resolution":{"observed_at":"2026-08-01T06:08:25.933242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.01046/citation-record","integrity":"/paper/2605.01046/integrity","json":"/paper/2605.01046/citation-record.json","paper":"/paper/2605.01046"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-06T15:12:38.498740Z","title":"Ji, Y ., Saratchandran, H., Gordon, C., Zhang, Z., and Lucey, S","venue":null,"work_id":"6ccf8730-b2b5-4ee1-83fb-2abde0da21df","year":2025},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:ee24773242e97702f1a9269a1fe4cc9ba1c219d7fec27784f955e0a1f3092157","observation_id":"4f408bd4-4950-4b3d-833f-b9fe20298af2","resolution":{"observed_at":"2026-07-06T15:12:38.499956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-07-06T15:12:38.497065Z","title":"Krause, J., Stark, M., Deng, J., and Fei-Fei, L","venue":null,"work_id":"315a247e-85a7-42f3-ab0c-318a1af51991","year":2013},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:a400b02449cbbabe25fd22fe194720b5d7f7a6e461deb35a3b328656e149c839","observation_id":"9d1516a2-3bc1-4452-8c57-8be6ec09cdf1","resolution":{"observed_at":"2026-07-06T15:12:38.498184Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1301.3584","last_updated":"2014-02-17T16:29:27Z","snapshot_observed_at":"2026-08-20T09:38:55.579894Z","submitted_at":"2013-01-16T04:47:02Z","title":"Revisiting Natural Gradient for Deep Networks","version":7},"cited_work":{"arxiv_id":"1301.3584","doi":"10.48550/arxiv.1301.3584","metadata_source":"pith","pith_arxiv_id":"1301.3584","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Revisiting Natural Gradient for Deep Networks","venue":"cs.LG","work_id":"15af0fe8-32d5-4d66-a808-b23c8fc4f239","year":2013},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/1301.3584","citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:84e7f8384752d21bd16a6d1cc5edad986bb3460a6479dbb7897cb6f22f5ba429","observation_id":"ea1b20dd-7175-4d7c-8480-731359f26a50","resolution":{"observed_at":"2026-07-01T07:35:28.310911Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08295","last_updated":"2024-04-16T12:52:47Z","snapshot_observed_at":"2026-08-03T03:29:01.959523Z","submitted_at":"2024-03-13T06:59:16Z","title":"Gemma: Open Models Based on Gemini Research and Technology","version":4},"cited_work":{"arxiv_id":"2403.08295","doi":"10.48550/arxiv.2403.08295","metadata_source":"pith","pith_arxiv_id":"2403.08295","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gemma: Open Models Based on Gemini Research and Technology","venue":"cs.CL","work_id":"a9ea2870-df28-40b8-a9e0-a7e9a116f793","year":2024},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:8c18d40daa97255c8e0662022095905dc35f3ce096637eb6a0d5d73d031950f9","observation_id":"a572646b-44fa-490b-8557-50de0492eff0","resolution":{"observed_at":"2026-07-01T07:35:28.883207Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-10T22:08:13.221222+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-10T22:08:13.221222+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":"2307.09288","doi":"10.24963/ijcai.2025/706","metadata_source":"pith","pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","venue":"cs.CL","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","year":2023},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:538f835d7524d40826a8e1be77732bd54ffaa11627351a776c8eae73442a5bf3","observation_id":"4913dd3b-be64-480f-bc70-d0d8b06d0f61","resolution":{"observed_at":"2026-07-01T07:35:28.313373Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1145/3736407","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"ACM Trans","venue":"ACM Transactions on Software Engineering and Methodology","work_id":"f9cee8e6-5ea4-45bd-919b-544fca9e78a7","year":2025},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:e0e5623cec563cda56afb9f6a3b902755166d925c510d93c3bb038186435b6db","observation_id":"0439ef3c-c2c1-4b16-80b9-7418c67a629f","resolution":{"observed_at":"2026-07-01T07:35:28.315216Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2025.acl-long","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"ISBN 979-8-89176-251-0","venue":null,"work_id":"2600ef32-de86-4edc-bcf2-b00fcc304cf8","year":2025},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:74c9cb6ff3a7846ad3a384efc4b13d885713ae5f5294e521764781e9ec27f603","observation_id":"bbf38db9-ce4d-4a20-9218-96599d22c780","resolution":{"observed_at":"2026-07-01T07:35:28.317050Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-10T01:08:17.50792+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-10T01:08:17.50792+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2410.01870","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T14:08:21.926039Z","title":"arXiv preprint arXiv:2410.01870 , year=","venue":null,"work_id":"92ea24c6-372f-43fb-87f5-ab6a4b656b72","year":2025},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:b6190b2c74f5a3ffb414f803eee89d87150beac2dc687a9eb4a917f2b31d9f7d","observation_id":"3d63671b-3be8-42ed-8fd0-7f04732c28cc","resolution":{"observed_at":"2026-07-01T07:35:28.880814Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-07-06T15:12:38.502113Z","title":"15 Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","venue":null,"work_id":"1af93044-0b1d-41d3-b572-d87339752cde","year":null},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:0aab8f8cb77b48924a1b6c4cff46b97d4dab91f1e884ed90d286e82951b738f2","observation_id":"8b577b3c-28b1-44f9-a4aa-5f92d75f6624","resolution":{"observed_at":"2026-07-06T15:12:38.503325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-07-06T15:12:38.500488Z","title":null,"venue":null,"work_id":"ff8aa257-d701-4edc-b6a8-8a30e3fed2e6","year":null},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:dcf821bb3da6f80f6a08472fb6b7c10b026b1e193b6f6e376ed1328f2dc84a5d","observation_id":"002bfe02-2a4e-490b-834f-ff33aeea4ede","resolution":{"observed_at":"2026-07-06T15:12:38.501557Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-07-06T15:12:38.503999Z","title":"For example, if W is a projection layer with m= 4096 and n= 4096 , then mn≈1.68×10 7, and F contains (mn)2 ≈2.8×10 14 entries","venue":null,"work_id":"4edad9ec-58a8-41aa-bb0d-983a35472dba","year":2022},"citing_paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-01T07:32:44.254402Z"},"links":{"citing_paper":"/paper/2605.01046"},"observation_digest":"sha256:cb461acc4b85ad79e0214120afb342d16bca57b07a191bce353aa2b9018df90a","observation_id":"d2e14037-079b-41e6-ac8d-71b7c090a372","resolution":{"observed_at":"2026-07-06T15:12:38.505289Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.01046","last_updated":"2026-05-26T18:00:50Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T03:03:35.250832Z","submitted_at":"2026-05-01T19:20:25Z","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning"},"reference_resolution":{"displayed":11,"state_counts":{"malformed_identifier":2,"metadata_mismatch":4,"parse_uncertain":0,"unresolved":1,"verified_exact":2,"verified_fuzzy":2},"total_outbound_references":11},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 1 inbound Pith citation observation for arXiv:2605.01046."}