{"as_of":"2026-08-18T10:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:01f2b85e35c0ef619baf1b25dcded38cd06f13f4ec7bed89a3e2b4382ff41328","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T11:38:34.581649Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T13:56:59.336897Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.04614","last_updated":"2025-05-21T23:01:22Z","snapshot_observed_at":"2026-08-16T13:00:34.368434Z","submitted_at":"2024-12-05T21:00:46Z","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04614","snapshot_observed_at":"2026-08-07T11:04:05.791113Z","title":"Extractive structures learned in pretraining enable generalization on finetuned facts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03614","last_updated":"2025-06-04T06:46:06Z","snapshot_observed_at":"2026-08-15T09:53:57.589178Z","submitted_at":"2025-06-04T06:46:06Z","title":"VLMs Can Aggregate Scattered Training Patches","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:04:05.791113Z"},"links":{"cited_paper":"/paper/2412.04614","citing_paper":"/paper/2506.03614"},"observation_digest":"sha256:615d5c91e139cce1e3c80e00f476a9703111b394bc965ade309ad425a805aefe","observation_id":"984829d6-5a12-4e9e-9eda-6e07cec21d3c","resolution":{"observed_at":"2026-08-07T11:04:05.791113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04614","last_updated":"2025-05-21T23:01:22Z","snapshot_observed_at":"2026-08-16T13:00:34.368434Z","submitted_at":"2024-12-05T21:00:46Z","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","version":3},"cited_work":{"arxiv_id":"2412.04614","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.04614","snapshot_observed_at":"2026-07-02T13:56:59.336897Z","title":"Extractive structures learned in pretraining enable generalization on finetuned facts","venue":null,"work_id":"f5786fb5-0716-4c50-b789-a3aa959dfa63","year":2024},"citing_paper":{"arxiv_id":"2510.26745","last_updated":"2026-05-18T17:56:38Z","snapshot_observed_at":"2026-08-16T03:19:50.202624Z","submitted_at":"2025-10-30T17:40:22Z","title":"Deep sequence models tend to memorize geometrically; it is unclear why","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-21T20:38:18.005002Z"},"links":{"cited_paper":"/paper/2412.04614","citing_paper":"/paper/2510.26745"},"observation_digest":"sha256:b0477cbea7c2d81b42009b923fa7e50c31a7172f43c9aadb6cbc6fcacb38b51a","observation_id":"1725881f-bc21-4c5c-9850-e93582da06ef","resolution":{"observed_at":"2026-05-21T20:40:36.368436Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04614","last_updated":"2025-05-21T23:01:22Z","snapshot_observed_at":"2026-08-16T13:00:34.368434Z","submitted_at":"2024-12-05T21:00:46Z","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","version":3},"cited_work":{"arxiv_id":"2412.04614","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.04614","snapshot_observed_at":"2026-07-02T13:56:59.336897Z","title":"Extractive structures learned in pretraining enable generalization on finetuned facts","venue":null,"work_id":"f5786fb5-0716-4c50-b789-a3aa959dfa63","year":2024},"citing_paper":{"arxiv_id":"2607.00341","last_updated":"2026-07-27T05:15:18Z","snapshot_observed_at":"2026-08-12T22:28:45.097171Z","submitted_at":"2026-07-01T02:32:02Z","title":"DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-02T13:46:59.407102Z"},"links":{"cited_paper":"/paper/2412.04614","citing_paper":"/paper/2607.00341"},"observation_digest":"sha256:e26eeeaeef5e9302909250363b4d7b91c1d83bfc71e084f076a85188b684b1d0","observation_id":"f4bb0656-1f84-4dff-ba1f-1b4ded31045a","resolution":{"observed_at":"2026-07-02T13:56:59.338652Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04614","last_updated":"2025-05-21T23:01:22Z","snapshot_observed_at":"2026-08-16T13:00:34.368434Z","submitted_at":"2024-12-05T21:00:46Z","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04614","snapshot_observed_at":"2026-08-02T09:18:43.665696Z","title":"Extractive structures learned in pretraining enable generalization on finetuned facts.arXiv preprint arXiv:2412.04614,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.00341","last_updated":"2026-07-27T05:15:18Z","snapshot_observed_at":"2026-08-12T22:28:45.097171Z","submitted_at":"2026-07-01T02:32:02Z","title":"DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T09:18:43.665696Z"},"links":{"cited_paper":"/paper/2412.04614","citing_paper":"/paper/2607.00341"},"observation_digest":"sha256:9a869181f280ef5b405720b292cb96a3fc275336604c9ae53a315b8da50b3cdd","observation_id":"fe1c7522-fd0b-4138-9403-a428dfbf95f6","resolution":{"observed_at":"2026-08-02T09:18:43.665696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04614","last_updated":"2025-05-21T23:01:22Z","snapshot_observed_at":"2026-08-16T13:00:34.368434Z","submitted_at":"2024-12-05T21:00:46Z","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04614","snapshot_observed_at":"2026-08-10T11:38:34.581649Z","title":"Mor Geva, Jasmijn Bastings, Katja Filippova, and Amir Globerson","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07261","last_updated":"2026-08-07T14:17:34Z","snapshot_observed_at":"2026-08-17T17:37:42.783626Z","submitted_at":"2026-08-07T14:17:34Z","title":"Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T11:38:34.581649Z"},"links":{"cited_paper":"/paper/2412.04614","citing_paper":"/paper/2608.07261"},"observation_digest":"sha256:7a863a387f9cdb04bf6673b6ec87c8aa785941b47f31e88b3b72702f97f3e791","observation_id":"bed8637e-3eee-4548-a1e6-d7ada862ea70","resolution":{"observed_at":"2026-08-10T11:38:34.581649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.04614/citation-record","integrity":"/paper/2412.04614/integrity","json":"/paper/2412.04614/citation-record.json","paper":"/paper/2412.04614"},"outbound":[],"paper":{"arxiv_id":"2412.04614","last_updated":"2025-05-21T23:01:22Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T13:00:34.368434Z","submitted_at":"2024-12-05T21:00:46Z","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2412.04614."}