{"as_of":"2026-08-08T08:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bb82f7fd09beb31c783a095389564297c88b5c1ef2d764a746b8cfba06679ad8","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":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":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":12,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:36:26.427861Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-07T10:36:26.427861Z","title":"arXiv preprint arXiv:2410.17897 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04956","last_updated":"2025-06-05T12:31:02Z","snapshot_observed_at":"2026-08-07T10:27:19.461334Z","submitted_at":"2025-06-05T12:31:02Z","title":"FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:36:26.427861Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2506.04956"},"observation_digest":"sha256:02a752b82c0f732001e2dedf737283d17775e5a1a9244fa1608646e26706daed","observation_id":"55058e80-ee24-4e04-8b99-f1f6d20469a9","resolution":{"observed_at":"2026-08-07T10:36:26.427861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":"2410.17897","doi":"10.48550/arxiv.2410.17897","metadata_source":"arxiv_reference","pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"29 Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tie-Yan Liu","venue":"arXiv (Cornell University)","work_id":"1a5e0b64-eb2f-4e31-b850-b8736e6c7379","year":2025},"citing_paper":{"arxiv_id":"2509.18993","last_updated":"2026-05-13T13:30:21Z","snapshot_observed_at":"2026-08-02T18:52:22.902766Z","submitted_at":"2025-09-23T13:43:02Z","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-18T14:51:30.312509Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2509.18993"},"observation_digest":"sha256:ba40dda9f8fdae3c8b320f6c9faca1d2ba595c1096baadf08d4a388d278a2ea2","observation_id":"b36f0623-f6f6-40b5-9f44-4e71f3429530","resolution":{"observed_at":"2026-05-18T14:52:41.251014Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-07-13T17:23:44.758186Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.26661","last_updated":"2026-07-01T17:46:52Z","snapshot_observed_at":"2026-07-13T17:23:44.301154Z","submitted_at":"2026-03-27T17:58:05Z","title":"GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-07-13T17:23:44.758186Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2603.26661"},"observation_digest":"sha256:1288903663d0a274b866ef5b5f41bca9da7e917b712b0e719010f7ab131b1241","observation_id":"78ec561b-e941-4b70-9877-9853e75da073","resolution":{"observed_at":"2026-07-13T17:23:44.758186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":"2410.17897","doi":"10.48550/arxiv.2410.17897","metadata_source":"arxiv_reference","pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"29 Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tie-Yan Liu","venue":"arXiv (Cornell University)","work_id":"1a5e0b64-eb2f-4e31-b850-b8736e6c7379","year":2025},"citing_paper":{"arxiv_id":"2604.21724","last_updated":"2026-04-24T17:56:56Z","snapshot_observed_at":"2026-07-06T23:08:14.631453Z","submitted_at":"2026-04-23T14:27:10Z","title":"Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-09T22:28:26.681945Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2604.21724"},"observation_digest":"sha256:792bce504063adaa5ca23ad50a35588a03d8bb9fd223b7bfb0ecbcb8fc36be47","observation_id":"32e9d63e-48bb-4139-acdd-ee023628ca20","resolution":{"observed_at":"2026-05-09T22:29:06.656850Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":"2410.17897","doi":"10.48550/arxiv.2410.17897","metadata_source":"arxiv_reference","pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"29 Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tie-Yan Liu","venue":"arXiv (Cornell University)","work_id":"1a5e0b64-eb2f-4e31-b850-b8736e6c7379","year":2025},"citing_paper":{"arxiv_id":"2605.20798","last_updated":"2026-05-20T06:43:34Z","snapshot_observed_at":"2026-08-02T17:01:43.729235Z","submitted_at":"2026-05-20T06:43:34Z","title":"Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-05-21T06:15:47.451870Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2605.20798"},"observation_digest":"sha256:dc1f5310acdb65b142e03cfd3b2ad3f29ad764b95a6b5b29203ba4fcf315129a","observation_id":"ab086379-102e-4e55-8fe4-9a7347352ca3","resolution":{"observed_at":"2026-05-21T06:19:42.065835Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":"2410.17897","doi":"10.48550/arxiv.2410.17897","metadata_source":"arxiv_reference","pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"29 Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tie-Yan Liu","venue":"arXiv (Cornell University)","work_id":"1a5e0b64-eb2f-4e31-b850-b8736e6c7379","year":2025},"citing_paper":{"arxiv_id":"2606.02780","last_updated":"2026-07-18T16:18:38Z","snapshot_observed_at":"2026-08-02T12:41:17.637289Z","submitted_at":"2026-06-01T18:43:34Z","title":"Do Value Vectors in Deep Layers Need Context from the Residual Stream?","version":2},"reference_index":111,"source":"arxiv_source","source_observed_at":"2026-06-28T14:35:48.292081Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2606.02780"},"observation_digest":"sha256:3b8bda95e01e0b05311eab1e06dab7196f325bd736fdd2dda4333ad10898aa17","observation_id":"6a7117e1-d1af-4d8c-9b64-52ceba65b84a","resolution":{"observed_at":"2026-07-01T23:16:23.491814Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-02T12:41:24.585284Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02780","last_updated":"2026-07-18T16:18:38Z","snapshot_observed_at":"2026-08-02T12:41:17.637289Z","submitted_at":"2026-06-01T18:43:34Z","title":"Do Value Vectors in Deep Layers Need Context from the Residual Stream?","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-02T12:41:24.585284Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2606.02780"},"observation_digest":"sha256:cc6dad362d3f27842c65a56f69c4adc3b9d05738489bf372027fd3b526f010eb","observation_id":"69a0b1ed-560f-4027-b8cd-135188bc46dd","resolution":{"observed_at":"2026-08-02T12:41:24.585284Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":"2410.17897","doi":"10.48550/arxiv.2410.17897","metadata_source":"arxiv_reference","pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"29 Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tie-Yan Liu","venue":"arXiv (Cornell University)","work_id":"1a5e0b64-eb2f-4e31-b850-b8736e6c7379","year":2025},"citing_paper":{"arxiv_id":"2606.07604","last_updated":"2026-05-29T09:40:38Z","snapshot_observed_at":"2026-08-03T04:00:50.272221Z","submitted_at":"2026-05-29T09:40:38Z","title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-06-28T23:29:02.457697Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2606.07604"},"observation_digest":"sha256:b52bc816cb92dfa168ede1953b251139e067846df9b31bff3787cd2bab812a3f","observation_id":"aa698068-f787-4388-8f47-f02c601ac28e","resolution":{"observed_at":"2026-06-28T23:32:46.740876Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":"2410.17897","doi":"10.48550/arxiv.2410.17897","metadata_source":"arxiv_reference","pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"29 Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tie-Yan Liu","venue":"arXiv (Cornell University)","work_id":"1a5e0b64-eb2f-4e31-b850-b8736e6c7379","year":2025},"citing_paper":{"arxiv_id":"2606.25198","last_updated":"2026-07-01T17:23:10Z","snapshot_observed_at":"2026-08-02T21:34:55.759064Z","submitted_at":"2026-06-23T21:44:08Z","title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-06-25T22:42:05.112858Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2606.25198"},"observation_digest":"sha256:f57ae69cbe33dc3a8cefa19299a88fdb49cf32b4b56be5b2eadfb23c92fee467","observation_id":"6182b72e-cb89-40e0-853e-931e813d968e","resolution":{"observed_at":"2026-07-04T18:40:02.639402Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":"2410.17897","doi":"10.48550/arxiv.2410.17897","metadata_source":"arxiv_reference","pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"29 Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tie-Yan Liu","venue":"arXiv (Cornell University)","work_id":"1a5e0b64-eb2f-4e31-b850-b8736e6c7379","year":2025},"citing_paper":{"arxiv_id":"2606.25198","last_updated":"2026-07-01T17:23:10Z","snapshot_observed_at":"2026-08-02T21:34:55.759064Z","submitted_at":"2026-06-23T21:44:08Z","title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-07-02T21:10:35.240433Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2606.25198"},"observation_digest":"sha256:42da1cd34a681782796691ca6e42d5324e22a2c24d7de5e6dd4593fdd8a42090","observation_id":"e3332ab5-80cd-4106-95bb-0ad3239f7e58","resolution":{"observed_at":"2026-07-02T21:17:23.795739Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-02T15:39:41.279102Z","title":"Value residual learning for alleviating attention concentration in transformers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.11889","last_updated":"2026-07-17T09:32:58Z","snapshot_observed_at":"2026-08-06T12:28:12.211551Z","submitted_at":"2026-04-24T17:00:53Z","title":"Scaling Point-in-Time Language Models","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T15:39:41.279102Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2607.11889"},"observation_digest":"sha256:fec898209ae895ee6acbb75f93ac2bb061f9eaba25504574f8e254bf1a0b5d9f","observation_id":"ce59e45b-da86-4834-964c-c04b5a410923","resolution":{"observed_at":"2026-08-02T15:39:41.279102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.17897","snapshot_observed_at":"2026-08-06T00:37:19.608145Z","title":"Value residual learning for alleviating attention concentration in transformers.arXiv preprint arXiv:2410.17897,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.01075","last_updated":"2026-08-02T08:19:39Z","snapshot_observed_at":"2026-08-08T06:01:36.264716Z","submitted_at":"2026-08-02T08:19:39Z","title":"Role-Decoupled Attention Residuals: Separating Matching and Content Retrieval Across Depth","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T00:37:19.608145Z"},"links":{"cited_paper":"/paper/2410.17897","citing_paper":"/paper/2608.01075"},"observation_digest":"sha256:11a18a36b40b33a6a5fad461a280345b9e2d3824911daf46cd915a54e55aac5e","observation_id":"1bc3ab78-2a7c-4c0d-8524-7b9e5213dc6b","resolution":{"observed_at":"2026-08-06T00:37:19.608145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2410.17897/citation-record","integrity":"/paper/2410.17897/integrity","json":"/paper/2410.17897/citation-record.json","paper":"/paper/2410.17897"},"outbound":[],"paper":{"arxiv_id":"2410.17897","last_updated":"2025-06-08T16:04:59Z","latest_version":5,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T19:38:31.218025Z","submitted_at":"2024-10-23T14:15:07Z","title":"Value Residual Learning"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:2410.17897."}