{"as_of":"2026-08-07T22:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:db1548e1bc5c0ac2a8e74e728889e448b1e8a0ddc2e6f7c008ac3825e08aebe2","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":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:50:33.396828Z","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":75,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-07T04:50:33.396828Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.21772","last_updated":"2025-06-11T09:58:33Z","snapshot_observed_at":"2026-08-07T04:43:04.875057Z","submitted_at":"2025-06-11T09:58:33Z","title":"Searching Efficient Deep Architectures for Radar Target Detection using Monte-Carlo Tree Search","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:50:33.396828Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2506.21772"},"observation_digest":"sha256:25cb7bdf3f9b8980e1939acd72681228e632febb3ed915fc902323e671d86d56","observation_id":"868df59b-5cf2-450e-a9f4-4b271d1413e8","resolution":{"observed_at":"2026-08-07T04:50:33.396828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-06T14:55:28.436138Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.17301","last_updated":"2025-07-23T08:06:13Z","snapshot_observed_at":"2026-08-06T14:49:22.729136Z","submitted_at":"2025-07-23T08:06:13Z","title":"Efficient Column-Wise N:M Pruning on RISC-V CPU","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T14:55:28.436138Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2507.17301"},"observation_digest":"sha256:435038cb21f9097bed370907160c2127febae7f67ba45c2cd994fd3944b3e8ab","observation_id":"828e290c-4146-411d-aa1b-b22b4f845db9","resolution":{"observed_at":"2026-08-06T14:55:28.436138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-05T22:03:09.861416Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.08339","last_updated":"2025-08-11T04:13:56Z","snapshot_observed_at":"2026-08-06T12:01:44.042194Z","submitted_at":"2025-08-11T04:13:56Z","title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","version":1},"reference_index":141,"source":"pdf_text","source_observed_at":"2026-08-05T22:03:09.861416Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2508.08339"},"observation_digest":"sha256:522bc17162f77ff6a15f5c0da7be2922f25a0b1aaae4620b530a8c948163e17b","observation_id":"0b6bef41-c4bd-4e4f-af24-b00ba500cd7f","resolution":{"observed_at":"2026-08-05T22:03:09.861416Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":"2006.05467","doi":"10.48550/arxiv.2006.05467","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Advances in Neural Information Proces s- ing Systems (2020)","venue":"arXiv (Cornell University)","work_id":"eb5f2473-840d-467a-bfbb-554fe63218ce","year":2020},"citing_paper":{"arxiv_id":"2604.10560","last_updated":"2026-04-12T10:04:48Z","snapshot_observed_at":"2026-07-06T22:59:09.778842Z","submitted_at":"2026-04-12T10:04:48Z","title":"Heterogeneous Connectivity in Sparse Networks: Fan-in Profiles, Gradient Hierarchy, and Topological Equilibria","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-10T16:44:28.554276Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2604.10560"},"observation_digest":"sha256:4a0b34e6507ec0542ce8b9b8ff77525a8ebbd59e3573dfb57bab607baab69e5a","observation_id":"2b98958b-5a28-4db8-8903-7b102b416c37","resolution":{"observed_at":"2026-05-11T08:16:01.318271Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":"2006.05467","doi":"10.48550/arxiv.2006.05467","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Advances in Neural Information Proces s- ing Systems (2020)","venue":"arXiv (Cornell University)","work_id":"eb5f2473-840d-467a-bfbb-554fe63218ce","year":2020},"citing_paper":{"arxiv_id":"2604.27052","last_updated":"2026-04-29T18:00:01Z","snapshot_observed_at":"2026-07-31T07:42:28.716016Z","submitted_at":"2026-04-29T18:00:01Z","title":"Man, Machine, and Mathematics","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-05-07T09:04:54.618705Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2604.27052"},"observation_digest":"sha256:50b4c860147cfe161ba85eaba8f85369ce1e906903f357680975c9eaca33715c","observation_id":"974f6a07-b6ec-4dbe-bced-572803e2617c","resolution":{"observed_at":"2026-05-12T09:51:27.783905Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":"2006.05467","doi":"10.48550/arxiv.2006.05467","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Advances in Neural Information Proces s- ing Systems (2020)","venue":"arXiv (Cornell University)","work_id":"eb5f2473-840d-467a-bfbb-554fe63218ce","year":2020},"citing_paper":{"arxiv_id":"2605.09639","last_updated":"2026-05-13T22:20:37Z","snapshot_observed_at":"2026-07-06T23:21:44.900680Z","submitted_at":"2026-05-10T16:34:39Z","title":"XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-12T02:52:50.298400Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2605.09639"},"observation_digest":"sha256:9272090cca33efe986da9c3eba1698dd643c5b6426f2ea77201db866bdd46e94","observation_id":"73648cb8-ede6-4c29-b9bc-4c45d214487f","resolution":{"observed_at":"2026-05-12T02:56:17.950231Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":"2006.05467","doi":"10.48550/arxiv.2006.05467","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Advances in Neural Information Proces s- ing Systems (2020)","venue":"arXiv (Cornell University)","work_id":"eb5f2473-840d-467a-bfbb-554fe63218ce","year":2020},"citing_paper":{"arxiv_id":"2605.09639","last_updated":"2026-05-13T22:20:37Z","snapshot_observed_at":"2026-07-06T23:21:44.900680Z","submitted_at":"2026-05-10T16:34:39Z","title":"XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-15T05:39:34.528827Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2605.09639"},"observation_digest":"sha256:325e0d572ab31cf26567fe52d714599a45f140fd6360e05b633ea87a6eb6b20a","observation_id":"ce8196d5-902f-4ce9-a740-0aef95a98160","resolution":{"observed_at":"2026-05-15T05:39:47.262686Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":"2006.05467","doi":"10.48550/arxiv.2006.05467","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Advances in Neural Information Proces s- ing Systems (2020)","venue":"arXiv (Cornell University)","work_id":"eb5f2473-840d-467a-bfbb-554fe63218ce","year":2020},"citing_paper":{"arxiv_id":"2605.12207","last_updated":"2026-05-12T14:46:00Z","snapshot_observed_at":"2026-07-06T23:23:54.142937Z","submitted_at":"2026-05-12T14:46:00Z","title":"Not How Many, But Which: Parameter Placement in Low-Rank Adaptation","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-13T06:13:55.497799Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2605.12207"},"observation_digest":"sha256:e2dca6cbce4b4089ec7f4d2ade1aefe144d4ece0fd7b361322092f73af3c7908","observation_id":"728598be-c2a3-4d8a-9596-42ba7360df30","resolution":{"observed_at":"2026-05-13T06:17:23.161921Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":"2006.05467","doi":"10.48550/arxiv.2006.05467","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Advances in Neural Information Proces s- ing Systems (2020)","venue":"arXiv (Cornell University)","work_id":"eb5f2473-840d-467a-bfbb-554fe63218ce","year":2020},"citing_paper":{"arxiv_id":"2605.25134","last_updated":"2026-05-29T11:48:18Z","snapshot_observed_at":"2026-07-06T23:35:06.733347Z","submitted_at":"2026-05-24T15:25:17Z","title":"Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate","version":3},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-06-30T11:47:36.599236Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2605.25134"},"observation_digest":"sha256:e7349041f65410e487fc5e2d28b19fdf9228a87312dfc157ada8d3a3b12042d5","observation_id":"b381cfd0-1f3d-4436-b5e6-210234ae7a17","resolution":{"observed_at":"2026-06-30T11:54:38.484306Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","version":3},"cited_work":{"arxiv_id":"2006.05467","doi":"10.48550/arxiv.2006.05467","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.05467","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Advances in Neural Information Proces s- ing Systems (2020)","venue":"arXiv (Cornell University)","work_id":"eb5f2473-840d-467a-bfbb-554fe63218ce","year":2020},"citing_paper":{"arxiv_id":"2606.22019","last_updated":"2026-06-20T12:48:31Z","snapshot_observed_at":"2026-08-06T19:21:18.734073Z","submitted_at":"2026-06-20T12:48:31Z","title":"Channel Location Constrains the Auditability of Subliminal Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-26T11:52:03.948568Z"},"links":{"cited_paper":"/paper/2006.05467","citing_paper":"/paper/2606.22019"},"observation_digest":"sha256:3a42c362d37367d6ffb8bd74e5e12e3c763469fef1b5637757606c0dcd0e88d0","observation_id":"d08197e2-e059-47c3-a5f3-372e9c1a1a16","resolution":{"observed_at":"2026-07-04T08:19:44.335780Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2006.05467/citation-record","integrity":"/paper/2006.05467/integrity","json":"/paper/2006.05467/citation-record.json","paper":"/paper/2006.05467"},"outbound":[],"paper":{"arxiv_id":"2006.05467","last_updated":"2020-11-19T03:54:34Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T21:26:14.847413Z","submitted_at":"2020-06-09T19:21:57Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2006.05467."}