{"as_of":"2026-08-07T17:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6c54496b2aa9e2a583cbedf5e84512e4fd630ed491493b14375b419e4b50bd60","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":17,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":17,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":17,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:34:37.639754Z","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":"2026-07-02T08:16:48.019661Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":"2002.07376","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-07-02T08:16:48.019661Z","title":"arXiv preprint arXiv:2002.07376 , year=","venue":null,"work_id":"c4d29a5d-ff53-4467-9015-8f08cc3ff51f","year":2002},"citing_paper":{"arxiv_id":"2310.12508","last_updated":"2024-04-04T07:45:38Z","snapshot_observed_at":"2026-08-03T17:30:25.153454Z","submitted_at":"2023-10-19T06:17:17Z","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","version":5},"reference_index":170,"source":"arxiv_source","source_observed_at":"2026-05-16T17:56:23.281678Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2310.12508"},"observation_digest":"sha256:367fd52de0c50f70ddbe8742a45df51fcf953991bbce35861af6f2b96f8598c5","observation_id":"1cbfc631-4d76-4da8-b919-9e4aa0053e2c","resolution":{"observed_at":"2026-05-16T17:56:23.622163Z","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":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-07T15:34:37.639754Z","title":"Picking winning tick- ets before training by preserving gradient flow,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2505.14797","last_updated":"2025-05-20T18:08:15Z","snapshot_observed_at":"2026-08-07T15:27:11.003672Z","submitted_at":"2025-05-20T18:08:15Z","title":"Efficient Privacy-Preserving Cross-Silo Federated Learning with Multi-Key Homomorphic Encryption","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:34:37.639754Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2505.14797"},"observation_digest":"sha256:4e87fcad7cd9d377ee0e712ab621cceb507b03628254b31ef16969f989615451","observation_id":"80bc991e-b43c-4815-ab48-766998a16114","resolution":{"observed_at":"2026-08-07T15:34:37.639754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-07T14:44:21.715735Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.17909","last_updated":"2025-05-23T13:53:21Z","snapshot_observed_at":"2026-08-07T14:35:57.000429Z","submitted_at":"2025-05-23T13:53:21Z","title":"NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-07T14:44:21.715735Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2505.17909"},"observation_digest":"sha256:062ec10ab386380b25d7a682dc2139473aa0caee587f919d7d54ff3a07f60481","observation_id":"609ad148-c3bc-42f5-9ba5-dd3c5f57f4aa","resolution":{"observed_at":"2026-08-07T14:44:21.715735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-07T14:33:09.091356Z","title":"Picking winning tickets before training by preserving gradient flow,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.18563","last_updated":"2025-05-24T07:06:36Z","snapshot_observed_at":"2026-08-07T14:27:16.669960Z","submitted_at":"2025-05-24T07:06:36Z","title":"PacTrain: Pruning and Adaptive Sparse Gradient Compression for Efficient Collective Communication in Distributed Deep Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T14:33:09.091356Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2505.18563"},"observation_digest":"sha256:945101394c99a921d94420084a935b19372506049216c393ccb1e43a779ad669","observation_id":"ea803949-0526-4e7c-9a97-99374dd142f1","resolution":{"observed_at":"2026-08-07T14:33:09.091356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-07T05:27:08.102709Z","title":"arXiv preprint arXiv:2002.07376 (2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07975","last_updated":"2025-06-09T17:49:29Z","snapshot_observed_at":"2026-08-07T05:18:54.986253Z","submitted_at":"2025-06-09T17:49:29Z","title":"Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T05:27:08.102709Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2506.07975"},"observation_digest":"sha256:3595f4a05b346c97cb85ab84ab3a90137fefc43ae54d73041496585a115c23f0","observation_id":"a75551b0-eea2-4f65-b1af-8522cd30e42a","resolution":{"observed_at":"2026-08-07T05:27:08.102709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-07T04:15:17.025375Z","title":"Picking winning tickets before training by preserving gradient flow","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.11449","last_updated":"2025-06-13T04:01:34Z","snapshot_observed_at":"2026-08-07T06:32:50.465354Z","submitted_at":"2025-06-13T04:01:34Z","title":"Dynamic Sparse Training of Diagonally Sparse Networks","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T04:15:17.025375Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2506.11449"},"observation_digest":"sha256:dd52000cec7ad9de4ccf51704e805adc880e9941ce3ac14b555817bf8be7549e","observation_id":"e7fd8b2d-45e8-4de9-ad77-f721bf722307","resolution":{"observed_at":"2026-08-07T04:15:17.025375Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-07T04:50:33.511032Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow,","venue":null,"work_id":null,"year":2002},"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":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:50:33.511032Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2506.21772"},"observation_digest":"sha256:82f7318b7a1902710953007e36dd0d29e74e122ebda6961dfe72f7e3ffd159d6","observation_id":"097eb9b6-9752-4214-ba26-09b33d081714","resolution":{"observed_at":"2026-08-07T04:50:33.511032Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-06T19:07:36.919868Z","title":"Picking winning tickets before training by preserving gradient flow","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.07140","last_updated":"2025-07-14T04:57:05Z","snapshot_observed_at":"2026-08-07T03:13:31.294588Z","submitted_at":"2025-07-09T03:25:45Z","title":"Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-06T19:07:36.919868Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2507.07140"},"observation_digest":"sha256:616e4c707b27b1c92b0bad84cd8e3fac48eb3515ff4fbc6ae0251793625cd297","observation_id":"d9b71dcf-fa57-483c-9ff7-06ddaa2c2f24","resolution":{"observed_at":"2026-08-06T19:07:36.919868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-06T14:55:28.441400Z","title":"Picking winning tickets before training by preserving gradient flow, 2020","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":41,"source":"pdf_text","source_observed_at":"2026-08-06T14:55:28.441400Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2507.17301"},"observation_digest":"sha256:d788e807f1b8e75827d21e863f472269017b1034224deaabc18d7c4c4c2497c6","observation_id":"de031a25-1e16-4682-881b-efdf1ad903b5","resolution":{"observed_at":"2026-08-06T14:55:28.441400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-05T22:03:09.880445Z","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":150,"source":"pdf_text","source_observed_at":"2026-08-05T22:03:09.880445Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2508.08339"},"observation_digest":"sha256:a5a1cd3c129b6fe02f8f7b766facccccd454516d3fdc6b2f98cd0570dbdde888","observation_id":"f93a18b3-5865-4e9d-9df6-a2574931afde","resolution":{"observed_at":"2026-08-05T22:03:09.880445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-05T21:08:18.710324Z","title":"Picking winning tickets before training by preserving gradient flow","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2508.09471","last_updated":"2025-08-13T04:00:56Z","snapshot_observed_at":"2026-08-05T21:08:18.045156Z","submitted_at":"2025-08-13T04:00:56Z","title":"EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T21:08:18.710324Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2508.09471"},"observation_digest":"sha256:1835c671c93811b1818ba16e4a5978d464539b00b371017ebdfb985f9dd1b74e","observation_id":"5c017746-2f3a-4eff-8a96-9e499b1f7067","resolution":{"observed_at":"2026-08-05T21:08:18.710324Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":"2002.07376","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-07-02T08:16:48.019661Z","title":"arXiv preprint arXiv:2002.07376 , year=","venue":null,"work_id":"c4d29a5d-ff53-4467-9015-8f08cc3ff51f","year":2002},"citing_paper":{"arxiv_id":"2604.09988","last_updated":"2026-04-11T02:16:33Z","snapshot_observed_at":"2026-08-02T23:45:36.179517Z","submitted_at":"2026-04-11T02:16:33Z","title":"Engineering Resource-constrained Software Systems with DNN Components: a Concept-based Pruning Approach","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-05-10T16:42:39.903430Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2604.09988"},"observation_digest":"sha256:ccbaaac08c6ec676cf998500c77e12d2e3936b153cd5accc49063cc3d91e6256","observation_id":"1acd5da7-b604-4fff-b307-e5b9d83e948c","resolution":{"observed_at":"2026-05-11T08:20:59.216348Z","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":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":"2002.07376","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-07-02T08:16:48.019661Z","title":"arXiv preprint arXiv:2002.07376 , year=","venue":null,"work_id":"c4d29a5d-ff53-4467-9015-8f08cc3ff51f","year":2002},"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":86,"source":"pdf_text","source_observed_at":"2026-05-13T06:13:55.497799Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2605.12207"},"observation_digest":"sha256:d57ecd3e822dd503923f19cb038822e0f956c9b50172ea46581b1486c3132972","observation_id":"39c6b556-1841-4003-aea3-dd023609d4b5","resolution":{"observed_at":"2026-05-13T06:17:23.193607Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":"2002.07376","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-07-02T08:16:48.019661Z","title":"arXiv preprint arXiv:2002.07376 , year=","venue":null,"work_id":"c4d29a5d-ff53-4467-9015-8f08cc3ff51f","year":2002},"citing_paper":{"arxiv_id":"2606.05478","last_updated":"2026-06-03T21:57:05Z","snapshot_observed_at":"2026-08-06T02:03:24.426362Z","submitted_at":"2026-06-03T21:57:05Z","title":"Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-06-28T06:14:02.804743Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2606.05478"},"observation_digest":"sha256:c7134b444e4c69f6d9edf06707714b5af536792eb13295d5c3d9061638b40dd9","observation_id":"91644d8b-8b40-487b-8a22-a3e29dd7ea0d","resolution":{"observed_at":"2026-07-02T08:16:48.021191Z","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":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":"2002.07376","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-07-02T08:16:48.019661Z","title":"arXiv preprint arXiv:2002.07376 , year=","venue":null,"work_id":"c4d29a5d-ff53-4467-9015-8f08cc3ff51f","year":2002},"citing_paper":{"arxiv_id":"2606.30382","last_updated":"2026-06-29T14:39:38Z","snapshot_observed_at":"2026-08-03T06:07:39.987871Z","submitted_at":"2026-06-29T14:39:38Z","title":"RQP: Resource-Oriented Quantiser Pruning for Neural Networks on FPGAs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-30T03:36:26.865685Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2606.30382"},"observation_digest":"sha256:b0aaeadb14508c2511d3f2d14013808ff88150c6a9221f117e1046a8530b21fa","observation_id":"d1ac8f57-f191-486a-bdd6-683e58ba9776","resolution":{"observed_at":"2026-07-01T15:25:47.438055Z","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":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-02T02:25:33.138417Z","title":"Picking winning tickets before training by preserving gradient flow.arXiv preprint arXiv:2002.07376, 2020","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.20555","last_updated":"2026-07-15T20:20:43Z","snapshot_observed_at":"2026-08-06T08:47:16.760212Z","submitted_at":"2026-07-15T20:20:43Z","title":"Double-Scoring: Reliable Extraction of Strong Lottery Tickets","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T02:25:33.138417Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2607.20555"},"observation_digest":"sha256:e664afee02b92d7c6ed281f1d3497455f66d9a2a09caa5575e8acc66e4174947","observation_id":"d240a51a-5447-45a5-87d6-0ae3a2ce8b32","resolution":{"observed_at":"2026-08-02T02:25:33.138417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-01T16:42:15.153700Z","title":"arXiv preprint arXiv:2002.07376 , year=","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.26404","last_updated":"2026-07-29T02:35:55Z","snapshot_observed_at":"2026-08-03T19:06:45.585998Z","submitted_at":"2026-07-29T02:35:55Z","title":"Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts","version":1},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-01T16:42:15.153700Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2607.26404"},"observation_digest":"sha256:b2ab8e54763ea2bd7f89688df27764c2ee47cd029cc6701ee77f6d55e789d83a","observation_id":"8787a990-056b-48cf-9e1c-1db6dca4a204","resolution":{"observed_at":"2026-08-01T16:42:15.153700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2002.07376/citation-record","integrity":"/paper/2002.07376/integrity","json":"/paper/2002.07376/citation-record.json","paper":"/paper/2002.07376"},"outbound":[],"paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient 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 17 inbound Pith citation observations for arXiv:2002.07376."}