{"as_of":"2026-08-09T21:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:46fa8840e0396b6b1089ab2288ab456744673d899c8cddf9bdc7470ca0867a4c","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:32:12.139557Z","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":"2026-05-25T06:40:24.853926Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.11206","last_updated":"2025-05-07T19:12:46Z","snapshot_observed_at":"2026-08-09T14:37:51.097941Z","submitted_at":"2024-06-17T04:53:47Z","title":"Retraining with Predicted Hard Labels Provably Increases Model Accuracy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11206","snapshot_observed_at":"2026-08-07T15:32:12.139557Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15195","last_updated":"2025-05-21T07:16:44Z","snapshot_observed_at":"2026-08-08T14:52:48.276800Z","submitted_at":"2025-05-21T07:16:44Z","title":"Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:32:12.139557Z"},"links":{"cited_paper":"/paper/2406.11206","citing_paper":"/paper/2505.15195"},"observation_digest":"sha256:e3f15f3d7fbee00659a62207b1455e7fda3107ff50f85e8ae9857cb4a446b382","observation_id":"646644d7-ad3d-4695-86f7-cc3766a5d9db","resolution":{"observed_at":"2026-08-07T15:32:12.139557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11206","last_updated":"2025-05-07T19:12:46Z","snapshot_observed_at":"2026-08-09T14:37:51.097941Z","submitted_at":"2024-06-17T04:53:47Z","title":"Retraining with Predicted Hard Labels Provably Increases Model Accuracy","version":3},"cited_work":{"arxiv_id":"2406.11206","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.11206","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.11206 , year=","venue":null,"work_id":"955882d1-5475-481b-aabf-7360d8e95732","year":null},"citing_paper":{"arxiv_id":"2605.04542","last_updated":"2026-05-06T06:42:47Z","snapshot_observed_at":"2026-07-06T23:17:18.486586Z","submitted_at":"2026-05-06T06:42:47Z","title":"Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation","version":1},"reference_index":111,"source":"arxiv_source","source_observed_at":"2026-05-08T16:53:00.860162Z"},"links":{"cited_paper":"/paper/2406.11206","citing_paper":"/paper/2605.04542"},"observation_digest":"sha256:0a097d8de4670a19f3f63a13848f0b373b37b03bb0688440b9bbfe5f49fb0849","observation_id":"898fd987-cb19-47e6-92fb-a8728b8a78ad","resolution":{"observed_at":"2026-05-11T17:56:08.376239Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11206","last_updated":"2025-05-07T19:12:46Z","snapshot_observed_at":"2026-08-09T14:37:51.097941Z","submitted_at":"2024-06-17T04:53:47Z","title":"Retraining with Predicted Hard Labels Provably Increases Model Accuracy","version":3},"cited_work":{"arxiv_id":"2406.11206","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.11206","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.11206 , year=","venue":null,"work_id":"955882d1-5475-481b-aabf-7360d8e95732","year":null},"citing_paper":{"arxiv_id":"2605.17767","last_updated":"2026-05-21T20:45:44Z","snapshot_observed_at":"2026-08-04T06:32:13.198687Z","submitted_at":"2026-05-18T02:37:50Z","title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","version":1},"reference_index":259,"source":"arxiv_source","source_observed_at":"2026-05-20T01:29:14.555216Z"},"links":{"cited_paper":"/paper/2406.11206","citing_paper":"/paper/2605.17767"},"observation_digest":"sha256:d8ddc40d875ef90e8c25fd4adf059037c09cb5361cca018f9444cc8574ba544a","observation_id":"fcc0fbc6-6611-456b-a647-5a00b89b1622","resolution":{"observed_at":"2026-05-20T01:32:55.952103Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11206","last_updated":"2025-05-07T19:12:46Z","snapshot_observed_at":"2026-08-09T14:37:51.097941Z","submitted_at":"2024-06-17T04:53:47Z","title":"Retraining with Predicted Hard Labels Provably Increases Model Accuracy","version":3},"cited_work":{"arxiv_id":"2406.11206","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.11206","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.11206 , year=","venue":null,"work_id":"955882d1-5475-481b-aabf-7360d8e95732","year":null},"citing_paper":{"arxiv_id":"2605.17767","last_updated":"2026-05-21T20:45:44Z","snapshot_observed_at":"2026-08-04T06:32:13.198687Z","submitted_at":"2026-05-18T02:37:50Z","title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","version":2},"reference_index":259,"source":"arxiv_source","source_observed_at":"2026-05-25T06:39:16.246591Z"},"links":{"cited_paper":"/paper/2406.11206","citing_paper":"/paper/2605.17767"},"observation_digest":"sha256:38d4d241f826c72e8533f8c37590d8327a5263f5415f386df01bed7e96769885","observation_id":"1902d477-d63e-421a-965f-2a3ef69a73dc","resolution":{"observed_at":"2026-05-25T06:40:24.857529Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.11206/citation-record","integrity":"/paper/2406.11206/integrity","json":"/paper/2406.11206/citation-record.json","paper":"/paper/2406.11206"},"outbound":[],"paper":{"arxiv_id":"2406.11206","last_updated":"2025-05-07T19:12:46Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T14:37:51.097941Z","submitted_at":"2024-06-17T04:53:47Z","title":"Retraining with Predicted Hard Labels Provably Increases Model Accuracy"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2406.11206."}