{"as_of":"2026-08-11T21:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1ca4cef27213d7579ad7efb14337e2a88ef85991a739e9aaac55a33331bb00bd","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":"2026-08-11T06:34:44.6726+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":"2026-08-06T20:15:52.772660Z","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":"2026-05-13T01:36:24.185938Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.04618","last_updated":"2025-03-06T17:03:17Z","snapshot_observed_at":"2026-08-07T17:24:08.451711Z","submitted_at":"2025-03-06T17:03:17Z","title":"Better Process Supervision with Bi-directional Rewarding Signals","version":1},"cited_work":{"arxiv_id":"2503.04618","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.04618","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Better process supervision with bi-directional rewarding signals","venue":null,"work_id":"ad958752-e170-415b-a6f9-0d746dc07b1a","year":2025},"citing_paper":{"arxiv_id":"2502.17419","last_updated":"2025-06-25T02:24:46Z","snapshot_observed_at":"2026-08-10T09:42:17.185681Z","submitted_at":"2025-02-24T18:50:52Z","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","version":6},"reference_index":167,"source":"pdf_text","source_observed_at":"2026-05-13T01:36:23.845366Z"},"links":{"cited_paper":"/paper/2503.04618","citing_paper":"/paper/2502.17419"},"observation_digest":"sha256:ff8b2b7e4fbe1fe36c0f83975f5691830b00af22c85166156509721210ed15b7","observation_id":"8b9ab6c2-3959-4d3b-9024-d8392cdc1d3f","resolution":{"observed_at":"2026-05-13T01:36:24.188168Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.04618","last_updated":"2025-03-06T17:03:17Z","snapshot_observed_at":"2026-08-07T17:24:08.451711Z","submitted_at":"2025-03-06T17:03:17Z","title":"Better Process Supervision with Bi-directional Rewarding Signals","version":1},"cited_work":{"arxiv_id":"2503.04618","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.04618","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Better process supervision with bi-directional rewarding signals","venue":null,"work_id":"ad958752-e170-415b-a6f9-0d746dc07b1a","year":2025},"citing_paper":{"arxiv_id":"2503.09567","last_updated":"2025-07-18T15:57:54Z","snapshot_observed_at":"2026-08-08T22:33:20.124926Z","submitted_at":"2025-03-12T17:35:03Z","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","version":5},"reference_index":104,"source":"pdf_text","source_observed_at":"2026-05-12T08:40:40.910461Z"},"links":{"cited_paper":"/paper/2503.04618","citing_paper":"/paper/2503.09567"},"observation_digest":"sha256:d2d2da454ad70d2bb799a9a7fec4f74eb71c4f2ec88637f0a343a7ccb87c58ec","observation_id":"c01d71ee-1804-4a3a-80bc-2a5460fbbee9","resolution":{"observed_at":"2026-05-12T08:40:41.897121Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.04618","last_updated":"2025-03-06T17:03:17Z","snapshot_observed_at":"2026-08-07T17:24:08.451711Z","submitted_at":"2025-03-06T17:03:17Z","title":"Better Process Supervision with Bi-directional Rewarding Signals","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.04618","snapshot_observed_at":"2026-08-06T20:15:52.772660Z","title":"Better process supervision with bi-directional rewarding signals","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.03483","last_updated":"2025-07-08T05:05:04Z","snapshot_observed_at":"2026-08-09T01:40:47.049405Z","submitted_at":"2025-07-04T11:20:09Z","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T20:15:52.772660Z"},"links":{"cited_paper":"/paper/2503.04618","citing_paper":"/paper/2507.03483"},"observation_digest":"sha256:426e682763948ac999cfacedb3dc231e7e3b4d1307d0bcc50f6e63314ee6e593","observation_id":"29c5a000-9b78-4855-8090-ad9185c86536","resolution":{"observed_at":"2026-08-06T20:15:52.772660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.04618","last_updated":"2025-03-06T17:03:17Z","snapshot_observed_at":"2026-08-07T17:24:08.451711Z","submitted_at":"2025-03-06T17:03:17Z","title":"Better Process Supervision with Bi-directional Rewarding Signals","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.04618","snapshot_observed_at":"2026-08-04T13:15:42.560110Z","title":"Better process supervision with bi-directional rewarding signals","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.01167","last_updated":"2026-05-30T06:40:26Z","snapshot_observed_at":"2026-08-09T12:10:30.690264Z","submitted_at":"2025-10-01T17:54:15Z","title":"Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T13:15:42.560110Z"},"links":{"cited_paper":"/paper/2503.04618","citing_paper":"/paper/2510.01167"},"observation_digest":"sha256:b90beea79f8eaa172259f73182c105db945aafa61de8f97f04bdcbd3ced8280f","observation_id":"30456905-3be2-46e8-9563-e7d1c9fe7d7d","resolution":{"observed_at":"2026-08-04T13:15:42.560110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2503.04618/citation-record","integrity":"/paper/2503.04618/integrity","json":"/paper/2503.04618/citation-record.json","paper":"/paper/2503.04618"},"outbound":[],"paper":{"arxiv_id":"2503.04618","last_updated":"2025-03-06T17:03:17Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T17:24:08.451711Z","submitted_at":"2025-03-06T17:03:17Z","title":"Better Process Supervision with Bi-directional Rewarding Signals"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2503.04618."}