{"as_of":"2026-08-05T04:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d18d5ec822c49084473cef97c200d385f26bd4dd8c6f4fbd27bf989fa8def8b9","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T02:12:28.098597Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-03T09:37:49.417670Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.21561","last_updated":"2026-06-11T07:05:17Z","snapshot_observed_at":"2026-07-06T21:17:00.913307Z","submitted_at":"2025-04-30T12:01:27Z","title":"Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning","version":5},"cited_work":{"arxiv_id":"2504.21561","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.21561","snapshot_observed_at":"2026-07-03T09:37:49.417670Z","title":"Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning","venue":"cs.CV","work_id":"cc59f3d1-3397-405b-9035-069c260c8db4","year":2025},"citing_paper":{"arxiv_id":"2606.12384","last_updated":"2026-07-31T08:54:09Z","snapshot_observed_at":"2026-08-05T04:09:57.903298Z","submitted_at":"2026-06-10T17:47:07Z","title":"APPO: Agentic Procedural Policy Optimization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-27T10:21:55.485624Z"},"links":{"cited_paper":"/paper/2504.21561","citing_paper":"/paper/2606.12384"},"observation_digest":"sha256:89be6ad8464f174d099925219db3912ed9fc04e2d066a8895fb5b08ce4d53f69","observation_id":"da5132a7-8b87-4936-a76c-0d4d54be4f53","resolution":{"observed_at":"2026-07-03T09:37:49.418940Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.21561","last_updated":"2026-06-11T07:05:17Z","snapshot_observed_at":"2026-07-06T21:17:00.913307Z","submitted_at":"2025-04-30T12:01:27Z","title":"Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.21561","snapshot_observed_at":"2026-08-03T02:12:28.098597Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.12384","last_updated":"2026-07-31T08:54:09Z","snapshot_observed_at":"2026-08-05T04:09:57.903298Z","submitted_at":"2026-06-10T17:47:07Z","title":"APPO: Agentic Procedural Policy Optimization","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T02:12:28.098597Z"},"links":{"cited_paper":"/paper/2504.21561","citing_paper":"/paper/2606.12384"},"observation_digest":"sha256:cdc9b86fed2a6b2462c5d21e5d0461ea62a2cf94a3cf61f18c59909d2c252900","observation_id":"d5ee414a-4573-458b-84b8-181f462be16e","resolution":{"observed_at":"2026-08-03T02:12:28.098597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.21561","last_updated":"2026-06-11T07:05:17Z","snapshot_observed_at":"2026-07-06T21:17:00.913307Z","submitted_at":"2025-04-30T12:01:27Z","title":"Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning","version":5},"cited_work":{"arxiv_id":"2504.21561","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.21561","snapshot_observed_at":"2026-07-03T09:37:49.417670Z","title":"Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning","venue":"cs.CV","work_id":"cc59f3d1-3397-405b-9035-069c260c8db4","year":2025},"citing_paper":{"arxiv_id":"2606.31392","last_updated":"2026-06-30T09:19:38Z","snapshot_observed_at":"2026-07-07T00:05:07.912609Z","submitted_at":"2026-06-30T09:19:38Z","title":"ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-01T05:23:21.162004Z"},"links":{"cited_paper":"/paper/2504.21561","citing_paper":"/paper/2606.31392"},"observation_digest":"sha256:277977f3b8a7640a77d6823586d5d106f179ce32acaa3e862e27edd1adff21b0","observation_id":"9d92bb0e-73e1-410a-b86e-0d0a1441882f","resolution":{"observed_at":"2026-07-01T10:35:41.878057Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2504.21561/citation-record","integrity":"/paper/2504.21561/integrity","json":"/paper/2504.21561/citation-record.json","paper":"/paper/2504.21561"},"outbound":[],"paper":{"arxiv_id":"2504.21561","last_updated":"2026-06-11T07:05:17Z","latest_version":5,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T21:17:00.913307Z","submitted_at":"2025-04-30T12:01:27Z","title":"Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2504.21561."}