{"as_of":"2026-08-12T17:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5d05ab20e29bba3975cfa9dc2b64023992899ad500501e026d45034696ccad2a","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:53:59.934887Z","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":"2026-08-07T13:54:10.870000Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.03181","last_updated":"2025-05-06T04:51:57Z","snapshot_observed_at":"2026-08-12T16:34:42.038755Z","submitted_at":"2025-05-06T04:51:57Z","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","version":1},"cited_work":{"arxiv_id":"2505.03181","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.03181","snapshot_observed_at":"2026-08-07T13:54:10.870000Z","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","venue":"cs.LG","work_id":"7bf01313-65c0-4a83-9192-69c9ef96511d","year":2025},"citing_paper":{"arxiv_id":"2505.20726","last_updated":"2025-07-29T02:51:37Z","snapshot_observed_at":"2026-08-07T22:45:15.753079Z","submitted_at":"2025-05-27T05:14:50Z","title":"ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:59.934887Z"},"links":{"cited_paper":"/paper/2505.03181","citing_paper":"/paper/2505.20726"},"observation_digest":"sha256:ac5aa998120a7f3314acbde6ddaaba2877568d4e445a8ef1272a76464202908d","observation_id":"3cfe34e8-1326-4792-b080-df0193139256","resolution":{"observed_at":"2026-08-07T13:54:10.983636Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.03181","last_updated":"2025-05-06T04:51:57Z","snapshot_observed_at":"2026-08-12T16:34:42.038755Z","submitted_at":"2025-05-06T04:51:57Z","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.03181","snapshot_observed_at":"2026-08-02T23:00:26.027030Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.15278","last_updated":"2026-05-31T02:07:13Z","snapshot_observed_at":"2026-08-08T02:47:52.848942Z","submitted_at":"2026-02-17T00:33:53Z","title":"Visual Persuasion: What Influences Decisions of Vision-Language Models?","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-02T23:00:26.027030Z"},"links":{"cited_paper":"/paper/2505.03181","citing_paper":"/paper/2602.15278"},"observation_digest":"sha256:7b3684d09ad3750531621fe405c14d6da7969d5bd2cd9d8e9a274edecac10e1b","observation_id":"08aa36ed-7f8e-4bab-810f-400428518e1e","resolution":{"observed_at":"2026-08-02T23:00:26.027030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.03181/citation-record","integrity":"/paper/2505.03181/integrity","json":"/paper/2505.03181/citation-record.json","paper":"/paper/2505.03181"},"outbound":[],"paper":{"arxiv_id":"2505.03181","last_updated":"2025-05-06T04:51:57Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T16:34:42.038755Z","submitted_at":"2025-05-06T04:51:57Z","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2505.03181."}