{"as_of":"2026-08-12T13:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1c0d38abc4b4f6d3d997dfdf32e24ef9088c4ecbd97dd9002508373e908d9c6d","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T21:46:28.542444Z","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":"2026-05-18T13:02:37.495563Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.12402","last_updated":"2023-07-30T13:20:13Z","snapshot_observed_at":"2026-08-08T05:02:29.486711Z","submitted_at":"2022-11-22T16:48:01Z","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","version":2},"cited_work":{"arxiv_id":"2211.12402","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.12402","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2211.12402","venue":null,"work_id":"801133a4-b76c-4228-b7a9-7293a9fa90cb","year":2023},"citing_paper":{"arxiv_id":"2311.01378","last_updated":"2024-02-05T03:46:00Z","snapshot_observed_at":"2026-07-31T21:45:51.138808Z","submitted_at":"2023-11-02T16:34:33Z","title":"Vision-Language Foundation Models as Effective Robot Imitators","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-16T21:44:27.562453Z"},"links":{"cited_paper":"/paper/2211.12402","citing_paper":"/paper/2311.01378"},"observation_digest":"sha256:7af355eb7be6326462596eccb4035503e706c65425f2ffd6c54881746e79672d","observation_id":"78aefb08-78d4-476d-a35f-ae965cd083a0","resolution":{"observed_at":"2026-05-16T21:44:27.636185Z","resolver_source":"arxiv_id","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":"2211.12402","last_updated":"2023-07-30T13:20:13Z","snapshot_observed_at":"2026-08-08T05:02:29.486711Z","submitted_at":"2022-11-22T16:48:01Z","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.12402","snapshot_observed_at":"2026-08-10T21:46:28.542444Z","title":"X2-vlm: All-in-one pre-trained model for vision-language tasks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03939","last_updated":"2025-01-11T14:21:37Z","snapshot_observed_at":"2026-08-11T03:31:24.809067Z","submitted_at":"2025-01-07T17:00:35Z","title":"Visual question answering: from early developments to recent advances -- a survey","version":2},"reference_index":107,"source":"arxiv_source","source_observed_at":"2026-08-10T21:46:28.542444Z"},"links":{"cited_paper":"/paper/2211.12402","citing_paper":"/paper/2501.03939"},"observation_digest":"sha256:7438d65de447e1a72ee732e1eae82004b81105c641ffa73c0454189088392b9a","observation_id":"2c153e38-dc5b-44ca-af25-dcc294b3b58b","resolution":{"observed_at":"2026-08-10T21:46:28.542444Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12402","last_updated":"2023-07-30T13:20:13Z","snapshot_observed_at":"2026-08-08T05:02:29.486711Z","submitted_at":"2022-11-22T16:48:01Z","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.12402","snapshot_observed_at":"2026-08-10T20:22:28.836606Z","title":"X 2-vlm: All-in-one pre-trained model for vision-language tasks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.08771","last_updated":"2025-07-02T12:39:10Z","snapshot_observed_at":"2026-08-12T09:05:13.248930Z","submitted_at":"2025-01-15T12:44:52Z","title":"Admitting Ignorance Helps the Video Question Answering Models to Answer","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T20:22:28.836606Z"},"links":{"cited_paper":"/paper/2211.12402","citing_paper":"/paper/2501.08771"},"observation_digest":"sha256:0ca5467884f541a9d21e192a090a20379324f310713bb990281695374a213ac7","observation_id":"803b90c5-5350-4593-ad3e-b099f4f80ad1","resolution":{"observed_at":"2026-08-10T20:22:28.836606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12402","last_updated":"2023-07-30T13:20:13Z","snapshot_observed_at":"2026-08-08T05:02:29.486711Z","submitted_at":"2022-11-22T16:48:01Z","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","version":2},"cited_work":{"arxiv_id":"2211.12402","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.12402","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2211.12402","venue":null,"work_id":"801133a4-b76c-4228-b7a9-7293a9fa90cb","year":2023},"citing_paper":{"arxiv_id":"2509.22123","last_updated":"2026-05-13T12:28:55Z","snapshot_observed_at":"2026-08-08T13:18:54.000166Z","submitted_at":"2025-09-26T09:46:13Z","title":"Multilingual Vision-Language Models, A Survey","version":2},"reference_index":164,"source":"pdf_text","source_observed_at":"2026-05-18T13:02:08.000814Z"},"links":{"cited_paper":"/paper/2211.12402","citing_paper":"/paper/2509.22123"},"observation_digest":"sha256:174bf5ea392152884f3a713b71374d4368070c8e717a0a8a47decdd3b6eab1dd","observation_id":"ca5c8fa8-8eab-468f-94a3-3dc0f21a84ff","resolution":{"observed_at":"2026-05-18T13:02:37.498107Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2211.12402/citation-record","integrity":"/paper/2211.12402/integrity","json":"/paper/2211.12402/citation-record.json","paper":"/paper/2211.12402"},"outbound":[],"paper":{"arxiv_id":"2211.12402","last_updated":"2023-07-30T13:20:13Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T05:02:29.486711Z","submitted_at":"2022-11-22T16:48:01Z","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks"},"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 4 inbound Pith citation observations for arXiv:2211.12402."}