{"as_of":"2026-08-17T03:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5c858b79c97a78f2abcaa10ed998199cbce82ffed428ed94e58bcd5a4443efe7","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":"2026-08-16T06:30:59.297886+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":"2026-08-15T20:24:36.037648Z","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":"2026-05-18T10:46:17.231325Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.12327","last_updated":"2024-04-26T01:50:55Z","snapshot_observed_at":"2026-08-16T14:41:38.465063Z","submitted_at":"2023-11-21T03:40:09Z","title":"Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12327","snapshot_observed_at":"2026-08-12T15:06:09.154447Z","title":"Vilam: A vision-language model with enhanced visual grounding and generalization capability,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.14715","last_updated":"2024-11-22T03:52:37Z","snapshot_observed_at":"2026-08-15T07:30:29.406621Z","submitted_at":"2024-11-22T03:52:37Z","title":"Any-to-3D Generation via Hybrid Diffusion Supervision","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T15:06:09.154447Z"},"links":{"cited_paper":"/paper/2311.12327","citing_paper":"/paper/2411.14715"},"observation_digest":"sha256:93bddd640ee9f73c99f524b520877bc82a0228697e85c7aa2092ca3a0a0c3f32","observation_id":"d1262267-e2dc-430e-81d1-5e465e451c67","resolution":{"observed_at":"2026-08-12T15:06:09.154447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12327","last_updated":"2024-04-26T01:50:55Z","snapshot_observed_at":"2026-08-16T14:41:38.465063Z","submitted_at":"2023-11-21T03:40:09Z","title":"Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12327","snapshot_observed_at":"2026-08-15T20:24:36.037648Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13081","last_updated":"2025-05-19T13:13:38Z","snapshot_observed_at":"2026-08-16T21:47:07.124602Z","submitted_at":"2025-05-19T13:13:38Z","title":"Walking the Tightrope: Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:36.037648Z"},"links":{"cited_paper":"/paper/2311.12327","citing_paper":"/paper/2505.13081"},"observation_digest":"sha256:b915d95d5058525928653deab425ee0556ae6990b858db95e9f13bc52f131cd4","observation_id":"7ebe48d3-79ed-4899-a6c6-b2f41d50c5e2","resolution":{"observed_at":"2026-08-15T20:24:36.037648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12327","last_updated":"2024-04-26T01:50:55Z","snapshot_observed_at":"2026-08-16T14:41:38.465063Z","submitted_at":"2023-11-21T03:40:09Z","title":"Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models","version":2},"cited_work":{"arxiv_id":"2311.12327","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.12327","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c88ee655-1831-4db7-b588-cdbba77b8268","year":2024},"citing_paper":{"arxiv_id":"2510.04142","last_updated":"2026-05-11T11:36:03Z","snapshot_observed_at":"2026-08-14T13:31:15.510705Z","submitted_at":"2025-10-05T10:42:21Z","title":"Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments","version":3},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-05-18T10:44:31.842696Z"},"links":{"cited_paper":"/paper/2311.12327","citing_paper":"/paper/2510.04142"},"observation_digest":"sha256:977be3a266796f00276cd17f280e4719b9e0ff420cd7ed22da833b40a490d027","observation_id":"3b44f9c2-f9f0-45d0-b583-3629b4dff606","resolution":{"observed_at":"2026-05-18T10:46:17.233706Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2311.12327/citation-record","integrity":"/paper/2311.12327/integrity","json":"/paper/2311.12327/citation-record.json","paper":"/paper/2311.12327"},"outbound":[],"paper":{"arxiv_id":"2311.12327","last_updated":"2024-04-26T01:50:55Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T14:41:38.465063Z","submitted_at":"2023-11-21T03:40:09Z","title":"Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2311.12327."}