{"as_of":"2026-08-17T09:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5443150ed25d88bf48ad8dfac9c31f3e470343cffc24be899f0a3c1321ea07ed","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":"2026-08-17T06:30:58.91139+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":"2026-08-11T14:44:17.629567Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-10T05:30:23.456663Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-10T05:30:23.456663Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.07096","last_updated":"2023-12-06T03:49:10Z","snapshot_observed_at":"2026-08-16T15:24:36.581615Z","submitted_at":"2023-06-12T13:20:29Z","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07096","snapshot_observed_at":"2026-08-11T14:44:17.629567Z","title":"Global and local semantic completion learning for vision-language pre-training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11706","last_updated":"2025-05-24T17:39:32Z","snapshot_observed_at":"2026-08-15T13:09:10.090692Z","submitted_at":"2024-12-16T12:28:22Z","title":"AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-11T14:44:17.629567Z"},"links":{"cited_paper":"/paper/2306.07096","citing_paper":"/paper/2412.11706"},"observation_digest":"sha256:d7863caf83deef96d972addb1be5eeec9baa329f317a436e8a820e5ca3fecbe0","observation_id":"0364c821-d588-4ed4-bfad-385e2dbe1c5e","resolution":{"observed_at":"2026-08-11T14:44:17.629567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07096","last_updated":"2023-12-06T03:49:10Z","snapshot_observed_at":"2026-08-16T15:24:36.581615Z","submitted_at":"2023-06-12T13:20:29Z","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07096","snapshot_observed_at":"2026-08-11T11:37:29.562590Z","title":"Global and local semantic completion learning for vision- language pre-training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.15156","last_updated":"2024-12-19T18:32:21Z","snapshot_observed_at":"2026-08-15T14:26:44.434605Z","submitted_at":"2024-12-19T18:32:21Z","title":"Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T11:37:29.562590Z"},"links":{"cited_paper":"/paper/2306.07096","citing_paper":"/paper/2412.15156"},"observation_digest":"sha256:0f7aa94947c6061ea53191127c70907393b5d5c5371b81aab12d8bebb03f2935","observation_id":"e5693b73-85d6-4af5-a130-ac5d644d12d3","resolution":{"observed_at":"2026-08-11T11:37:29.562590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07096","last_updated":"2023-12-06T03:49:10Z","snapshot_observed_at":"2026-08-16T15:24:36.581615Z","submitted_at":"2023-06-12T13:20:29Z","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07096","snapshot_observed_at":"2026-08-07T14:14:35.316643Z","title":"Global and local semantic completion learning for vision-language pre-training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.19707","last_updated":"2025-05-26T08:56:59Z","snapshot_observed_at":"2026-08-16T04:12:17.531424Z","submitted_at":"2025-05-26T08:56:59Z","title":"MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:14:35.316643Z"},"links":{"cited_paper":"/paper/2306.07096","citing_paper":"/paper/2505.19707"},"observation_digest":"sha256:650fc18b5cc5ffcde1b1cfd650555822f43cfdb18efd574bfe15f06526581c10","observation_id":"11897d5a-7781-4dea-b17f-b8c7302fd3fe","resolution":{"observed_at":"2026-08-07T14:14:35.316643Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07096","last_updated":"2023-12-06T03:49:10Z","snapshot_observed_at":"2026-08-16T15:24:36.581615Z","submitted_at":"2023-06-12T13:20:29Z","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","version":2},"cited_work":{"arxiv_id":"2306.07096","doi":"10.48550/arxiv.2306.07096","metadata_source":"pith","pith_arxiv_id":"2306.07096","snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","venue":"cs.CV","work_id":"bb398d84-1f8e-40a4-925d-cffaa459ffc5","year":2023},"citing_paper":{"arxiv_id":"2505.19952","last_updated":"2025-05-26T13:17:50Z","snapshot_observed_at":"2026-08-16T12:05:59.799474Z","submitted_at":"2025-05-26T13:17:50Z","title":"Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:07:36.870380Z"},"links":{"cited_paper":"/paper/2306.07096","citing_paper":"/paper/2505.19952"},"observation_digest":"sha256:6ccc2ee48313057636e253f2afe62025daf4d1944462f8010654d80061132b87","observation_id":"a939717c-1883-4fa2-99d7-4d71ecaf91b4","resolution":{"observed_at":"2026-08-07T14:07:41.095133Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2306.07096/citation-record","integrity":"/paper/2306.07096/integrity","json":"/paper/2306.07096/citation-record.json","paper":"/paper/2306.07096"},"outbound":[],"paper":{"arxiv_id":"2306.07096","last_updated":"2023-12-06T03:49:10Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T15:24:36.581615Z","submitted_at":"2023-06-12T13:20:29Z","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2306.07096."}