{"as_of":"2026-08-24T04:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ef1fecc3a1e2e28346c82cbf23d8b2de82b668250c74050e3eeccbdefb82401c","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":"2026-08-23T06:30:58.430688+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":"2026-08-07T14:01:41.449159Z","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":"2026-08-06T21:41:58.173949Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.01293","last_updated":"2024-07-20T07:52:29Z","snapshot_observed_at":"2026-08-17T06:37:04.747347Z","submitted_at":"2024-02-02T10:30:05Z","title":"Can MLLMs Perform Text-to-Image In-Context Learning?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01293","snapshot_observed_at":"2026-08-07T14:01:41.449159Z","title":"Can mllms perform text-to-image in- context learning? arXiv preprint arXiv:2402.01293, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20271","last_updated":"2025-05-26T17:49:10Z","snapshot_observed_at":"2026-08-18T10:40:21.454421Z","submitted_at":"2025-05-26T17:49:10Z","title":"In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T14:01:41.449159Z"},"links":{"cited_paper":"/paper/2402.01293","citing_paper":"/paper/2505.20271"},"observation_digest":"sha256:5f05701284d0c8f2c54712c23796296b2e165aa2889b39f72c0fc840992eb066","observation_id":"5f40f0b7-071c-43c1-bd3d-66f8be7ad9ab","resolution":{"observed_at":"2026-08-07T14:01:41.449159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01293","last_updated":"2024-07-20T07:52:29Z","snapshot_observed_at":"2026-08-17T06:37:04.747347Z","submitted_at":"2024-02-02T10:30:05Z","title":"Can MLLMs Perform Text-to-Image In-Context Learning?","version":3},"cited_work":{"arxiv_id":"2402.01293","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.01293","snapshot_observed_at":"2026-08-06T21:41:58.173949Z","title":"Can MLLMs Perform Text-to-Image In-Context Learning?","venue":"cs.LG","work_id":"06664973-3e68-428d-b679-be70add2f679","year":2024},"citing_paper":{"arxiv_id":"2506.23639","last_updated":"2025-06-30T09:08:08Z","snapshot_observed_at":"2026-08-16T20:36:56.520212Z","submitted_at":"2025-06-30T09:08:08Z","title":"Unified Multimodal Understanding via Byte-Pair Visual Encoding","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:41:50.990343Z"},"links":{"cited_paper":"/paper/2402.01293","citing_paper":"/paper/2506.23639"},"observation_digest":"sha256:2c0e087f1c36e62e8ed3b4f3c4b564200b5656ac830c5a10daedefe3fcdea89c","observation_id":"62a8891b-c809-48cf-b8fa-8d0059b3e8d1","resolution":{"observed_at":"2026-08-06T21:41:58.277662Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.01293/citation-record","integrity":"/paper/2402.01293/integrity","json":"/paper/2402.01293/citation-record.json","paper":"/paper/2402.01293"},"outbound":[],"paper":{"arxiv_id":"2402.01293","last_updated":"2024-07-20T07:52:29Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T06:37:04.747347Z","submitted_at":"2024-02-02T10:30:05Z","title":"Can MLLMs Perform Text-to-Image In-Context Learning?"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.01293."}