{"as_of":"2026-08-06T16:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5357c096d8af337463e0d2eead5f9570432d178c8af5d8152662ecf0c1fa9a2a","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-25T21:23:44.253416Z","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":"2026-07-04T19:20:07.153269Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.20014","last_updated":"2024-12-28T04:23:47Z","snapshot_observed_at":"2026-07-06T20:13:58.813488Z","submitted_at":"2024-12-28T04:23:47Z","title":"ProtCLIP: Function-Informed Protein Multi-Modal Learning","version":1},"cited_work":{"arxiv_id":"2412.20014","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.20014","snapshot_observed_at":"2026-07-04T19:20:07.153269Z","title":"Bring my cup! personalizing vision-language-action models with visual attentive prompting,","venue":null,"work_id":"4a81014f-f6ed-48fa-ad6c-23303b466099","year":2024},"citing_paper":{"arxiv_id":"2606.25360","last_updated":"2026-06-24T03:45:06Z","snapshot_observed_at":"2026-08-05T09:22:56.337937Z","submitted_at":"2026-06-24T03:45:06Z","title":"Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-25T21:23:44.253416Z"},"links":{"cited_paper":"/paper/2412.20014","citing_paper":"/paper/2606.25360"},"observation_digest":"sha256:0a5359befea5af6a20e8d843b889680c46c5f27437631543110f72a5047556ce","observation_id":"596185ce-c585-4a7d-952d-58411ee7f0e5","resolution":{"observed_at":"2026-07-04T19:20:07.154799Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.20014/citation-record","integrity":"/paper/2412.20014/integrity","json":"/paper/2412.20014/citation-record.json","paper":"/paper/2412.20014"},"outbound":[],"paper":{"arxiv_id":"2412.20014","last_updated":"2024-12-28T04:23:47Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T20:13:58.813488Z","submitted_at":"2024-12-28T04:23:47Z","title":"ProtCLIP: Function-Informed Protein Multi-Modal 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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2412.20014."}