{"as_of":"2026-08-08T19:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b67779c2889aed413cf90cc81cede6a5a73ebd5e09a0c16913d644507b72348d","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T11:54:18.192758Z","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":"2026-05-11T07:56:00.385518Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.08641","last_updated":"2025-04-11T15:41:43Z","snapshot_observed_at":"2026-08-07T16:06:29.686223Z","submitted_at":"2025-04-11T15:41:43Z","title":"Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.08641","snapshot_observed_at":"2026-08-07T11:54:18.192758Z","title":"Training-free guidance in text-to-video generation via multimodal planning and structured noise initialization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.01144","last_updated":"2025-06-04T07:45:25Z","snapshot_observed_at":"2026-08-07T11:48:12.548017Z","submitted_at":"2025-06-01T19:55:33Z","title":"FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T11:54:18.192758Z"},"links":{"cited_paper":"/paper/2504.08641","citing_paper":"/paper/2506.01144"},"observation_digest":"sha256:4b41d7e06a9825d39930f7997615404f7526aab2e53dc44006752ad0b8629e17","observation_id":"6720005f-9818-41c1-a6a0-76b3308019ba","resolution":{"observed_at":"2026-08-07T11:54:18.192758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.08641","last_updated":"2025-04-11T15:41:43Z","snapshot_observed_at":"2026-08-07T16:06:29.686223Z","submitted_at":"2025-04-11T15:41:43Z","title":"Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.08641","snapshot_observed_at":"2026-08-06T23:49:54.533224Z","title":"Training-free guidance in text-to-video generation via multimodal planning and structured noise initialization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16119","last_updated":"2025-06-19T08:11:45Z","snapshot_observed_at":"2026-08-06T23:42:09.423923Z","submitted_at":"2025-06-19T08:11:45Z","title":"FastInit: Fast Noise Initialization for Temporally Consistent Video Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:49:54.533224Z"},"links":{"cited_paper":"/paper/2504.08641","citing_paper":"/paper/2506.16119"},"observation_digest":"sha256:d7f6bed730a119f271f76b94f80565390f94e14ba5dffecae9da15037c456a9c","observation_id":"83fb48dd-eb6e-4b34-870c-797d5b720a6e","resolution":{"observed_at":"2026-08-06T23:49:54.533224Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.08641","last_updated":"2025-04-11T15:41:43Z","snapshot_observed_at":"2026-08-07T16:06:29.686223Z","submitted_at":"2025-04-11T15:41:43Z","title":"Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization","version":1},"cited_work":{"arxiv_id":"2504.08641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.08641","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Training-free guidance in text-to-video generation via multimodal planning and structured noise initialization.arXivpreprint","venue":null,"work_id":"aca9dcae-a381-4445-a38c-e062236a2aaf","year":2025},"citing_paper":{"arxiv_id":"2604.09201","last_updated":"2026-04-10T10:43:18Z","snapshot_observed_at":"2026-07-06T22:58:08.579543Z","submitted_at":"2026-04-10T10:43:18Z","title":"CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T16:53:54.166457Z"},"links":{"cited_paper":"/paper/2504.08641","citing_paper":"/paper/2604.09201"},"observation_digest":"sha256:356217d5edd833b63d76f27f7d3b5a14d275c809402bfeae2fefded00de4dc72","observation_id":"31d8ca06-de0d-42f6-81b9-73f530125032","resolution":{"observed_at":"2026-05-11T07:56:00.391214Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2504.08641/citation-record","integrity":"/paper/2504.08641/integrity","json":"/paper/2504.08641/citation-record.json","paper":"/paper/2504.08641"},"outbound":[],"paper":{"arxiv_id":"2504.08641","last_updated":"2025-04-11T15:41:43Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:06:29.686223Z","submitted_at":"2025-04-11T15:41:43Z","title":"Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2504.08641."}