{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZQ4STNFG5UILWO57USIVM4RWEL","short_pith_number":"pith:ZQ4STNFG","schema_version":"1.0","canonical_sha256":"cc3929b4a6ed10bb3bbfa49156723622e16b99056de83b613e234791c719badd","source":{"kind":"arxiv","id":"2607.14645","version":1},"attestation_state":"computed","paper":{"title":"Autoregressive Modeling of Film with Applications in Video Montage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Bryan Rusell, Fabian Caba Heilbron, Greg Shakhnarovich, Josef Sivic, Marcelo Sandoval-Casta\\~neda, Shiry Ginosar","submitted_at":"2026-07-16T07:13:54Z","abstract_excerpt":"This work introduces FilmGPT, an autoregressive transformer designed to address the challenge of video montage--turning a collection of raw, \"unwatchable\" footage into coherent cinematic sequences. Inspired by language learning in modern LLMs, we train a long-context autoregressive transformer on a large corpus of movies. The aim is to implicitly capture the \"grammar\" of film directly from data rather than from hand-coded rules. Unlike other generative models, FilmGPT does not generate any new video frames. Instead, at inference time, we introduce a footage-constrained decoding algorithm to se"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.14645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T07:13:54Z","cross_cats_sorted":[],"title_canon_sha256":"136e7dd6368662352e971c114934b154117ad8738aa251f5d8ac69ce96479070","abstract_canon_sha256":"8e95357fc3042344be1b4304e1fbed3d7a72b13ba78b5880c0a18be60179c21c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:22.705648Z","signature_b64":"3WP0JpKhpRgVxIJ3NmNeZxT0Xv+d6ZHAk2Z93P4A35fOLxGp0UjKGEMbWn3cJ0jQK2j6VH3XAFi8WJ5xpmm7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc3929b4a6ed10bb3bbfa49156723622e16b99056de83b613e234791c719badd","last_reissued_at":"2026-07-17T01:21:22.704755Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:22.704755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoregressive Modeling of Film with Applications in Video Montage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Bryan Rusell, Fabian Caba Heilbron, Greg Shakhnarovich, Josef Sivic, Marcelo Sandoval-Casta\\~neda, Shiry Ginosar","submitted_at":"2026-07-16T07:13:54Z","abstract_excerpt":"This work introduces FilmGPT, an autoregressive transformer designed to address the challenge of video montage--turning a collection of raw, \"unwatchable\" footage into coherent cinematic sequences. Inspired by language learning in modern LLMs, we train a long-context autoregressive transformer on a large corpus of movies. The aim is to implicitly capture the \"grammar\" of film directly from data rather than from hand-coded rules. Unlike other generative models, FilmGPT does not generate any new video frames. Instead, at inference time, we introduce a footage-constrained decoding algorithm to se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14645","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.14645/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.14645","created_at":"2026-07-17T01:21:22.705224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14645v1","created_at":"2026-07-17T01:21:22.705224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14645","created_at":"2026-07-17T01:21:22.705224+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ4STNFG5UIL","created_at":"2026-07-17T01:21:22.705224+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ4STNFG5UILWO57","created_at":"2026-07-17T01:21:22.705224+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ4STNFG","created_at":"2026-07-17T01:21:22.705224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL","json":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL.json","graph_json":"https://pith.science/api/pith-number/ZQ4STNFG5UILWO57USIVM4RWEL/graph.json","events_json":"https://pith.science/api/pith-number/ZQ4STNFG5UILWO57USIVM4RWEL/events.json","paper":"https://pith.science/paper/ZQ4STNFG"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL","download_json":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL.json","view_paper":"https://pith.science/paper/ZQ4STNFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14645&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ4STNFG5UILWO57USIVM4RWEL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ4STNFG5UILWO57USIVM4RWEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ4STNFG5UILWO57USIVM4RWEL/action/replication_record"}},"created_at":"2026-07-17T01:21:22.705224+00:00","updated_at":"2026-07-17T01:21:22.705224+00:00"}