{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6WK6XSZHMDUFTICIXAXIFPF7GP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"582e82e0aef1be94e2eec498b17f627ee39f1fa98a428168c7aa19e3712b7056","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T21:24:41Z","title_canon_sha256":"d65006fe45fba9acb5bb09475ba7f7f041d3ae5e202bbee1c89ba979a397c312"},"schema_version":"1.0","source":{"id":"2412.18688","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18688","created_at":"2026-07-05T11:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18688v2","created_at":"2026-07-05T11:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18688","created_at":"2026-07-05T11:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"6WK6XSZHMDUF","created_at":"2026-07-05T11:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"6WK6XSZHMDUFTICI","created_at":"2026-07-05T11:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"6WK6XSZH","created_at":"2026-07-05T11:48:22Z"}],"graph_snapshots":[{"event_id":"sha256:acceeb05c2060161128d72a226c02b82475cdd66d178a02bc836ca20d37f710a","target":"graph","created_at":"2026-07-05T11:48:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.18688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An image may convey a thousand words, but a video composed of hundreds or thousands of image frames tells a more intricate story. Despite significant progress in multimodal large language models (MLLMs), generating extended videos remains a formidable challenge. As of this writing, OpenAI's Sora, the current state-of-the-art system, is still limited to producing videos that are up to one minute in length. This limitation stems from the complexity of long video generation, which requires more than generative AI techniques for approximating density functions essential aspects such as planning, s","authors_text":"Faraz Waseem, Muhammad Shahzad","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T21:24:41Z","title":"Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18688","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8636e81961a52dd269a76aea4eaf91a098ec95521ec58dc842d3b6c5eb8ec03b","target":"record","created_at":"2026-07-05T11:48:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"582e82e0aef1be94e2eec498b17f627ee39f1fa98a428168c7aa19e3712b7056","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T21:24:41Z","title_canon_sha256":"d65006fe45fba9acb5bb09475ba7f7f041d3ae5e202bbee1c89ba979a397c312"},"schema_version":"1.0","source":{"id":"2412.18688","kind":"arxiv","version":2}},"canonical_sha256":"f595ebcb2760e859a048b82e82bcbf33f0363bd1c0cc5d3c740d1be8c91ee7a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f595ebcb2760e859a048b82e82bcbf33f0363bd1c0cc5d3c740d1be8c91ee7a8","first_computed_at":"2026-07-05T11:48:22.153238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:22.153238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MO589EOj5HbyA9JB7kLWloxBeuMoeP0JSVm14vM6BAqOln/FK9JHpS5xh883O4DbGLEVJz8Oirl8jxtd+jc2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:22.153739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18688","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8636e81961a52dd269a76aea4eaf91a098ec95521ec58dc842d3b6c5eb8ec03b","sha256:acceeb05c2060161128d72a226c02b82475cdd66d178a02bc836ca20d37f710a"],"state_sha256":"c041ce4fcce555e572eea535aa44ddb38466cfbf84cca11bcd59eca7705ff690"}