{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RTY7D7BCHRCDLLXF7P4SSAW53B","short_pith_number":"pith:RTY7D7BC","schema_version":"1.0","canonical_sha256":"8cf1f1fc223c4435aee5fbf92902ddd856b1ceb938500283794a1a8850c6f45c","source":{"kind":"arxiv","id":"2410.10076","version":3},"attestation_state":"computed","paper":{"title":"VideoAgent: Self-Improving Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Abhranil Chandra, Achint Soni, Bo Dai, Percy Liang, Sebastian Fischmeister, Sherry Yang, Sreyas Venkataraman","submitted_at":"2024-10-14T01:39:56Z","abstract_excerpt":"Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot controls to be executed. However, a major bottleneck in leveraging video generation for control lies in the quality of the generated videos, which often suffer from hallucinatory content and unrealistic physics, resulting in low task success when control actions are extracted from the generated videos. While scaling up dataset and model size provides a partial solution, integrati"},"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":"2410.10076","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-14T01:39:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dbef9259952af80528c912e5a167abb9bddacd5ae5f3d46c3f15ab06b485f31d","abstract_canon_sha256":"6cceddc16e22ac23fc2aefa3654a678b8f226d890370a459e2a7f15d28e67a60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:25.761951Z","signature_b64":"S+bUuCo/6hMV00GGnRIkQyfOVWqBEYXGtmbNyrA7DAhIzNXnGgjKlGWKHoLknRisp5XiGYrZYTfP+o8qEQmeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cf1f1fc223c4435aee5fbf92902ddd856b1ceb938500283794a1a8850c6f45c","last_reissued_at":"2026-07-05T10:11:25.761434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:25.761434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoAgent: Self-Improving Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Abhranil Chandra, Achint Soni, Bo Dai, Percy Liang, Sebastian Fischmeister, Sherry Yang, Sreyas Venkataraman","submitted_at":"2024-10-14T01:39:56Z","abstract_excerpt":"Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot controls to be executed. However, a major bottleneck in leveraging video generation for control lies in the quality of the generated videos, which often suffer from hallucinatory content and unrealistic physics, resulting in low task success when control actions are extracted from the generated videos. While scaling up dataset and model size provides a partial solution, integrati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10076","kind":"arxiv","version":3},"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/2410.10076/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":"2410.10076","created_at":"2026-07-05T10:11:25.761500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10076v3","created_at":"2026-07-05T10:11:25.761500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10076","created_at":"2026-07-05T10:11:25.761500+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTY7D7BCHRCD","created_at":"2026-07-05T10:11:25.761500+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTY7D7BCHRCDLLXF","created_at":"2026-07-05T10:11:25.761500+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTY7D7BC","created_at":"2026-07-05T10:11:25.761500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22818","citing_title":"MotiMotion: Motion-Controlled Video Generation with Visual Reasoning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":209,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B","json":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B.json","graph_json":"https://pith.science/api/pith-number/RTY7D7BCHRCDLLXF7P4SSAW53B/graph.json","events_json":"https://pith.science/api/pith-number/RTY7D7BCHRCDLLXF7P4SSAW53B/events.json","paper":"https://pith.science/paper/RTY7D7BC"},"agent_actions":{"view_html":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B","download_json":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B.json","view_paper":"https://pith.science/paper/RTY7D7BC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10076&json=true","fetch_graph":"https://pith.science/api/pith-number/RTY7D7BCHRCDLLXF7P4SSAW53B/graph.json","fetch_events":"https://pith.science/api/pith-number/RTY7D7BCHRCDLLXF7P4SSAW53B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B/action/storage_attestation","attest_author":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B/action/author_attestation","sign_citation":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B/action/citation_signature","submit_replication":"https://pith.science/pith/RTY7D7BCHRCDLLXF7P4SSAW53B/action/replication_record"}},"created_at":"2026-07-05T10:11:25.761500+00:00","updated_at":"2026-07-05T10:11:25.761500+00:00"}