{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VQ2JXEZBJQJFDMVNHBOZGRZNIZ","short_pith_number":"pith:VQ2JXEZB","schema_version":"1.0","canonical_sha256":"ac349b93214c1251b2ad385d93472d4651a9dec50aa906385daff17306e6b5bd","source":{"kind":"arxiv","id":"2504.15369","version":1},"attestation_state":"computed","paper":{"title":"Solving New Tasks by Adapting Internet Video Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Calvin Luo, Chen Sun, Yilun Du, Zilai Zeng","submitted_at":"2025-04-21T18:20:13Z","abstract_excerpt":"Video generative models demonstrate great promise in robotics by serving as visual planners or as policy supervisors. When pretrained on internet-scale data, such video models intimately understand alignment with natural language, and can thus facilitate generalization to novel downstream behavior through text-conditioning. However, they may not be sensitive to the specificities of the particular environment the agent inhabits. On the other hand, training video models on in-domain examples of robotic behavior naturally encodes environment-specific intricacies, but the scale of available demons"},"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":"2504.15369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-21T18:20:13Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"cb19a75a5fda5f99583fdc7e97b09b0190dcd53f5b4d6f64229c6b528f8f1bbb","abstract_canon_sha256":"07c95cb0472f45c1128fd7b6fb58e8b9133f10a2240aacef0f3b4d098c644690"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:01.643894Z","signature_b64":"RAldQHgTTu5IegoF1l+HVZIl8KZUinyAFBas+YpJ/J3QPMTzSI40VcYTosQeqQ0O5OUzqUGD2MRwnJUTxWDvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac349b93214c1251b2ad385d93472d4651a9dec50aa906385daff17306e6b5bd","last_reissued_at":"2026-07-05T10:52:01.643358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:01.643358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving New Tasks by Adapting Internet Video Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Calvin Luo, Chen Sun, Yilun Du, Zilai Zeng","submitted_at":"2025-04-21T18:20:13Z","abstract_excerpt":"Video generative models demonstrate great promise in robotics by serving as visual planners or as policy supervisors. When pretrained on internet-scale data, such video models intimately understand alignment with natural language, and can thus facilitate generalization to novel downstream behavior through text-conditioning. However, they may not be sensitive to the specificities of the particular environment the agent inhabits. On the other hand, training video models on in-domain examples of robotic behavior naturally encodes environment-specific intricacies, but the scale of available demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15369","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/2504.15369/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":"2504.15369","created_at":"2026-07-05T10:52:01.643423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15369v1","created_at":"2026-07-05T10:52:01.643423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15369","created_at":"2026-07-05T10:52:01.643423+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQ2JXEZBJQJF","created_at":"2026-07-05T10:52:01.643423+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQ2JXEZBJQJFDMVN","created_at":"2026-07-05T10:52:01.643423+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQ2JXEZB","created_at":"2026-07-05T10:52:01.643423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01955","citing_title":"WALL-WM: Carving World Action Modeling at the Event Joints","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15840","citing_title":"Large Video Planner Enables Generalizable Robot Control","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ","json":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ.json","graph_json":"https://pith.science/api/pith-number/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/graph.json","events_json":"https://pith.science/api/pith-number/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/events.json","paper":"https://pith.science/paper/VQ2JXEZB"},"agent_actions":{"view_html":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ","download_json":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ.json","view_paper":"https://pith.science/paper/VQ2JXEZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15369&json=true","fetch_graph":"https://pith.science/api/pith-number/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/action/storage_attestation","attest_author":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/action/author_attestation","sign_citation":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/action/citation_signature","submit_replication":"https://pith.science/pith/VQ2JXEZBJQJFDMVNHBOZGRZNIZ/action/replication_record"}},"created_at":"2026-07-05T10:52:01.643423+00:00","updated_at":"2026-07-05T10:52:01.643423+00:00"}