{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H4WCIS6EHMDN47EQGT4CPSWM76","short_pith_number":"pith:H4WCIS6E","schema_version":"1.0","canonical_sha256":"3f2c244bc43b06de7c9034f827caccff95032c6f62d7a40617ed17fb5377d9cc","source":{"kind":"arxiv","id":"2310.08576","version":1},"attestation_state":"computed","paper":{"title":"Learning to Act from Actionless Videos through Dense Correspondences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Jiayuan Mao, Joshua B. Tenenbaum, Po-Chen Ko, Shao-Hua Sun, Yilun Du","submitted_at":"2023-10-12T17:59:23Z","abstract_excerpt":"In this work, we present an approach to construct a video-based robot policy capable of reliably executing diverse tasks across different robots and environments from few video demonstrations without using any action annotations. Our method leverages images as a task-agnostic representation, encoding both the state and action information, and text as a general representation for specifying robot goals. By synthesizing videos that ``hallucinate'' robot executing actions and in combination with dense correspondences between frames, our approach can infer the closed-formed action to execute to an"},"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":"2310.08576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-12T17:59:23Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"a49023c6523cb3e1ea57776117dc0a23f8e59316ac9ab7aeddaa95b99b3d3641","abstract_canon_sha256":"d9f1439118584c13f7028b394ca0eeee96da5979a3d7a2c2bb411a5b66c9e6a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:17.293489Z","signature_b64":"w+UU2KEi1oe96oPZ43CCfu12m7rR3xggBwscM6qOho+ujc0IrRNrX3TyEMEgrK09sRBXj6WPouuIUaONaVzHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f2c244bc43b06de7c9034f827caccff95032c6f62d7a40617ed17fb5377d9cc","last_reissued_at":"2026-07-05T07:00:17.293015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:17.293015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Act from Actionless Videos through Dense Correspondences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Jiayuan Mao, Joshua B. Tenenbaum, Po-Chen Ko, Shao-Hua Sun, Yilun Du","submitted_at":"2023-10-12T17:59:23Z","abstract_excerpt":"In this work, we present an approach to construct a video-based robot policy capable of reliably executing diverse tasks across different robots and environments from few video demonstrations without using any action annotations. Our method leverages images as a task-agnostic representation, encoding both the state and action information, and text as a general representation for specifying robot goals. By synthesizing videos that ``hallucinate'' robot executing actions and in combination with dense correspondences between frames, our approach can infer the closed-formed action to execute to an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08576","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/2310.08576/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":"2310.08576","created_at":"2026-07-05T07:00:17.293072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08576v1","created_at":"2026-07-05T07:00:17.293072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08576","created_at":"2026-07-05T07:00:17.293072+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4WCIS6EHMDN","created_at":"2026-07-05T07:00:17.293072+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4WCIS6EHMDN47EQ","created_at":"2026-07-05T07:00:17.293072+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4WCIS6E","created_at":"2026-07-05T07:00:17.293072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01166","citing_title":"Structured 4D Latent Predictive Model for Robot Planning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01773","citing_title":"IGen: Scalable Data Generation for Robot Learning from Open-World Images","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2401.00025","citing_title":"Any-point Trajectory Modeling for Policy Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15840","citing_title":"Large Video Planner Enables Generalizable Robot Control","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12587","citing_title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03181","citing_title":"Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2503.00200","citing_title":"Unified Video Action Model","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03637","citing_title":"Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11386","citing_title":"ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07474","citing_title":"ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06168","citing_title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15938","citing_title":"VADF: Vision-Adaptive Diffusion Policy Framework for Efficient Robotic Manipulation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76","json":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76.json","graph_json":"https://pith.science/api/pith-number/H4WCIS6EHMDN47EQGT4CPSWM76/graph.json","events_json":"https://pith.science/api/pith-number/H4WCIS6EHMDN47EQGT4CPSWM76/events.json","paper":"https://pith.science/paper/H4WCIS6E"},"agent_actions":{"view_html":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76","download_json":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76.json","view_paper":"https://pith.science/paper/H4WCIS6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08576&json=true","fetch_graph":"https://pith.science/api/pith-number/H4WCIS6EHMDN47EQGT4CPSWM76/graph.json","fetch_events":"https://pith.science/api/pith-number/H4WCIS6EHMDN47EQGT4CPSWM76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76/action/storage_attestation","attest_author":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76/action/author_attestation","sign_citation":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76/action/citation_signature","submit_replication":"https://pith.science/pith/H4WCIS6EHMDN47EQGT4CPSWM76/action/replication_record"}},"created_at":"2026-07-05T07:00:17.293072+00:00","updated_at":"2026-07-05T07:00:17.293072+00:00"}