{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EYENGJZ5TOPGZAE63UVPGSQ32E","short_pith_number":"pith:EYENGJZ5","schema_version":"1.0","canonical_sha256":"2608d3273d9b9e6c809edd2af34a1bd11ba8b157333adae209415b6ac7dd18b7","source":{"kind":"arxiv","id":"2405.01527","version":2},"attestation_state":"computed","paper":{"title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Abhinav Gupta, Homanga Bharadhwaj, Roozbeh Mottaghi, Shubham Tulsiani","submitted_at":"2024-05-02T17:56:55Z","abstract_excerpt":"We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation: interacting with unseen objects in novel scenes without test-time adaptation. While typical approaches rely on a large amount of demonstration data for such generalization, we propose an approach that leverages web videos to predict plausible interaction plans and learns a task-agnostic transformation to obtain robot actions in the real world. Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal, and can be trained with diverse videos"},"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":"2405.01527","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-02T17:56:55Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1cfa8ee5a9eb53956feb7beb397e48ea97841fc1e58895d624a9b5535b9f3523","abstract_canon_sha256":"a5ce9be924eabe9146cb371e3d3f814bb5c140613cf70ceb4bed4a2c3568011d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:40.169960Z","signature_b64":"IfTGLPk9tml2NBTV8QM8auQX0EmTcWZh5joLZsOI0tEihZYZ/JrQTDIf4kF7CRAUszDPnnVdC4RdqWaSoOmTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2608d3273d9b9e6c809edd2af34a1bd11ba8b157333adae209415b6ac7dd18b7","last_reissued_at":"2026-07-05T08:53:40.169534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:40.169534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Abhinav Gupta, Homanga Bharadhwaj, Roozbeh Mottaghi, Shubham Tulsiani","submitted_at":"2024-05-02T17:56:55Z","abstract_excerpt":"We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation: interacting with unseen objects in novel scenes without test-time adaptation. While typical approaches rely on a large amount of demonstration data for such generalization, we propose an approach that leverages web videos to predict plausible interaction plans and learns a task-agnostic transformation to obtain robot actions in the real world. Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal, and can be trained with diverse videos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01527","kind":"arxiv","version":2},"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/2405.01527/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":"2405.01527","created_at":"2026-07-05T08:53:40.169591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.01527v2","created_at":"2026-07-05T08:53:40.169591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01527","created_at":"2026-07-05T08:53:40.169591+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYENGJZ5TOPG","created_at":"2026-07-05T08:53:40.169591+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYENGJZ5TOPGZAE6","created_at":"2026-07-05T08:53:40.169591+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYENGJZ5","created_at":"2026-07-05T08:53:40.169591+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19333","citing_title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10614","citing_title":"Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01433","citing_title":"AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04671","citing_title":"X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15493","citing_title":"GR-3 Technical Report","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":17,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02792","citing_title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E","json":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E.json","graph_json":"https://pith.science/api/pith-number/EYENGJZ5TOPGZAE63UVPGSQ32E/graph.json","events_json":"https://pith.science/api/pith-number/EYENGJZ5TOPGZAE63UVPGSQ32E/events.json","paper":"https://pith.science/paper/EYENGJZ5"},"agent_actions":{"view_html":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E","download_json":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E.json","view_paper":"https://pith.science/paper/EYENGJZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.01527&json=true","fetch_graph":"https://pith.science/api/pith-number/EYENGJZ5TOPGZAE63UVPGSQ32E/graph.json","fetch_events":"https://pith.science/api/pith-number/EYENGJZ5TOPGZAE63UVPGSQ32E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E/action/storage_attestation","attest_author":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E/action/author_attestation","sign_citation":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E/action/citation_signature","submit_replication":"https://pith.science/pith/EYENGJZ5TOPGZAE63UVPGSQ32E/action/replication_record"}},"created_at":"2026-07-05T08:53:40.169591+00:00","updated_at":"2026-07-05T08:53:40.169591+00:00"}