{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WESESZC76S2IZRCQOCTFLFKWSQ","short_pith_number":"pith:WESESZC7","schema_version":"1.0","canonical_sha256":"b12449645ff4b48cc45070a65595569429ecdd104e6a61100e3deadf960e4d7c","source":{"kind":"arxiv","id":"2401.00025","version":3},"attestation_state":"computed","paper":{"title":"Any-point Trajectory Modeling for Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Pre-training a model to predict future trajectories of arbitrary points in videos supplies control guidance that lets robots learn policies from minimal action-labeled data.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chuan Wen, John So, Kai Chen, Pieter Abbeel, Qi Dou, Xingyu Lin, Yang Gao","submitted_at":"2023-12-28T23:34:43Z","abstract_excerpt":"Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning. However, the high cost of collecting demonstration data is a significant bottleneck. Videos, as a rich data source, contain knowledge of behaviors, physics, and semantics, but extracting control-specific information from them is challenging due to the lack of action labels. In this work, we introduce a novel framework, Any-point Trajectory Modeling (ATM), that utilizes video demonstrations by pre-training a trajectory model to predict future trajec"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2401.00025","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-28T23:34:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f0e6f867bde371defd2e2692b35013ad6027c83dc67b96b6714e4c89521c4b2d","abstract_canon_sha256":"207d057b618a3ca7c114531026d9aaa973945c29387380ab0067e268a7bfe3da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.232174Z","signature_b64":"KneziBtHvE7zdnN3LfdifO+5wPpUDzrbS9UKCGj5sxsG01gu+1vOMJ8HGmh5G4hpP23eaic0ba8mROWE6k35Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b12449645ff4b48cc45070a65595569429ecdd104e6a61100e3deadf960e4d7c","last_reissued_at":"2026-05-17T23:38:46.231720Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.231720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Any-point Trajectory Modeling for Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Pre-training a model to predict future trajectories of arbitrary points in videos supplies control guidance that lets robots learn policies from minimal action-labeled data.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chuan Wen, John So, Kai Chen, Pieter Abbeel, Qi Dou, Xingyu Lin, Yang Gao","submitted_at":"2023-12-28T23:34:43Z","abstract_excerpt":"Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning. However, the high cost of collecting demonstration data is a significant bottleneck. Videos, as a rich data source, contain knowledge of behaviors, physics, and semantics, but extracting control-specific information from them is challenging due to the lack of action labels. In this work, we introduce a novel framework, Any-point Trajectory Modeling (ATM), that utilizes video demonstrations by pre-training a trajectory model to predict future trajec"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across over 130 language-conditioned tasks we evaluated in both simulation and the real world, ATM outperforms strong video pre-training baselines by 80% on average.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That predicted trajectories of arbitrary points supply sufficiently accurate and transferable control guidance to enable robust policy learning from only minimal action-labeled data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ATM pre-trains models to predict trajectories of any points in videos, then uses those predictions to learn strong visuomotor policies from minimal action labels, beating baselines by 80% on 130+ tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Pre-training a model to predict future trajectories of arbitrary points in videos supplies control guidance that lets robots learn policies from minimal action-labeled data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2a7cb39692e3d4d76f56771bb608dfd2dbe79a6af1017b9004ea210571b0f3c2"},"source":{"id":"2401.00025","kind":"arxiv","version":3},"verdict":{"id":"60a17f23-8822-4180-82cb-177037712d97","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T23:27:58.879801Z","strongest_claim":"Across over 130 language-conditioned tasks we evaluated in both simulation and the real world, ATM outperforms strong video pre-training baselines by 80% on average.","one_line_summary":"ATM pre-trains models to predict trajectories of any points in videos, then uses those predictions to learn strong visuomotor policies from minimal action labels, beating baselines by 80% on 130+ tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That predicted trajectories of arbitrary points supply sufficiently accurate and transferable control guidance to enable robust policy learning from only minimal action-labeled data.","pith_extraction_headline":"Pre-training a model to predict future trajectories of arbitrary points in videos supplies control guidance that lets robots learn policies from minimal action-labeled data."},"references":{"count":56,"sample":[{"doi":"","year":2007,"title":"Trajectory- tracking and path-following of underactuated au- tonomous vehicles with parametric modeling uncertainty","work_id":"5d129caa-4470-446b-846b-2f93e56fa144","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Affordances from human videos 417 as a versatile rep- resentation for robotics","work_id":"bb92ac12-300b-4596-b676-cdc3976e29c1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Video pretraining (vpt): Learning to act by watching unlabeled online videos","work_id":"008a87ff-6368-4639-b2a4-91059d0f90e5","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Zero-shot robot manipu- lation from passive human videos","work_id":"69f1ea0a-5458-4344-9835-4e29765c78e1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","work_id":"954b4359-f4ed-4c73-ae5b-f75d486b6fc8","ref_index":5,"cited_arxiv_id":"2310.10639","is_internal_anchor":true}],"resolved_work":56,"snapshot_sha256":"938093790cb94781782dbeabc28d34840063a6deb7c9842712caca02fd0269be","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9187ea1df91f2e5a6bf976650ba3caeb7965e49d028fa35436ffdce100d4291b"},"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":"2401.00025","created_at":"2026-05-17T23:38:46.231802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00025v3","created_at":"2026-05-17T23:38:46.231802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00025","created_at":"2026-05-17T23:38:46.231802+00:00"},{"alias_kind":"pith_short_12","alias_value":"WESESZC76S2I","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"WESESZC76S2IZRCQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"WESESZC7","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":32,"sample":[{"citing_arxiv_id":"2605.23856","citing_title":"Point Tracking Improves World Action Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2412.12870","citing_title":"Physically Interpretable World Models via Weakly Supervised Representation Learning","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21862","citing_title":"EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22123","citing_title":"Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22816","citing_title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15944","citing_title":"FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15944","citing_title":"FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17522","citing_title":"RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19580","citing_title":"PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16743","citing_title":"LACE: Latent Visual Representation for Cross-Embodiment Learning","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2510.01433","citing_title":"AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2511.12878","citing_title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2505.15659","citing_title":"FLARE: Robot Learning with Implicit World Modeling","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2507.15493","citing_title":"GR-3 Technical Report","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":117,"is_internal_anchor":true},{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2503.22020","citing_title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2412.10345","citing_title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","ref_index":98,"is_internal_anchor":true},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2504.02792","citing_title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10307","citing_title":"PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ","json":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ.json","graph_json":"https://pith.science/api/pith-number/WESESZC76S2IZRCQOCTFLFKWSQ/graph.json","events_json":"https://pith.science/api/pith-number/WESESZC76S2IZRCQOCTFLFKWSQ/events.json","paper":"https://pith.science/paper/WESESZC7"},"agent_actions":{"view_html":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ","download_json":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ.json","view_paper":"https://pith.science/paper/WESESZC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00025&json=true","fetch_graph":"https://pith.science/api/pith-number/WESESZC76S2IZRCQOCTFLFKWSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WESESZC76S2IZRCQOCTFLFKWSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/action/storage_attestation","attest_author":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/action/author_attestation","sign_citation":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/action/citation_signature","submit_replication":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/action/replication_record"}},"created_at":"2026-05-17T23:38:46.231802+00:00","updated_at":"2026-05-17T23:38:46.231802+00:00"}