{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WESESZC76S2IZRCQOCTFLFKWSQ","short_pith_number":"pith:WESESZC7","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"},"canonical_sha256":"b12449645ff4b48cc45070a65595569429ecdd104e6a61100e3deadf960e4d7c","source":{"kind":"arxiv","id":"2401.00025","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00025","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00025v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00025","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"WESESZC76S2I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WESESZC76S2IZRCQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WESESZC7","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WESESZC76S2IZRCQOCTFLFKWSQ","target":"record","payload":{"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"},"canonical_sha256":"b12449645ff4b48cc45070a65595569429ecdd104e6a61100e3deadf960e4d7c","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"},"source_kind":"arxiv","source_id":"2401.00025","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"24lDxrih/tVMbHz1QfUdJ1TpLqCwtzargVoe8oxVr+gL0g9tvnHfD5cWX/cat5IYRj9jMLyOkAhhExpyNVXlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:26:26.987975Z"},"content_sha256":"d980f6beed402a3af3f447dcb8a964df0da526822e0c973e37985a0566b40da5","schema_version":"1.0","event_id":"sha256:d980f6beed402a3af3f447dcb8a964df0da526822e0c973e37985a0566b40da5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WESESZC76S2IZRCQOCTFLFKWSQ","target":"graph","payload":{"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"},"verdict_id":"60a17f23-8822-4180-82cb-177037712d97"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zk4xSrJXcln0xqL6qq6UffBgq56AiOr+O3ksBAxdXZa1w4VICFcH9wCN1GrrS09dql+96RvT2NxAdwfGzfbtBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:26:26.988962Z"},"content_sha256":"5b40650c76821973b2cb68cc64579b36c042530406bec4deca3b8cd3fd368bf6","schema_version":"1.0","event_id":"sha256:5b40650c76821973b2cb68cc64579b36c042530406bec4deca3b8cd3fd368bf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/bundle.json","state_url":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WESESZC76S2IZRCQOCTFLFKWSQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T16:26:26Z","links":{"resolver":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ","bundle":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/bundle.json","state":"https://pith.science/pith/WESESZC76S2IZRCQOCTFLFKWSQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WESESZC76S2IZRCQOCTFLFKWSQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WESESZC76S2IZRCQOCTFLFKWSQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"207d057b618a3ca7c114531026d9aaa973945c29387380ab0067e268a7bfe3da","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-28T23:34:43Z","title_canon_sha256":"f0e6f867bde371defd2e2692b35013ad6027c83dc67b96b6714e4c89521c4b2d"},"schema_version":"1.0","source":{"id":"2401.00025","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00025","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00025v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00025","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"WESESZC76S2I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WESESZC76S2IZRCQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WESESZC7","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5b40650c76821973b2cb68cc64579b36c042530406bec4deca3b8cd3fd368bf6","target":"graph","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"2a7cb39692e3d4d76f56771bb608dfd2dbe79a6af1017b9004ea210571b0f3c2"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9187ea1df91f2e5a6bf976650ba3caeb7965e49d028fa35436ffdce100d4291b"},"paper":{"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","authors_text":"Chuan Wen, John So, Kai Chen, Pieter Abbeel, Qi Dou, Xingyu Lin, Yang Gao","cross_cats":["cs.CV"],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-28T23:34:43Z","title":"Any-point Trajectory Modeling for Policy Learning"},"references":{"count":56,"internal_anchors":6,"resolved_work":56,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Trajectory- tracking and path-following of underactuated au- tonomous vehicles with parametric modeling uncertainty","work_id":"5d129caa-4470-446b-846b-2f93e56fa144","year":2007},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Affordances from human videos 417 as a versatile rep- resentation for robotics","work_id":"bb92ac12-300b-4596-b676-cdc3976e29c1","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Video pretraining (vpt): Learning to act by watching unlabeled online videos","work_id":"008a87ff-6368-4639-b2a4-91059d0f90e5","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Zero-shot robot manipu- lation from passive human videos","work_id":"69f1ea0a-5458-4344-9835-4e29765c78e1","year":2023},{"cited_arxiv_id":"2310.10639","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","work_id":"954b4359-f4ed-4c73-ae5b-f75d486b6fc8","year":2023}],"snapshot_sha256":"938093790cb94781782dbeabc28d34840063a6deb7c9842712caca02fd0269be"},"source":{"id":"2401.00025","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T23:27:58.879801Z","id":"60a17f23-8822-4180-82cb-177037712d97","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"60a17f23-8822-4180-82cb-177037712d97"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d980f6beed402a3af3f447dcb8a964df0da526822e0c973e37985a0566b40da5","target":"record","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"207d057b618a3ca7c114531026d9aaa973945c29387380ab0067e268a7bfe3da","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-28T23:34:43Z","title_canon_sha256":"f0e6f867bde371defd2e2692b35013ad6027c83dc67b96b6714e4c89521c4b2d"},"schema_version":"1.0","source":{"id":"2401.00025","kind":"arxiv","version":3}},"canonical_sha256":"b12449645ff4b48cc45070a65595569429ecdd104e6a61100e3deadf960e4d7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b12449645ff4b48cc45070a65595569429ecdd104e6a61100e3deadf960e4d7c","first_computed_at":"2026-05-17T23:38:46.231720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.231720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KneziBtHvE7zdnN3LfdifO+5wPpUDzrbS9UKCGj5sxsG01gu+1vOMJ8HGmh5G4hpP23eaic0ba8mROWE6k35Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.232174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00025","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d980f6beed402a3af3f447dcb8a964df0da526822e0c973e37985a0566b40da5","sha256:5b40650c76821973b2cb68cc64579b36c042530406bec4deca3b8cd3fd368bf6"],"state_sha256":"b9d98ac325052285bd9a6e230cbfbf5a06972f5f01c687bf9769fde67532a065"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRk1saBq+AC3BIlsrwurxCAH5+VcdYKwcGM42x6kXyuz62X+6S02vtXfCbgn97z96+rL1DaXxZYhFZWLGiozBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:26:26.993512Z","bundle_sha256":"47c50e686fab47f7e940d16ec6c0c68043a9d6bb045fd4e7709749e8aa56f7d4"}}