{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HDXTXHQTTL7TJRCDTY7K36UCUG","short_pith_number":"pith:HDXTXHQT","schema_version":"1.0","canonical_sha256":"38ef3b9e139aff34c4439e3eadfa82a1b6f6b1b3f0e39551091c225c0995ee66","source":{"kind":"arxiv","id":"2503.23877","version":1},"attestation_state":"computed","paper":{"title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Amy Luo, Dinesh Jayaraman, Ian Pedroza, Jason Ma, Jie Wang, Junyao Shi, Tianyou Wang, Zhuolun Zhao","submitted_at":"2025-03-31T09:27:00Z","abstract_excerpt":"Many recent advances in robotic manipulation have come through imitation learning, yet these rely largely on mimicking a particularly hard-to-acquire form of demonstrations: those collected on the same robot in the same room with the same objects as the trained policy must handle at test time. In contrast, large pre-recorded human video datasets demonstrating manipulation skills in-the-wild already exist, which contain valuable information for robots. Is it possible to distill a repository of useful robotic skill policies out of such data without any additional requirements on robot-specific d"},"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":"2503.23877","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-31T09:27:00Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"5d18ddb588b463bbe45008f759d786a4e01b2c2dca47df8dd2dcf31f3d519a9a","abstract_canon_sha256":"346cc49f7930349c3d05ecc1be3cd690254aa538b9225bbea44b569dd1843e1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:01.192261Z","signature_b64":"eBDj7EqyParBt4S/+hH98JF/xcsyeM2l4P5C7oGXxDNLvXD8c6PgUC/nn+FLLjEpJUyN3DONodM1rJBlilNNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38ef3b9e139aff34c4439e3eadfa82a1b6f6b1b3f0e39551091c225c0995ee66","last_reissued_at":"2026-07-05T10:42:01.191794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:01.191794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Amy Luo, Dinesh Jayaraman, Ian Pedroza, Jason Ma, Jie Wang, Junyao Shi, Tianyou Wang, Zhuolun Zhao","submitted_at":"2025-03-31T09:27:00Z","abstract_excerpt":"Many recent advances in robotic manipulation have come through imitation learning, yet these rely largely on mimicking a particularly hard-to-acquire form of demonstrations: those collected on the same robot in the same room with the same objects as the trained policy must handle at test time. In contrast, large pre-recorded human video datasets demonstrating manipulation skills in-the-wild already exist, which contain valuable information for robots. Is it possible to distill a repository of useful robotic skill policies out of such data without any additional requirements on robot-specific d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23877","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/2503.23877/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":"2503.23877","created_at":"2026-07-05T10:42:01.191852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23877v1","created_at":"2026-07-05T10:42:01.191852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23877","created_at":"2026-07-05T10:42:01.191852+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDXTXHQTTL7T","created_at":"2026-07-05T10:42:01.191852+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDXTXHQTTL7TJRCD","created_at":"2026-07-05T10:42:01.191852+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDXTXHQT","created_at":"2026-07-05T10:42:01.191852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28813","citing_title":"Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":104,"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":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG","json":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG.json","graph_json":"https://pith.science/api/pith-number/HDXTXHQTTL7TJRCDTY7K36UCUG/graph.json","events_json":"https://pith.science/api/pith-number/HDXTXHQTTL7TJRCDTY7K36UCUG/events.json","paper":"https://pith.science/paper/HDXTXHQT"},"agent_actions":{"view_html":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG","download_json":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG.json","view_paper":"https://pith.science/paper/HDXTXHQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23877&json=true","fetch_graph":"https://pith.science/api/pith-number/HDXTXHQTTL7TJRCDTY7K36UCUG/graph.json","fetch_events":"https://pith.science/api/pith-number/HDXTXHQTTL7TJRCDTY7K36UCUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG/action/storage_attestation","attest_author":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG/action/author_attestation","sign_citation":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG/action/citation_signature","submit_replication":"https://pith.science/pith/HDXTXHQTTL7TJRCDTY7K36UCUG/action/replication_record"}},"created_at":"2026-07-05T10:42:01.191852+00:00","updated_at":"2026-07-05T10:42:01.191852+00:00"}