{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DASG5RF3UEDXEMP26JDDNS24CF","short_pith_number":"pith:DASG5RF3","schema_version":"1.0","canonical_sha256":"18246ec4bba1077231faf24636cb5c117ab27a19ef8ac43d5b6a0c936e90a0e1","source":{"kind":"arxiv","id":"2502.09886","version":1},"attestation_state":"computed","paper":{"title":"Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Fangchen Liu, Oleh Rybkin, Pieter Abbeel, Weirui Ye, Yang Gao, Zheng Ding","submitted_at":"2025-02-14T03:22:03Z","abstract_excerpt":"Simulation offers a promising approach for cheaply scaling training data for generalist policies. To scalably generate data from diverse and realistic tasks, existing algorithms either rely on large language models (LLMs) that may hallucinate tasks not interesting for robotics; or digital twins, which require careful real-to-sim alignment and are hard to scale. To address these challenges, we introduce Video2Policy, a novel framework that leverages internet RGB videos to reconstruct tasks based on everyday human behavior. Our approach comprises two phases: (1) task generation in simulation fro"},"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":"2502.09886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-14T03:22:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8f606124d4dd9189653569f293f6687f7e21f969163ddec39e1de421784b1980","abstract_canon_sha256":"f959c9b75c6ddba1cc977c2f5f81b566c0bf4367197693331e9b9b83819ce617"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:13.813990Z","signature_b64":"hCxX6mdRbBEs0zX++n79Fdf1wDeyNlKURllDVepCsC7Ie3aLDuaLwMSd88rdQEQYBU3YOHxG7ROWA+VFVyPgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18246ec4bba1077231faf24636cb5c117ab27a19ef8ac43d5b6a0c936e90a0e1","last_reissued_at":"2026-07-05T10:14:13.813456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:13.813456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Fangchen Liu, Oleh Rybkin, Pieter Abbeel, Weirui Ye, Yang Gao, Zheng Ding","submitted_at":"2025-02-14T03:22:03Z","abstract_excerpt":"Simulation offers a promising approach for cheaply scaling training data for generalist policies. To scalably generate data from diverse and realistic tasks, existing algorithms either rely on large language models (LLMs) that may hallucinate tasks not interesting for robotics; or digital twins, which require careful real-to-sim alignment and are hard to scale. To address these challenges, we introduce Video2Policy, a novel framework that leverages internet RGB videos to reconstruct tasks based on everyday human behavior. Our approach comprises two phases: (1) task generation in simulation fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09886","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/2502.09886/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":"2502.09886","created_at":"2026-07-05T10:14:13.813532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09886v1","created_at":"2026-07-05T10:14:13.813532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09886","created_at":"2026-07-05T10:14:13.813532+00:00"},{"alias_kind":"pith_short_12","alias_value":"DASG5RF3UEDX","created_at":"2026-07-05T10:14:13.813532+00:00"},{"alias_kind":"pith_short_16","alias_value":"DASG5RF3UEDXEMP2","created_at":"2026-07-05T10:14:13.813532+00:00"},{"alias_kind":"pith_short_8","alias_value":"DASG5RF3","created_at":"2026-07-05T10:14:13.813532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01721","citing_title":"CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08828","citing_title":"Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09023","citing_title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21723","citing_title":"VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01773","citing_title":"IGen: Scalable Data Generation for Robot Learning from Open-World Images","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13030","citing_title":"Motus: A Unified Latent Action World Model","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03637","citing_title":"Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15013","citing_title":"DEX-Mouse: A Low-cost Portable and Universal Interface with Force Feedback for Data Collection of Dexterous Robotic Hands","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF","json":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF.json","graph_json":"https://pith.science/api/pith-number/DASG5RF3UEDXEMP26JDDNS24CF/graph.json","events_json":"https://pith.science/api/pith-number/DASG5RF3UEDXEMP26JDDNS24CF/events.json","paper":"https://pith.science/paper/DASG5RF3"},"agent_actions":{"view_html":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF","download_json":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF.json","view_paper":"https://pith.science/paper/DASG5RF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09886&json=true","fetch_graph":"https://pith.science/api/pith-number/DASG5RF3UEDXEMP26JDDNS24CF/graph.json","fetch_events":"https://pith.science/api/pith-number/DASG5RF3UEDXEMP26JDDNS24CF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF/action/storage_attestation","attest_author":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF/action/author_attestation","sign_citation":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF/action/citation_signature","submit_replication":"https://pith.science/pith/DASG5RF3UEDXEMP26JDDNS24CF/action/replication_record"}},"created_at":"2026-07-05T10:14:13.813532+00:00","updated_at":"2026-07-05T10:14:13.813532+00:00"}