{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RXIAQLMUSO3EJFOJP35MHOVC5Z","short_pith_number":"pith:RXIAQLMU","schema_version":"1.0","canonical_sha256":"8dd0082d9493b64495c97efac3baa2ee56282af8f8075554fbfc469469970ce1","source":{"kind":"arxiv","id":"2402.02511","version":3},"attestation_state":"computed","paper":{"title":"PoCo: Policy Composition from and for Heterogeneous Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward H. Adelson, Jialiang Zhao, Lirui Wang, Russ Tedrake, Yilun Du","submitted_at":"2024-02-04T14:51:49Z","abstract_excerpt":"Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile, and proprioceptive information, and collected in different domains such as simulation, real robots, and human videos. Current methods usually collect and pool all data from one domain to train a single policy to handle such heterogeneity in tasks and domains, which is prohibitively expensive and difficult. In this work, we present a flexible approach, dubbed Policy Composition, to combine information acro"},"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":"2402.02511","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-04T14:51:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fe8ea84a952f4c54383a7d505d7b96118bf44d8f3c7d89ca771773fa79b9855","abstract_canon_sha256":"f1e3ad4f158e9f5317df39f1e0b3242aeae2fb56b8bd274aa7c1c4fce25cbb23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:22.678523Z","signature_b64":"zxcAoM8+74hAVFr66bJbIK6PY6WRdrKo6ztgtgx7SRlDDj7lVf5QwJ5RR97JBs6Vwrh5HSpbgiHVg3HWJ6qCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dd0082d9493b64495c97efac3baa2ee56282af8f8075554fbfc469469970ce1","last_reissued_at":"2026-07-05T09:42:22.677962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:22.677962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoCo: Policy Composition from and for Heterogeneous Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward H. Adelson, Jialiang Zhao, Lirui Wang, Russ Tedrake, Yilun Du","submitted_at":"2024-02-04T14:51:49Z","abstract_excerpt":"Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile, and proprioceptive information, and collected in different domains such as simulation, real robots, and human videos. Current methods usually collect and pool all data from one domain to train a single policy to handle such heterogeneity in tasks and domains, which is prohibitively expensive and difficult. In this work, we present a flexible approach, dubbed Policy Composition, to combine information acro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02511","kind":"arxiv","version":3},"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/2402.02511/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":"2402.02511","created_at":"2026-07-05T09:42:22.678043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02511v3","created_at":"2026-07-05T09:42:22.678043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02511","created_at":"2026-07-05T09:42:22.678043+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXIAQLMUSO3E","created_at":"2026-07-05T09:42:22.678043+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXIAQLMUSO3EJFOJ","created_at":"2026-07-05T09:42:22.678043+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXIAQLMU","created_at":"2026-07-05T09:42:22.678043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21646","citing_title":"Energy-based Compositional Diffusion Planning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10818","citing_title":"IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23468","citing_title":"Multi-Modal Manipulation via Multi-Modal Policy Consensus","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15799","citing_title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2409.00588","citing_title":"Diffusion Policy Policy Optimization","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05855","citing_title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23121","citing_title":"Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z","json":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z.json","graph_json":"https://pith.science/api/pith-number/RXIAQLMUSO3EJFOJP35MHOVC5Z/graph.json","events_json":"https://pith.science/api/pith-number/RXIAQLMUSO3EJFOJP35MHOVC5Z/events.json","paper":"https://pith.science/paper/RXIAQLMU"},"agent_actions":{"view_html":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z","download_json":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z.json","view_paper":"https://pith.science/paper/RXIAQLMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02511&json=true","fetch_graph":"https://pith.science/api/pith-number/RXIAQLMUSO3EJFOJP35MHOVC5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/RXIAQLMUSO3EJFOJP35MHOVC5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z/action/storage_attestation","attest_author":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z/action/author_attestation","sign_citation":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z/action/citation_signature","submit_replication":"https://pith.science/pith/RXIAQLMUSO3EJFOJP35MHOVC5Z/action/replication_record"}},"created_at":"2026-07-05T09:42:22.678043+00:00","updated_at":"2026-07-05T09:42:22.678043+00:00"}