{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T3MYFNLUX7JJ7WRWN7VWCROLBG","short_pith_number":"pith:T3MYFNLU","schema_version":"1.0","canonical_sha256":"9ed982b574bfd29fda366feb6145cb09a4cdd45846e855983c245c88bc183b5d","source":{"kind":"arxiv","id":"2310.08573","version":1},"attestation_state":"computed","paper":{"title":"PolyTask: Learning Unified Policies through Behavior Distillation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lerrel Pinto, Siddhant Haldar","submitted_at":"2023-10-12T17:57:32Z","abstract_excerpt":"Unified models capable of solving a wide variety of tasks have gained traction in vision and NLP due to their ability to share regularities and structures across tasks, which improves individual task performance and reduces computational footprint. However, the impact of such models remains limited in embodied learning problems, which present unique challenges due to interactivity, sample inefficiency, and sequential task presentation. In this work, we present PolyTask, a novel method for learning a single unified model that can solve various embodied tasks through a 'learn then distill' mecha"},"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":"2310.08573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-12T17:57:32Z","cross_cats_sorted":[],"title_canon_sha256":"3046db58c92bf2b56484eb3513693436762410392f6f5d8ac996e6fb70100c10","abstract_canon_sha256":"bf1c858748377956861e3616ced35dc5bcb6abded7b3159075006b0de2efddb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:17.258786Z","signature_b64":"zjHYTKNQ0L49K5Ur5irmjiYOA6gA7iSXb15mHTlGuAxIMUEfn4en+YHFObC+JLCRKJcANrVAIq0JCcyd/R3fCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ed982b574bfd29fda366feb6145cb09a4cdd45846e855983c245c88bc183b5d","last_reissued_at":"2026-07-05T07:00:17.258305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:17.258305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolyTask: Learning Unified Policies through Behavior Distillation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lerrel Pinto, Siddhant Haldar","submitted_at":"2023-10-12T17:57:32Z","abstract_excerpt":"Unified models capable of solving a wide variety of tasks have gained traction in vision and NLP due to their ability to share regularities and structures across tasks, which improves individual task performance and reduces computational footprint. However, the impact of such models remains limited in embodied learning problems, which present unique challenges due to interactivity, sample inefficiency, and sequential task presentation. In this work, we present PolyTask, a novel method for learning a single unified model that can solve various embodied tasks through a 'learn then distill' mecha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08573","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/2310.08573/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":"2310.08573","created_at":"2026-07-05T07:00:17.258374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08573v1","created_at":"2026-07-05T07:00:17.258374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08573","created_at":"2026-07-05T07:00:17.258374+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3MYFNLUX7JJ","created_at":"2026-07-05T07:00:17.258374+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3MYFNLUX7JJ7WRW","created_at":"2026-07-05T07:00:17.258374+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3MYFNLU","created_at":"2026-07-05T07:00:17.258374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03449","citing_title":"Neural Operators for Multi-Task Control and Adaptation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2501.15830","citing_title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG","json":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG.json","graph_json":"https://pith.science/api/pith-number/T3MYFNLUX7JJ7WRWN7VWCROLBG/graph.json","events_json":"https://pith.science/api/pith-number/T3MYFNLUX7JJ7WRWN7VWCROLBG/events.json","paper":"https://pith.science/paper/T3MYFNLU"},"agent_actions":{"view_html":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG","download_json":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG.json","view_paper":"https://pith.science/paper/T3MYFNLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08573&json=true","fetch_graph":"https://pith.science/api/pith-number/T3MYFNLUX7JJ7WRWN7VWCROLBG/graph.json","fetch_events":"https://pith.science/api/pith-number/T3MYFNLUX7JJ7WRWN7VWCROLBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG/action/storage_attestation","attest_author":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG/action/author_attestation","sign_citation":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG/action/citation_signature","submit_replication":"https://pith.science/pith/T3MYFNLUX7JJ7WRWN7VWCROLBG/action/replication_record"}},"created_at":"2026-07-05T07:00:17.258374+00:00","updated_at":"2026-07-05T07:00:17.258374+00:00"}