{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DUWGK2HA2WTULJ7BP5BX25Y6W3","short_pith_number":"pith:DUWGK2HA","schema_version":"1.0","canonical_sha256":"1d2c6568e0d5a745a7e17f437d771eb6e253d8d998396956cf8ec31314b05217","source":{"kind":"arxiv","id":"2210.06601","version":2},"attestation_state":"computed","paper":{"title":"Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ashvin Nair, Gengchen Yan, Homer Walke, Kuan Fang, Patrick Yin, Sergey Levine","submitted_at":"2022-10-12T21:46:38Z","abstract_excerpt":"The utilization of broad datasets has proven to be crucial for generalization for a wide range of fields. However, how to effectively make use of diverse multi-task data for novel downstream tasks still remains a grand challenge in robotics. To tackle this challenge, we introduce a framework that acquires goal-conditioned policies for unseen temporally extended tasks via offline reinforcement learning on broad data, in combination with online fine-tuning guided by subgoals in learned lossy representation space. When faced with a novel task goal, the framework uses an affordance model to plan a"},"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":"2210.06601","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-12T21:46:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ec8dc1b1f86fddd878c236bf425652239f75f61bc56474b001eef9334044b5b4","abstract_canon_sha256":"6d40ce314dd614154dc078f53381f7b4c19b1bd74fb9b0ab3a741524ac090c78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:00.369704Z","signature_b64":"beYzAqIIWPHT9+WJsqbbOhtEDMcbgsie/4MUait1zrIxk6K2ALWfguwZZNyGQX990c0oH70iNCa86D9QiWsxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d2c6568e0d5a745a7e17f437d771eb6e253d8d998396956cf8ec31314b05217","last_reissued_at":"2026-07-05T06:02:00.369364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:00.369364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ashvin Nair, Gengchen Yan, Homer Walke, Kuan Fang, Patrick Yin, Sergey Levine","submitted_at":"2022-10-12T21:46:38Z","abstract_excerpt":"The utilization of broad datasets has proven to be crucial for generalization for a wide range of fields. However, how to effectively make use of diverse multi-task data for novel downstream tasks still remains a grand challenge in robotics. To tackle this challenge, we introduce a framework that acquires goal-conditioned policies for unseen temporally extended tasks via offline reinforcement learning on broad data, in combination with online fine-tuning guided by subgoals in learned lossy representation space. When faced with a novel task goal, the framework uses an affordance model to plan a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06601","kind":"arxiv","version":2},"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/2210.06601/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":"2210.06601","created_at":"2026-07-05T06:02:00.369420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06601v2","created_at":"2026-07-05T06:02:00.369420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06601","created_at":"2026-07-05T06:02:00.369420+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUWGK2HA2WTU","created_at":"2026-07-05T06:02:00.369420+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUWGK2HA2WTULJ7B","created_at":"2026-07-05T06:02:00.369420+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUWGK2HA","created_at":"2026-07-05T06:02:00.369420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3","json":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3.json","graph_json":"https://pith.science/api/pith-number/DUWGK2HA2WTULJ7BP5BX25Y6W3/graph.json","events_json":"https://pith.science/api/pith-number/DUWGK2HA2WTULJ7BP5BX25Y6W3/events.json","paper":"https://pith.science/paper/DUWGK2HA"},"agent_actions":{"view_html":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3","download_json":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3.json","view_paper":"https://pith.science/paper/DUWGK2HA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06601&json=true","fetch_graph":"https://pith.science/api/pith-number/DUWGK2HA2WTULJ7BP5BX25Y6W3/graph.json","fetch_events":"https://pith.science/api/pith-number/DUWGK2HA2WTULJ7BP5BX25Y6W3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3/action/storage_attestation","attest_author":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3/action/author_attestation","sign_citation":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3/action/citation_signature","submit_replication":"https://pith.science/pith/DUWGK2HA2WTULJ7BP5BX25Y6W3/action/replication_record"}},"created_at":"2026-07-05T06:02:00.369420+00:00","updated_at":"2026-07-05T06:02:00.369420+00:00"}