{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7IT6SIX452AHJHBFNAAXLEDUJF","short_pith_number":"pith:7IT6SIX4","schema_version":"1.0","canonical_sha256":"fa27e922fcee80749c2568017590744956fb6167fc2fbb61e0dee1acbb5e999b","source":{"kind":"arxiv","id":"2212.07398","version":4},"attestation_state":"computed","paper":{"title":"Policy Adaptation from Foundation Model Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Annabella Macaluso, Li Erran Li, Ping Luo, Xiaolong Wang, Yuying Ge","submitted_at":"2022-12-14T18:31:47Z","abstract_excerpt":"Recent progress on vision-language foundation models have brought significant advancement to building general-purpose robots. By using the pre-trained models to encode the scene and instructions as inputs for decision making, the instruction-conditioned policy can generalize across different objects and tasks. While this is encouraging, the policy still fails in most cases given an unseen task or environment. In this work, we propose Policy Adaptation from Foundation model Feedback (PAFF). When deploying the trained policy to a new task or a new environment, we first let the policy play with r"},"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":"2212.07398","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T18:31:47Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"f1fe2914326fcd3a5be5d5f61684680dbed215137528e7b2a8f836904357b3a5","abstract_canon_sha256":"35e6e7382eea9055992e1a97b67650f67f389cfbf60d05c306ceae5bc90ee28e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:09.102423Z","signature_b64":"kk8zVVppSnGBzDG49lvSDHN0rjC7kXbF3p4ooF/pf4yhS/Q+Sod9Mclu4fz8WHZI35mbhDiJ2BdKnB6bF/FqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa27e922fcee80749c2568017590744956fb6167fc2fbb61e0dee1acbb5e999b","last_reissued_at":"2026-07-05T05:53:09.101915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:09.101915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Adaptation from Foundation Model Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Annabella Macaluso, Li Erran Li, Ping Luo, Xiaolong Wang, Yuying Ge","submitted_at":"2022-12-14T18:31:47Z","abstract_excerpt":"Recent progress on vision-language foundation models have brought significant advancement to building general-purpose robots. By using the pre-trained models to encode the scene and instructions as inputs for decision making, the instruction-conditioned policy can generalize across different objects and tasks. While this is encouraging, the policy still fails in most cases given an unseen task or environment. In this work, we propose Policy Adaptation from Foundation model Feedback (PAFF). When deploying the trained policy to a new task or a new environment, we first let the policy play with r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07398","kind":"arxiv","version":4},"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/2212.07398/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":"2212.07398","created_at":"2026-07-05T05:53:09.101974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07398v4","created_at":"2026-07-05T05:53:09.101974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07398","created_at":"2026-07-05T05:53:09.101974+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IT6SIX452AH","created_at":"2026-07-05T05:53:09.101974+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IT6SIX452AHJHBF","created_at":"2026-07-05T05:53:09.101974+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IT6SIX4","created_at":"2026-07-05T05:53:09.101974+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/7IT6SIX452AHJHBFNAAXLEDUJF","json":"https://pith.science/pith/7IT6SIX452AHJHBFNAAXLEDUJF.json","graph_json":"https://pith.science/api/pith-number/7IT6SIX452AHJHBFNAAXLEDUJF/graph.json","events_json":"https://pith.science/api/pith-number/7IT6SIX452AHJHBFNAAXLEDUJF/events.json","paper":"https://pith.science/paper/7IT6SIX4"},"agent_actions":{"view_html":"https://pith.science/pith/7IT6SIX452AHJHBFNAAXLEDUJF","download_json":"https://pith.science/pith/7IT6SIX452AHJHBFNAAXLEDUJF.json","view_paper":"https://pith.science/paper/7IT6SIX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07398&json=true","fetch_graph":"https://pith.science/api/pith-number/7IT6SIX452AHJHBFNAAXLEDUJF/graph.json","fetch_events":"https://pith.science/api/pith-number/7IT6SIX452AHJHBFNAAXLEDUJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IT6SIX452AHJHBFNAAXLEDUJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IT6SIX452AHJHBFNAAXLEDUJF/action/storage_attestation","attest_author":"https://pith.science/pith/7IT6SIX452AHJHBFNAAXLEDUJF/action/author_attestation","sign_citation":"https://pith.science/pith/7IT6SIX452AHJHBFNAAXLEDUJF/action/citation_signature","submit_replication":"https://pith.science/pith/7IT6SIX452AHJHBFNAAXLEDUJF/action/replication_record"}},"created_at":"2026-07-05T05:53:09.101974+00:00","updated_at":"2026-07-05T05:53:09.101974+00:00"}