{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JYBZH3RIFN3MD74NRJC6TZEQN4","short_pith_number":"pith:JYBZH3RI","schema_version":"1.0","canonical_sha256":"4e0393ee282b76c1ff8d8a45e9e4906f280a76ca16fc4b4a8747e825695c6c78","source":{"kind":"arxiv","id":"2301.06987","version":3},"attestation_state":"computed","paper":{"title":"Sim-Anchored Learning for On-the-Fly Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bassel El Mabsout, Kate Saenko, Renato Mancuso, Shahin Roozkhosh, Siddharth Mysore","submitted_at":"2023-01-17T16:16:53Z","abstract_excerpt":"Fine-tuning simulation-trained RL agents with real-world data often degrades crucial behaviors due to limited or skewed data distributions. We argue that designer priorities exist not just in reward functions, but also in simulation design choices like task selection and state initialization. When adapting to real-world data, agents can experience catastrophic forgetting in important but underrepresented scenarios. We propose framing live-adaptation as a multi-objective optimization problem, where policy objectives must be satisfied both in simulation and reality. Our approach leverages critic"},"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":"2301.06987","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-01-17T16:16:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"feb3a7fb6581d357944446b26f83efa8cdefd5fa8ce479493dfa3c5295daf018","abstract_canon_sha256":"55f99384155cf2c259664b32f70bc93e36951d3867647ca2af99efde99c5377a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:19.511541Z","signature_b64":"OllQL2z06waS6wrIdQ8toHCvUMW6ZPC3Nc6QNL7qTVZvfCNvznp3RiakBxwl6P7LnmJwJe7Z6esptO0R8BrdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e0393ee282b76c1ff8d8a45e9e4906f280a76ca16fc4b4a8747e825695c6c78","last_reissued_at":"2026-07-05T10:57:19.511010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:19.511010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sim-Anchored Learning for On-the-Fly Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bassel El Mabsout, Kate Saenko, Renato Mancuso, Shahin Roozkhosh, Siddharth Mysore","submitted_at":"2023-01-17T16:16:53Z","abstract_excerpt":"Fine-tuning simulation-trained RL agents with real-world data often degrades crucial behaviors due to limited or skewed data distributions. We argue that designer priorities exist not just in reward functions, but also in simulation design choices like task selection and state initialization. When adapting to real-world data, agents can experience catastrophic forgetting in important but underrepresented scenarios. We propose framing live-adaptation as a multi-objective optimization problem, where policy objectives must be satisfied both in simulation and reality. Our approach leverages critic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06987","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/2301.06987/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":"2301.06987","created_at":"2026-07-05T10:57:19.511072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06987v3","created_at":"2026-07-05T10:57:19.511072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06987","created_at":"2026-07-05T10:57:19.511072+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYBZH3RIFN3M","created_at":"2026-07-05T10:57:19.511072+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYBZH3RIFN3MD74N","created_at":"2026-07-05T10:57:19.511072+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYBZH3RI","created_at":"2026-07-05T10:57:19.511072+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/JYBZH3RIFN3MD74NRJC6TZEQN4","json":"https://pith.science/pith/JYBZH3RIFN3MD74NRJC6TZEQN4.json","graph_json":"https://pith.science/api/pith-number/JYBZH3RIFN3MD74NRJC6TZEQN4/graph.json","events_json":"https://pith.science/api/pith-number/JYBZH3RIFN3MD74NRJC6TZEQN4/events.json","paper":"https://pith.science/paper/JYBZH3RI"},"agent_actions":{"view_html":"https://pith.science/pith/JYBZH3RIFN3MD74NRJC6TZEQN4","download_json":"https://pith.science/pith/JYBZH3RIFN3MD74NRJC6TZEQN4.json","view_paper":"https://pith.science/paper/JYBZH3RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06987&json=true","fetch_graph":"https://pith.science/api/pith-number/JYBZH3RIFN3MD74NRJC6TZEQN4/graph.json","fetch_events":"https://pith.science/api/pith-number/JYBZH3RIFN3MD74NRJC6TZEQN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYBZH3RIFN3MD74NRJC6TZEQN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYBZH3RIFN3MD74NRJC6TZEQN4/action/storage_attestation","attest_author":"https://pith.science/pith/JYBZH3RIFN3MD74NRJC6TZEQN4/action/author_attestation","sign_citation":"https://pith.science/pith/JYBZH3RIFN3MD74NRJC6TZEQN4/action/citation_signature","submit_replication":"https://pith.science/pith/JYBZH3RIFN3MD74NRJC6TZEQN4/action/replication_record"}},"created_at":"2026-07-05T10:57:19.511072+00:00","updated_at":"2026-07-05T10:57:19.511072+00:00"}