{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JEZH6XTWWL3RJXW6XRAHHD7D3O","short_pith_number":"pith:JEZH6XTW","schema_version":"1.0","canonical_sha256":"49327f5e76b2f714dedebc40738fe3dba9b2cbbd2474e7a880ae0d24cf992617","source":{"kind":"arxiv","id":"2406.15917","version":1},"attestation_state":"computed","paper":{"title":"To Err is Robotic: Rapid Value-Based Trial-and-Error during Deployment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alexander Khazatsky, Chelsea Finn, Maximilian Du, Tobias Gerstenberg","submitted_at":"2024-06-22T18:57:37Z","abstract_excerpt":"When faced with a novel scenario, it can be hard to succeed on the first attempt. In these challenging situations, it is important to know how to retry quickly and meaningfully. Retrying behavior can emerge naturally in robots trained on diverse data, but such robot policies will typically only exhibit undirected retrying behavior and may not terminate a suboptimal approach before an unrecoverable mistake. We can improve these robot policies by instilling an explicit ability to try, evaluate, and retry a diverse range of strategies. We introduce Bellman-Guided Retrials, an algorithm that works"},"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":"2406.15917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-22T18:57:37Z","cross_cats_sorted":[],"title_canon_sha256":"c923521eb46155768c7f9d394f5b55508a19e9aff995d37cfa49d0a919eb47fe","abstract_canon_sha256":"3c77b44abbb8d21fac1a7513bb1d8c456851121c4e57102bf6f1d149c8e23e16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:50.552873Z","signature_b64":"20OND9Fe2hj4aGaLeyNuuwV3rZPlp9Q1oZEthpBx+r+cQyeXZhUa6soyxt5ycIcZ9gFFM/RUNRGiN8YxNFCkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49327f5e76b2f714dedebc40738fe3dba9b2cbbd2474e7a880ae0d24cf992617","last_reissued_at":"2026-07-05T08:35:50.552410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:50.552410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To Err is Robotic: Rapid Value-Based Trial-and-Error during Deployment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alexander Khazatsky, Chelsea Finn, Maximilian Du, Tobias Gerstenberg","submitted_at":"2024-06-22T18:57:37Z","abstract_excerpt":"When faced with a novel scenario, it can be hard to succeed on the first attempt. In these challenging situations, it is important to know how to retry quickly and meaningfully. Retrying behavior can emerge naturally in robots trained on diverse data, but such robot policies will typically only exhibit undirected retrying behavior and may not terminate a suboptimal approach before an unrecoverable mistake. We can improve these robot policies by instilling an explicit ability to try, evaluate, and retry a diverse range of strategies. We introduce Bellman-Guided Retrials, an algorithm that works"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15917","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/2406.15917/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":"2406.15917","created_at":"2026-07-05T08:35:50.552475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15917v1","created_at":"2026-07-05T08:35:50.552475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15917","created_at":"2026-07-05T08:35:50.552475+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEZH6XTWWL3R","created_at":"2026-07-05T08:35:50.552475+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEZH6XTWWL3RJXW6","created_at":"2026-07-05T08:35:50.552475+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEZH6XTW","created_at":"2026-07-05T08:35:50.552475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01111","citing_title":"FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O","json":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O.json","graph_json":"https://pith.science/api/pith-number/JEZH6XTWWL3RJXW6XRAHHD7D3O/graph.json","events_json":"https://pith.science/api/pith-number/JEZH6XTWWL3RJXW6XRAHHD7D3O/events.json","paper":"https://pith.science/paper/JEZH6XTW"},"agent_actions":{"view_html":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O","download_json":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O.json","view_paper":"https://pith.science/paper/JEZH6XTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15917&json=true","fetch_graph":"https://pith.science/api/pith-number/JEZH6XTWWL3RJXW6XRAHHD7D3O/graph.json","fetch_events":"https://pith.science/api/pith-number/JEZH6XTWWL3RJXW6XRAHHD7D3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O/action/storage_attestation","attest_author":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O/action/author_attestation","sign_citation":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O/action/citation_signature","submit_replication":"https://pith.science/pith/JEZH6XTWWL3RJXW6XRAHHD7D3O/action/replication_record"}},"created_at":"2026-07-05T08:35:50.552475+00:00","updated_at":"2026-07-05T08:35:50.552475+00:00"}