{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:62VUHCQHECPB6OC6BRFWKFOEJC","short_pith_number":"pith:62VUHCQH","schema_version":"1.0","canonical_sha256":"f6ab438a07209e1f385e0c4b6515c448a6e05c07a15090bac99de71d80014f5d","source":{"kind":"arxiv","id":"2307.10524","version":2},"attestation_state":"computed","paper":{"title":"Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Shaolei Ren, Tongxin Li, Yiheng Lin","submitted_at":"2023-07-20T01:56:10Z","abstract_excerpt":"We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice. Our work departs from the typical approach of treating advice as coming from black-box sources by instead considering a setting where additional information about how the advice is generated is available. We prove a first-of-its-kind consistency and robustness tradeoff given Q-value advice under a general MDP model that includes both continuous and discrete state/action spaces. Our results highlight that utilizing Q-val"},"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":"2307.10524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T01:56:10Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"2833b84cb59dfa003fa410a7af75650ba66348bce5ce51d626eb08f3766ba581","abstract_canon_sha256":"6ddcf47c3a9159160331ac7bcd482f0295afebd8186cc4f394a02736cac34a66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:32.194039Z","signature_b64":"9b8C1sXG1ABrr4UAJidDeqB7DY7sQag/eZTjYL79+Jp1roZhUo/S3m8a1bJIDdrjulAvUrZXf9CS6lkMcgEIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6ab438a07209e1f385e0c4b6515c448a6e05c07a15090bac99de71d80014f5d","last_reissued_at":"2026-07-05T07:06:32.193551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:32.193551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Shaolei Ren, Tongxin Li, Yiheng Lin","submitted_at":"2023-07-20T01:56:10Z","abstract_excerpt":"We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice. Our work departs from the typical approach of treating advice as coming from black-box sources by instead considering a setting where additional information about how the advice is generated is available. We prove a first-of-its-kind consistency and robustness tradeoff given Q-value advice under a general MDP model that includes both continuous and discrete state/action spaces. Our results highlight that utilizing Q-val"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10524","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/2307.10524/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":"2307.10524","created_at":"2026-07-05T07:06:32.193610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10524v2","created_at":"2026-07-05T07:06:32.193610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10524","created_at":"2026-07-05T07:06:32.193610+00:00"},{"alias_kind":"pith_short_12","alias_value":"62VUHCQHECPB","created_at":"2026-07-05T07:06:32.193610+00:00"},{"alias_kind":"pith_short_16","alias_value":"62VUHCQHECPB6OC6","created_at":"2026-07-05T07:06:32.193610+00:00"},{"alias_kind":"pith_short_8","alias_value":"62VUHCQH","created_at":"2026-07-05T07:06:32.193610+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/62VUHCQHECPB6OC6BRFWKFOEJC","json":"https://pith.science/pith/62VUHCQHECPB6OC6BRFWKFOEJC.json","graph_json":"https://pith.science/api/pith-number/62VUHCQHECPB6OC6BRFWKFOEJC/graph.json","events_json":"https://pith.science/api/pith-number/62VUHCQHECPB6OC6BRFWKFOEJC/events.json","paper":"https://pith.science/paper/62VUHCQH"},"agent_actions":{"view_html":"https://pith.science/pith/62VUHCQHECPB6OC6BRFWKFOEJC","download_json":"https://pith.science/pith/62VUHCQHECPB6OC6BRFWKFOEJC.json","view_paper":"https://pith.science/paper/62VUHCQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10524&json=true","fetch_graph":"https://pith.science/api/pith-number/62VUHCQHECPB6OC6BRFWKFOEJC/graph.json","fetch_events":"https://pith.science/api/pith-number/62VUHCQHECPB6OC6BRFWKFOEJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62VUHCQHECPB6OC6BRFWKFOEJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62VUHCQHECPB6OC6BRFWKFOEJC/action/storage_attestation","attest_author":"https://pith.science/pith/62VUHCQHECPB6OC6BRFWKFOEJC/action/author_attestation","sign_citation":"https://pith.science/pith/62VUHCQHECPB6OC6BRFWKFOEJC/action/citation_signature","submit_replication":"https://pith.science/pith/62VUHCQHECPB6OC6BRFWKFOEJC/action/replication_record"}},"created_at":"2026-07-05T07:06:32.193610+00:00","updated_at":"2026-07-05T07:06:32.193610+00:00"}