{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F4SLNJKC55CSWB2JADDK4U3P54","short_pith_number":"pith:F4SLNJKC","schema_version":"1.0","canonical_sha256":"2f24b6a542ef452b074900c6ae536fef28f4223cd20093c52ac8dfa275462fc4","source":{"kind":"arxiv","id":"2409.15521","version":1},"attestation_state":"computed","paper":{"title":"CANDERE-COACH: Reinforcement Learning from Noisy Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Matthew E. Taylor, Srijita Das, Yuxuan Li","submitted_at":"2024-09-23T20:14:12Z","abstract_excerpt":"In recent times, Reinforcement learning (RL) has been widely applied to many challenging tasks. However, in order to perform well, it requires access to a good reward function which is often sparse or manually engineered with scope for error. Introducing human prior knowledge is often seen as a possible solution to the above-mentioned problem, such as imitation learning, learning from preference, and inverse reinforcement learning. Learning from feedback is another framework that enables an RL agent to learn from binary evaluative signals describing the teacher's (positive or negative) evaluat"},"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":"2409.15521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-23T20:14:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e915378f7466a11ae604e57bdd04636181adfe9770bf5bb1aa8c1a1bcda7b65","abstract_canon_sha256":"589a7acd5f51d002c1610b4d1d4882f00381c8abc48b268d2aaf1281a520b9b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:56.212427Z","signature_b64":"KubDcnIiH64WXug+8XCvyyFm5zHyvZynvd5v/Mn3ibPh6jyFRmePqo4M5z5OH1vz66FCwpnzqdvs+fVwN3u0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f24b6a542ef452b074900c6ae536fef28f4223cd20093c52ac8dfa275462fc4","last_reissued_at":"2026-07-05T09:10:56.211974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:56.211974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CANDERE-COACH: Reinforcement Learning from Noisy Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Matthew E. Taylor, Srijita Das, Yuxuan Li","submitted_at":"2024-09-23T20:14:12Z","abstract_excerpt":"In recent times, Reinforcement learning (RL) has been widely applied to many challenging tasks. However, in order to perform well, it requires access to a good reward function which is often sparse or manually engineered with scope for error. Introducing human prior knowledge is often seen as a possible solution to the above-mentioned problem, such as imitation learning, learning from preference, and inverse reinforcement learning. Learning from feedback is another framework that enables an RL agent to learn from binary evaluative signals describing the teacher's (positive or negative) evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15521","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/2409.15521/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":"2409.15521","created_at":"2026-07-05T09:10:56.212029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15521v1","created_at":"2026-07-05T09:10:56.212029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15521","created_at":"2026-07-05T09:10:56.212029+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4SLNJKC55CS","created_at":"2026-07-05T09:10:56.212029+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4SLNJKC55CSWB2J","created_at":"2026-07-05T09:10:56.212029+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4SLNJKC","created_at":"2026-07-05T09:10:56.212029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24515","citing_title":"Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54","json":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54.json","graph_json":"https://pith.science/api/pith-number/F4SLNJKC55CSWB2JADDK4U3P54/graph.json","events_json":"https://pith.science/api/pith-number/F4SLNJKC55CSWB2JADDK4U3P54/events.json","paper":"https://pith.science/paper/F4SLNJKC"},"agent_actions":{"view_html":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54","download_json":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54.json","view_paper":"https://pith.science/paper/F4SLNJKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15521&json=true","fetch_graph":"https://pith.science/api/pith-number/F4SLNJKC55CSWB2JADDK4U3P54/graph.json","fetch_events":"https://pith.science/api/pith-number/F4SLNJKC55CSWB2JADDK4U3P54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/action/storage_attestation","attest_author":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/action/author_attestation","sign_citation":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/action/citation_signature","submit_replication":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/action/replication_record"}},"created_at":"2026-07-05T09:10:56.212029+00:00","updated_at":"2026-07-05T09:10:56.212029+00:00"}