{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F4SLNJKC55CSWB2JADDK4U3P54","short_pith_number":"pith:F4SLNJKC","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"},"canonical_sha256":"2f24b6a542ef452b074900c6ae536fef28f4223cd20093c52ac8dfa275462fc4","source":{"kind":"arxiv","id":"2409.15521","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15521","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15521v1","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15521","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_12","alias_value":"F4SLNJKC55CS","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_16","alias_value":"F4SLNJKC55CSWB2J","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_8","alias_value":"F4SLNJKC","created_at":"2026-07-05T09:10:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F4SLNJKC55CSWB2JADDK4U3P54","target":"record","payload":{"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"},"canonical_sha256":"2f24b6a542ef452b074900c6ae536fef28f4223cd20093c52ac8dfa275462fc4","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"},"source_kind":"arxiv","source_id":"2409.15521","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sCZT7JOj1oh1nB5dSvO6T18r8GesX2Lorhuphr6j8D0vQmOmkZ1bR4sZTuUdf8rieq0rGexUuC9TbCOu+VdpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:26:53.622169Z"},"content_sha256":"37839ea7f393cb60d35130459be2fac33ecb4215e29fa8a6f021e97228b1144c","schema_version":"1.0","event_id":"sha256:37839ea7f393cb60d35130459be2fac33ecb4215e29fa8a6f021e97228b1144c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F4SLNJKC55CSWB2JADDK4U3P54","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udNu2wfGP2wgpqZPSfTnj6CxoOKqhBGOgqURlspRMr2LqHUf/RpcoK3RaES+52gFtNV876rbk58UOqvLrwHcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:26:53.622551Z"},"content_sha256":"eb3d66d80e87f7e05ea814d9008cdf633fb105f22c4ac243445f810986fb467d","schema_version":"1.0","event_id":"sha256:eb3d66d80e87f7e05ea814d9008cdf633fb105f22c4ac243445f810986fb467d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/bundle.json","state_url":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4SLNJKC55CSWB2JADDK4U3P54/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T10:26:53Z","links":{"resolver":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54","bundle":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/bundle.json","state":"https://pith.science/pith/F4SLNJKC55CSWB2JADDK4U3P54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4SLNJKC55CSWB2JADDK4U3P54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F4SLNJKC55CSWB2JADDK4U3P54","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"589a7acd5f51d002c1610b4d1d4882f00381c8abc48b268d2aaf1281a520b9b3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-23T20:14:12Z","title_canon_sha256":"2e915378f7466a11ae604e57bdd04636181adfe9770bf5bb1aa8c1a1bcda7b65"},"schema_version":"1.0","source":{"id":"2409.15521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15521","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15521v1","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15521","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_12","alias_value":"F4SLNJKC55CS","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_16","alias_value":"F4SLNJKC55CSWB2J","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_8","alias_value":"F4SLNJKC","created_at":"2026-07-05T09:10:56Z"}],"graph_snapshots":[{"event_id":"sha256:eb3d66d80e87f7e05ea814d9008cdf633fb105f22c4ac243445f810986fb467d","target":"graph","created_at":"2026-07-05T09:10:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.15521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Matthew E. Taylor, Srijita Das, Yuxuan Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-23T20:14:12Z","title":"CANDERE-COACH: Reinforcement Learning from Noisy Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15521","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:37839ea7f393cb60d35130459be2fac33ecb4215e29fa8a6f021e97228b1144c","target":"record","created_at":"2026-07-05T09:10:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"589a7acd5f51d002c1610b4d1d4882f00381c8abc48b268d2aaf1281a520b9b3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-23T20:14:12Z","title_canon_sha256":"2e915378f7466a11ae604e57bdd04636181adfe9770bf5bb1aa8c1a1bcda7b65"},"schema_version":"1.0","source":{"id":"2409.15521","kind":"arxiv","version":1}},"canonical_sha256":"2f24b6a542ef452b074900c6ae536fef28f4223cd20093c52ac8dfa275462fc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f24b6a542ef452b074900c6ae536fef28f4223cd20093c52ac8dfa275462fc4","first_computed_at":"2026-07-05T09:10:56.211974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:56.211974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KubDcnIiH64WXug+8XCvyyFm5zHyvZynvd5v/Mn3ibPh6jyFRmePqo4M5z5OH1vz66FCwpnzqdvs+fVwN3u0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:56.212427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37839ea7f393cb60d35130459be2fac33ecb4215e29fa8a6f021e97228b1144c","sha256:eb3d66d80e87f7e05ea814d9008cdf633fb105f22c4ac243445f810986fb467d"],"state_sha256":"ad07594795e900d5c3b9cf93ba02c7adb62ef6079ae964a9336619b51eb25e66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEss4XkCG+ChWJDCWHDiqWcGTCOwOgIQ87n2BBRNEI9HnVRg5ivy3Ztq611bNfiANcS6MTUXmTJKfGiDd3YMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:26:53.624541Z","bundle_sha256":"4d4205ad87807e8dc0e8948a58703946e000b80efa5179874ae9d9aea8b950dc"}}