{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7IZAURTHYJN43EG2DM6QYRJUHA","short_pith_number":"pith:7IZAURTH","canonical_record":{"source":{"id":"1805.10627","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-27T13:51:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2254f5dc1ddaa8a3df117fd52039c5ee83480555a0117dfa4fd9da7a035e27d7","abstract_canon_sha256":"be66dd2d0000906a95913f1ea58177c5bc6c12b316d5b677ba9c06e8957cf3ae"},"schema_version":"1.0"},"canonical_sha256":"fa320a4667c25bcd90da1b3d0c45343826ca12389439f2a6f1a8cfcb51feb7b7","source":{"kind":"arxiv","id":"1805.10627","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10627","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10627v3","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10627","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"7IZAURTHYJN4","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7IZAURTHYJN43EG2","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7IZAURTH","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7IZAURTHYJN43EG2DM6QYRJUHA","target":"record","payload":{"canonical_record":{"source":{"id":"1805.10627","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-27T13:51:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2254f5dc1ddaa8a3df117fd52039c5ee83480555a0117dfa4fd9da7a035e27d7","abstract_canon_sha256":"be66dd2d0000906a95913f1ea58177c5bc6c12b316d5b677ba9c06e8957cf3ae"},"schema_version":"1.0"},"canonical_sha256":"fa320a4667c25bcd90da1b3d0c45343826ca12389439f2a6f1a8cfcb51feb7b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:22.995105Z","signature_b64":"Qxr6/cAIE4TXsOUB8HJ5i2GgwqtjLsomX237BA1lgYpwfaBN3dxQHu1U5qh3HYqRJSXGxGtZoGWyFkHAaCr4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa320a4667c25bcd90da1b3d0c45343826ca12389439f2a6f1a8cfcb51feb7b7","last_reissued_at":"2026-05-17T23:58:22.994297Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:22.994297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.10627","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rpx4BYLkepieHKXz8pM+WcSAbTcPPKqsjJEqlJn08p4D/E6m4qQl4mT4gdpCssf4A84vWyAgUDPZHo/6t5QdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:36:52.235421Z"},"content_sha256":"7853678c0cc7b2c6bd98a683917a283933564654f51412fe04a0bf3745d5b039","schema_version":"1.0","event_id":"sha256:7853678c0cc7b2c6bd98a683917a283933564654f51412fe04a0bf3745d5b039"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7IZAURTHYJN43EG2DM6QYRJUHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Joshua Uyheng, Julia Kreutzer, Stefan Riezler","submitted_at":"2018-05-27T13:51:48Z","abstract_excerpt":"We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator, and the effect of the quality of reward estimates on the overall RL task. Our analysis of cardinal (5-point ratings) and ordinal (pairwise preferences) feedback shows that their intra- and inter-annotator $\\alpha$-agreement is comparable. Best reliability is obtained for standar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10627","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":""},"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":"2026-05-17T23:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gElPgT866osXJ4vnWk66mWLbwpX+IblQCyNXm9Qfa6HxymWVKA/D2KL6lPZrxE+NrbJB8LMg/oEEnTkHOFtFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:36:52.235933Z"},"content_sha256":"3415e55d152ae8548fe7b3d324169f6c1d8fdd788ec102fffecf2cd908f26365","schema_version":"1.0","event_id":"sha256:3415e55d152ae8548fe7b3d324169f6c1d8fdd788ec102fffecf2cd908f26365"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7IZAURTHYJN43EG2DM6QYRJUHA/bundle.json","state_url":"https://pith.science/pith/7IZAURTHYJN43EG2DM6QYRJUHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7IZAURTHYJN43EG2DM6QYRJUHA/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":"2026-06-09T14:36:52Z","links":{"resolver":"https://pith.science/pith/7IZAURTHYJN43EG2DM6QYRJUHA","bundle":"https://pith.science/pith/7IZAURTHYJN43EG2DM6QYRJUHA/bundle.json","state":"https://pith.science/pith/7IZAURTHYJN43EG2DM6QYRJUHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7IZAURTHYJN43EG2DM6QYRJUHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7IZAURTHYJN43EG2DM6QYRJUHA","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":"be66dd2d0000906a95913f1ea58177c5bc6c12b316d5b677ba9c06e8957cf3ae","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-27T13:51:48Z","title_canon_sha256":"2254f5dc1ddaa8a3df117fd52039c5ee83480555a0117dfa4fd9da7a035e27d7"},"schema_version":"1.0","source":{"id":"1805.10627","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10627","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10627v3","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10627","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"7IZAURTHYJN4","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7IZAURTHYJN43EG2","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7IZAURTH","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:3415e55d152ae8548fe7b3d324169f6c1d8fdd788ec102fffecf2cd908f26365","target":"graph","created_at":"2026-05-17T23:58:22Z","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"},"paper":{"abstract_excerpt":"We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator, and the effect of the quality of reward estimates on the overall RL task. Our analysis of cardinal (5-point ratings) and ordinal (pairwise preferences) feedback shows that their intra- and inter-annotator $\\alpha$-agreement is comparable. Best reliability is obtained for standar","authors_text":"Joshua Uyheng, Julia Kreutzer, Stefan Riezler","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-27T13:51:48Z","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10627","kind":"arxiv","version":3},"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":"sha256:7853678c0cc7b2c6bd98a683917a283933564654f51412fe04a0bf3745d5b039","target":"record","created_at":"2026-05-17T23:58:22Z","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":"be66dd2d0000906a95913f1ea58177c5bc6c12b316d5b677ba9c06e8957cf3ae","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-27T13:51:48Z","title_canon_sha256":"2254f5dc1ddaa8a3df117fd52039c5ee83480555a0117dfa4fd9da7a035e27d7"},"schema_version":"1.0","source":{"id":"1805.10627","kind":"arxiv","version":3}},"canonical_sha256":"fa320a4667c25bcd90da1b3d0c45343826ca12389439f2a6f1a8cfcb51feb7b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa320a4667c25bcd90da1b3d0c45343826ca12389439f2a6f1a8cfcb51feb7b7","first_computed_at":"2026-05-17T23:58:22.994297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:22.994297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qxr6/cAIE4TXsOUB8HJ5i2GgwqtjLsomX237BA1lgYpwfaBN3dxQHu1U5qh3HYqRJSXGxGtZoGWyFkHAaCr4DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:22.995105Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.10627","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7853678c0cc7b2c6bd98a683917a283933564654f51412fe04a0bf3745d5b039","sha256:3415e55d152ae8548fe7b3d324169f6c1d8fdd788ec102fffecf2cd908f26365"],"state_sha256":"7319bdd5d120754df43e6978d5a832de2a68ad06dd87ed6146d4c5218d61d2db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sNcOAVdjYmIdSmNhoCnB0c13N82c52nHQo59DswFOUu39FYpIpEO/vN6GaQyxtT5aFq4eye4Tdj771Dyi0uNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T14:36:52.238189Z","bundle_sha256":"a45a6f32fe11f1393579ce2deb9df014bbcab380f0909d72eac2b8c168b51abb"}}