{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QZING43BF4KAUW2FOBRBLPDBQG","short_pith_number":"pith:QZING43B","canonical_record":{"source":{"id":"1805.03766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T00:51:06Z","cross_cats_sorted":[],"title_canon_sha256":"b27741d2db3ab81b70c13affb96ac61dde4fbfdf58b663a5ad064d262ee05f7b","abstract_canon_sha256":"a0f874233194917646243a77bf8ecee95267281860ea84b1f436609cafbc9d7f"},"schema_version":"1.0"},"canonical_sha256":"8650d373612f140a5b45706215bc6181a6caecec58fea36851572aad96cf40a5","source":{"kind":"arxiv","id":"1805.03766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03766","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03766v1","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03766","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"QZING43BF4KA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"QZING43BF4KAUW2F","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"QZING43B","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QZING43BF4KAUW2FOBRBLPDBQG","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T00:51:06Z","cross_cats_sorted":[],"title_canon_sha256":"b27741d2db3ab81b70c13affb96ac61dde4fbfdf58b663a5ad064d262ee05f7b","abstract_canon_sha256":"a0f874233194917646243a77bf8ecee95267281860ea84b1f436609cafbc9d7f"},"schema_version":"1.0"},"canonical_sha256":"8650d373612f140a5b45706215bc6181a6caecec58fea36851572aad96cf40a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:18.829157Z","signature_b64":"VIKlMMdSQssg9L2fSGdTlnPwitXzeB/KKcXOWY/Ss0UfAqpJhVUpyCub813X7kc04iK1SnzMLSeFqcvitXYFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8650d373612f140a5b45706215bc6181a6caecec58fea36851572aad96cf40a5","last_reissued_at":"2026-05-18T00:16:18.828643Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:18.828643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03766","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":"2026-05-18T00:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WoOi1+8+eQKuNDusH7MC5DZTFNuFCfkLRtrQH028EBUwNXK7z00YmpICpZic8hhK6v6TImi3YTq9qVuOJSuQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:44:50.340928Z"},"content_sha256":"eabf6fceee9d30a59d561122ca2c507790a4b4cdf38aecb43a105b81f3c7e140","schema_version":"1.0","event_id":"sha256:eabf6fceee9d30a59d561122ca2c507790a4b4cdf38aecb43a105b81f3c7e140"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QZING43BF4KAUW2FOBRBLPDBQG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discourse-Aware Neural Rewards for Coherent Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antoine Bosselut, Asli Celikyilmaz, Jianfeng Gao, Po-Sen Huang, Xiaodong He, Yejin Choi","submitted_at":"2018-05-10T00:51:06Z","abstract_excerpt":"In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired discourse structure. Empirical results demonstrate that a generator trained with the learned reward produces more coherent and less repetitive text than models trained with cross-entropy or with reinforcement learning with commonly used scores as rewards."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03766","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":""},"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":"2026-05-18T00:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jDRNWl+EFi2ZCCbyyNZ9xIuge6lpOiCkjFYpqi4qrU18B7O54FUqEDHFeQx+JqqYyVJRXq6re6lFTUwp+8Q8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:44:50.341322Z"},"content_sha256":"943b7e963aed2b317576a58e257e08a535320b6017bbe88c38738340e2d532d9","schema_version":"1.0","event_id":"sha256:943b7e963aed2b317576a58e257e08a535320b6017bbe88c38738340e2d532d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZING43BF4KAUW2FOBRBLPDBQG/bundle.json","state_url":"https://pith.science/pith/QZING43BF4KAUW2FOBRBLPDBQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZING43BF4KAUW2FOBRBLPDBQG/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":"2026-08-03T18:44:50Z","links":{"resolver":"https://pith.science/pith/QZING43BF4KAUW2FOBRBLPDBQG","bundle":"https://pith.science/pith/QZING43BF4KAUW2FOBRBLPDBQG/bundle.json","state":"https://pith.science/pith/QZING43BF4KAUW2FOBRBLPDBQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZING43BF4KAUW2FOBRBLPDBQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QZING43BF4KAUW2FOBRBLPDBQG","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":"a0f874233194917646243a77bf8ecee95267281860ea84b1f436609cafbc9d7f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T00:51:06Z","title_canon_sha256":"b27741d2db3ab81b70c13affb96ac61dde4fbfdf58b663a5ad064d262ee05f7b"},"schema_version":"1.0","source":{"id":"1805.03766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03766","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03766v1","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03766","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"QZING43BF4KA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"QZING43BF4KAUW2F","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"QZING43B","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:943b7e963aed2b317576a58e257e08a535320b6017bbe88c38738340e2d532d9","target":"graph","created_at":"2026-05-18T00:16:18Z","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":"In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired discourse structure. Empirical results demonstrate that a generator trained with the learned reward produces more coherent and less repetitive text than models trained with cross-entropy or with reinforcement learning with commonly used scores as rewards.","authors_text":"Antoine Bosselut, Asli Celikyilmaz, Jianfeng Gao, Po-Sen Huang, Xiaodong He, Yejin Choi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T00:51:06Z","title":"Discourse-Aware Neural Rewards for Coherent Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03766","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:eabf6fceee9d30a59d561122ca2c507790a4b4cdf38aecb43a105b81f3c7e140","target":"record","created_at":"2026-05-18T00:16:18Z","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":"a0f874233194917646243a77bf8ecee95267281860ea84b1f436609cafbc9d7f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T00:51:06Z","title_canon_sha256":"b27741d2db3ab81b70c13affb96ac61dde4fbfdf58b663a5ad064d262ee05f7b"},"schema_version":"1.0","source":{"id":"1805.03766","kind":"arxiv","version":1}},"canonical_sha256":"8650d373612f140a5b45706215bc6181a6caecec58fea36851572aad96cf40a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8650d373612f140a5b45706215bc6181a6caecec58fea36851572aad96cf40a5","first_computed_at":"2026-05-18T00:16:18.828643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:18.828643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VIKlMMdSQssg9L2fSGdTlnPwitXzeB/KKcXOWY/Ss0UfAqpJhVUpyCub813X7kc04iK1SnzMLSeFqcvitXYFAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:18.829157Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eabf6fceee9d30a59d561122ca2c507790a4b4cdf38aecb43a105b81f3c7e140","sha256:943b7e963aed2b317576a58e257e08a535320b6017bbe88c38738340e2d532d9"],"state_sha256":"941f37f2ee1854a0cd23b77a88fad3c645830e127f8734473d510765a3e61eb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqDcgIYThc4fJJwVrt/jLuY1Y80c3A602uYpd7+SZKDi843qwfpfgmXZz/XD3dtBrKVunsXfBQUZDVjG3g+oCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:44:50.343751Z","bundle_sha256":"a44ba88231d2fa051bf3399551ed30bd8371b80ba4d098450d5cdb2782c9d29a"}}