{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TEEPA5YULDXIZ3D5USJOTD3LTR","short_pith_number":"pith:TEEPA5YU","canonical_record":{"source":{"id":"1908.05731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T19:54:23Z","cross_cats_sorted":[],"title_canon_sha256":"68bd7dc43fce7448d6b9b1492b18a65672096a8fc2ce359409be72dd6ae772f8","abstract_canon_sha256":"3a9a8e79a0c0d8d449f90c652ad108379118645803e0b45b000716f935058de1"},"schema_version":"1.0"},"canonical_sha256":"9908f0771458ee8cec7da492e98f6b9c430494ae3de4e1f6afe9b7c2a774942e","source":{"kind":"arxiv","id":"1908.05731","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05731","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05731v1","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05731","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"TEEPA5YULDXI","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"TEEPA5YULDXIZ3D5","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"TEEPA5YU","created_at":"2026-07-04T23:57:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TEEPA5YULDXIZ3D5USJOTD3LTR","target":"record","payload":{"canonical_record":{"source":{"id":"1908.05731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T19:54:23Z","cross_cats_sorted":[],"title_canon_sha256":"68bd7dc43fce7448d6b9b1492b18a65672096a8fc2ce359409be72dd6ae772f8","abstract_canon_sha256":"3a9a8e79a0c0d8d449f90c652ad108379118645803e0b45b000716f935058de1"},"schema_version":"1.0"},"canonical_sha256":"9908f0771458ee8cec7da492e98f6b9c430494ae3de4e1f6afe9b7c2a774942e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:57:52.741635Z","signature_b64":"9WoRCAU6z2/frXhrcC7trcnwpicqlwUa25lkJ4IFg9XmvxIene5sb01kOSnL9/AuuNnD3Tc7NEj7mzliYhQUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9908f0771458ee8cec7da492e98f6b9c430494ae3de4e1f6afe9b7c2a774942e","last_reissued_at":"2026-07-04T23:57:52.741256Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:57:52.741256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.05731","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":"2026-07-04T23:57:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q/j4meuwDWu7IGjLefAtjo7QGfW5Obq6h2vZN1kgUY+3gZVBX8PR0P7GjWwZVWz3JNO3QXmCX5Zf++3cyYckAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:50:23.743901Z"},"content_sha256":"57ff4b2423de26cf4d3fe749380e974651c784e8b8071ed2bfbe92cff9e3025d","schema_version":"1.0","event_id":"sha256:57ff4b2423de26cf4d3fe749380e974651c784e8b8071ed2bfbe92cff9e3025d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TEEPA5YULDXIZ3D5USJOTD3LTR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simple and Effective Noisy Channel Modeling for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kyra Yee, Michael Auli, Nathan Ng, Yann N. Dauphin","submitted_at":"2019-08-15T19:54:23Z","abstract_excerpt":"Previous work on neural noisy channel modeling relied on latent variable models that incrementally process the source and target sentence. This makes decoding decisions based on partial source prefixes even though the full source is available. We pursue an alternative approach based on standard sequence to sequence models which utilize the entire source. These models perform remarkably well as channel models, even though they have neither been trained on, nor designed to factor over incomplete target sentences. Experiments with neural language models trained on billions of words show that nois"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05731","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/1908.05731/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":"2026-07-04T23:57:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cBVQm2kxK8MQfFbwRoFrUcQl+yYPsxWc/Fu84l/kCGUMerRvzgLYCQWsB/nYaGTT8n9r5xSA3OjuJti0T6bkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:50:23.744534Z"},"content_sha256":"464d74ff0d141c0790d3825b454136669b9949e8131e379ef77665e2273565a7","schema_version":"1.0","event_id":"sha256:464d74ff0d141c0790d3825b454136669b9949e8131e379ef77665e2273565a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TEEPA5YULDXIZ3D5USJOTD3LTR/bundle.json","state_url":"https://pith.science/pith/TEEPA5YULDXIZ3D5USJOTD3LTR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TEEPA5YULDXIZ3D5USJOTD3LTR/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":"2026-08-16T06:50:23Z","links":{"resolver":"https://pith.science/pith/TEEPA5YULDXIZ3D5USJOTD3LTR","bundle":"https://pith.science/pith/TEEPA5YULDXIZ3D5USJOTD3LTR/bundle.json","state":"https://pith.science/pith/TEEPA5YULDXIZ3D5USJOTD3LTR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TEEPA5YULDXIZ3D5USJOTD3LTR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TEEPA5YULDXIZ3D5USJOTD3LTR","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":"3a9a8e79a0c0d8d449f90c652ad108379118645803e0b45b000716f935058de1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T19:54:23Z","title_canon_sha256":"68bd7dc43fce7448d6b9b1492b18a65672096a8fc2ce359409be72dd6ae772f8"},"schema_version":"1.0","source":{"id":"1908.05731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05731","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05731v1","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05731","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"TEEPA5YULDXI","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"TEEPA5YULDXIZ3D5","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"TEEPA5YU","created_at":"2026-07-04T23:57:52Z"}],"graph_snapshots":[{"event_id":"sha256:464d74ff0d141c0790d3825b454136669b9949e8131e379ef77665e2273565a7","target":"graph","created_at":"2026-07-04T23:57:52Z","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/1908.05731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous work on neural noisy channel modeling relied on latent variable models that incrementally process the source and target sentence. This makes decoding decisions based on partial source prefixes even though the full source is available. We pursue an alternative approach based on standard sequence to sequence models which utilize the entire source. These models perform remarkably well as channel models, even though they have neither been trained on, nor designed to factor over incomplete target sentences. Experiments with neural language models trained on billions of words show that nois","authors_text":"Kyra Yee, Michael Auli, Nathan Ng, Yann N. Dauphin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T19:54:23Z","title":"Simple and Effective Noisy Channel Modeling for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05731","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":"sha256:57ff4b2423de26cf4d3fe749380e974651c784e8b8071ed2bfbe92cff9e3025d","target":"record","created_at":"2026-07-04T23:57:52Z","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":"3a9a8e79a0c0d8d449f90c652ad108379118645803e0b45b000716f935058de1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T19:54:23Z","title_canon_sha256":"68bd7dc43fce7448d6b9b1492b18a65672096a8fc2ce359409be72dd6ae772f8"},"schema_version":"1.0","source":{"id":"1908.05731","kind":"arxiv","version":1}},"canonical_sha256":"9908f0771458ee8cec7da492e98f6b9c430494ae3de4e1f6afe9b7c2a774942e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9908f0771458ee8cec7da492e98f6b9c430494ae3de4e1f6afe9b7c2a774942e","first_computed_at":"2026-07-04T23:57:52.741256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:57:52.741256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9WoRCAU6z2/frXhrcC7trcnwpicqlwUa25lkJ4IFg9XmvxIene5sb01kOSnL9/AuuNnD3Tc7NEj7mzliYhQUDQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:57:52.741635Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05731","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57ff4b2423de26cf4d3fe749380e974651c784e8b8071ed2bfbe92cff9e3025d","sha256:464d74ff0d141c0790d3825b454136669b9949e8131e379ef77665e2273565a7"],"state_sha256":"5c8500dea0a537447546201e910c39c63349ea5bd70a39c326896e2af9151e20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGBGcSyqJm/Vs51CQ7r+7cHwiFYd7xPLaFyBfxHWyrLMcy7Esi0zxZty4xB0KGmK4ejZ5uqW/xJvrVGWrXw2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T06:50:23.750352Z","bundle_sha256":"22f5915915e66e2abb7712d221cb490d35a85029e68818b2a0f6ccac7647f887"}}