{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:R2BV3YFUXUDAPXO4OO27W7NHUU","short_pith_number":"pith:R2BV3YFU","canonical_record":{"source":{"id":"1606.02960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-09T13:29:34Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"a09261f425f7a22bec3cf55e86ef4d81dc6933beff7e567e92c5bf94e2dffdd6","abstract_canon_sha256":"a275c437d6a189afb954f6196102ac61a9a2e288a79a21fb4d53781319370073"},"schema_version":"1.0"},"canonical_sha256":"8e835de0b4bd0607dddc73b5fb7da7a52aa38d5e0a786e655591110a949328b1","source":{"kind":"arxiv","id":"1606.02960","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02960","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02960v2","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02960","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"R2BV3YFUXUDA","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"R2BV3YFUXUDAPXO4","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"R2BV3YFU","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:R2BV3YFUXUDAPXO4OO27W7NHUU","target":"record","payload":{"canonical_record":{"source":{"id":"1606.02960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-09T13:29:34Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"a09261f425f7a22bec3cf55e86ef4d81dc6933beff7e567e92c5bf94e2dffdd6","abstract_canon_sha256":"a275c437d6a189afb954f6196102ac61a9a2e288a79a21fb4d53781319370073"},"schema_version":"1.0"},"canonical_sha256":"8e835de0b4bd0607dddc73b5fb7da7a52aa38d5e0a786e655591110a949328b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:41.921534Z","signature_b64":"wfuDHfomSeNdM9n51xlY4QkcCmYasClq8OpDWR3n/O3Q3rrL74/lau2Y7wQfZlU8OzkhEOq4ST9rfRLDqty6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e835de0b4bd0607dddc73b5fb7da7a52aa38d5e0a786e655591110a949328b1","last_reissued_at":"2026-05-18T00:59:41.920974Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:41.920974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.02960","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:59:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvDl/yJ55tq1Lxry2Q20Zn4/tGWdD0dW8PYr0qp9uINheNDw1OqLDaVyQYE01qrPE1eBbvUFfxHiMJG8VXG4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T05:07:26.333425Z"},"content_sha256":"0984d4c2cc900e4f10f84d7c9c19317f75078723ab41a524267595bad146064b","schema_version":"1.0","event_id":"sha256:0984d4c2cc900e4f10f84d7c9c19317f75078723ab41a524267595bad146064b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:R2BV3YFUXUDAPXO4OO27W7NHUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sequence-to-Sequence Learning as Beam-Search Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Sam Wiseman","submitted_at":"2016-06-09T13:29:34Z","abstract_excerpt":"Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work, we introduce a model and beam-search training scheme, based on the work of Daume III and Marcu (2005), that extends seq2seq to learn global sequence scores. This structured approach avoids classical biases associated with local training and unifies the training loss with the te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02960","kind":"arxiv","version":2},"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":"2026-05-18T00:59:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TeWmUWBaMAnQydnirkxFaQ/aBGyk9KkmNHm0y5ZIPmIQh8dYIAEmUDc/0aq1DilLcOgPEDeCpcW4BRYv78t2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T05:07:26.334077Z"},"content_sha256":"6bae7e27640ca67bfed88a8dbc6e5454d7d6028e24e47c1495d773bfac7342f6","schema_version":"1.0","event_id":"sha256:6bae7e27640ca67bfed88a8dbc6e5454d7d6028e24e47c1495d773bfac7342f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2BV3YFUXUDAPXO4OO27W7NHUU/bundle.json","state_url":"https://pith.science/pith/R2BV3YFUXUDAPXO4OO27W7NHUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2BV3YFUXUDAPXO4OO27W7NHUU/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":"2026-05-25T05:07:26Z","links":{"resolver":"https://pith.science/pith/R2BV3YFUXUDAPXO4OO27W7NHUU","bundle":"https://pith.science/pith/R2BV3YFUXUDAPXO4OO27W7NHUU/bundle.json","state":"https://pith.science/pith/R2BV3YFUXUDAPXO4OO27W7NHUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2BV3YFUXUDAPXO4OO27W7NHUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:R2BV3YFUXUDAPXO4OO27W7NHUU","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":"a275c437d6a189afb954f6196102ac61a9a2e288a79a21fb4d53781319370073","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-09T13:29:34Z","title_canon_sha256":"a09261f425f7a22bec3cf55e86ef4d81dc6933beff7e567e92c5bf94e2dffdd6"},"schema_version":"1.0","source":{"id":"1606.02960","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02960","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02960v2","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02960","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"R2BV3YFUXUDA","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"R2BV3YFUXUDAPXO4","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"R2BV3YFU","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:6bae7e27640ca67bfed88a8dbc6e5454d7d6028e24e47c1495d773bfac7342f6","target":"graph","created_at":"2026-05-18T00:59:41Z","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":"Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work, we introduce a model and beam-search training scheme, based on the work of Daume III and Marcu (2005), that extends seq2seq to learn global sequence scores. This structured approach avoids classical biases associated with local training and unifies the training loss with the te","authors_text":"Alexander M. Rush, Sam Wiseman","cross_cats":["cs.LG","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-09T13:29:34Z","title":"Sequence-to-Sequence Learning as Beam-Search Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02960","kind":"arxiv","version":2},"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":"sha256:0984d4c2cc900e4f10f84d7c9c19317f75078723ab41a524267595bad146064b","target":"record","created_at":"2026-05-18T00:59:41Z","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":"a275c437d6a189afb954f6196102ac61a9a2e288a79a21fb4d53781319370073","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-09T13:29:34Z","title_canon_sha256":"a09261f425f7a22bec3cf55e86ef4d81dc6933beff7e567e92c5bf94e2dffdd6"},"schema_version":"1.0","source":{"id":"1606.02960","kind":"arxiv","version":2}},"canonical_sha256":"8e835de0b4bd0607dddc73b5fb7da7a52aa38d5e0a786e655591110a949328b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e835de0b4bd0607dddc73b5fb7da7a52aa38d5e0a786e655591110a949328b1","first_computed_at":"2026-05-18T00:59:41.920974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:59:41.920974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wfuDHfomSeNdM9n51xlY4QkcCmYasClq8OpDWR3n/O3Q3rrL74/lau2Y7wQfZlU8OzkhEOq4ST9rfRLDqty6AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:59:41.921534Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.02960","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0984d4c2cc900e4f10f84d7c9c19317f75078723ab41a524267595bad146064b","sha256:6bae7e27640ca67bfed88a8dbc6e5454d7d6028e24e47c1495d773bfac7342f6"],"state_sha256":"cac1ae48136c26408d43dd97f6399d71104e016677e3aca4f84882a0616c7e82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WbyvYKwp3J9Nt3Veay9kUHqhGFYe7zZGoLMCmFDx/WUid0EJg7fqOvc8OX+S9FP2ZfJ613Vql0sxHjX38LD5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T05:07:26.337471Z","bundle_sha256":"d1f620a2a3c1590339a594ae16f1de024096965d241b3e8b0e1f4b86fadf82ed"}}