{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PRYBQJDIKLDNETG55YIJIDXELI","short_pith_number":"pith:PRYBQJDI","canonical_record":{"source":{"id":"1702.02429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T13:56:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"39cec7f339b57d4bc9c0d764f99b898675bb10758d5de2ce3a6672686e5b561f","abstract_canon_sha256":"9a7a5707cffc7f3b359ff5fd1b8042e65bfa1f22f21dc22db9eaa743ed00404e"},"schema_version":"1.0"},"canonical_sha256":"7c7018246852c6d24cddee10940ee45a29eb6774e29615b8419add253f9befde","source":{"kind":"arxiv","id":"1702.02429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02429","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02429v1","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02429","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"PRYBQJDIKLDN","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PRYBQJDIKLDNETG5","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PRYBQJDI","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PRYBQJDIKLDNETG55YIJIDXELI","target":"record","payload":{"canonical_record":{"source":{"id":"1702.02429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T13:56:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"39cec7f339b57d4bc9c0d764f99b898675bb10758d5de2ce3a6672686e5b561f","abstract_canon_sha256":"9a7a5707cffc7f3b359ff5fd1b8042e65bfa1f22f21dc22db9eaa743ed00404e"},"schema_version":"1.0"},"canonical_sha256":"7c7018246852c6d24cddee10940ee45a29eb6774e29615b8419add253f9befde","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:05.956922Z","signature_b64":"7/hrDnejln82+yIHvOPmoZC/pVOD1os7MlDNlKHkCvZFGD8l0lILc2azG2EDy2to9Nt4OmYgVO/7qVqJ7CUOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c7018246852c6d24cddee10940ee45a29eb6774e29615b8419add253f9befde","last_reissued_at":"2026-05-18T00:51:05.956349Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:05.956349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.02429","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":"2026-05-18T00:51:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9RBpogafpDa1LiaSDC3vo5Fng9Wu5II8pF58xhDrTuCMwTuP0/1erspTZ52VQlSaJIgUwlOYod8vQvMwQIxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:59:33.005990Z"},"content_sha256":"07fde9a5f3f95f11984e924c3f33c5143909ba072847494e8a4ec3ac10554703","schema_version":"1.0","event_id":"sha256:07fde9a5f3f95f11984e924c3f33c5143909ba072847494e8a4ec3ac10554703"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PRYBQJDIKLDNETG55YIJIDXELI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trainable Greedy Decoding for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiatao Gu, Kyunghyun Cho, Victor O.K. Li","submitted_at":"2017-02-08T13:56:16Z","abstract_excerpt":"Recent research in neural machine translation has largely focused on two aspects; neural network architectures and end-to-end learning algorithms. The problem of decoding, however, has received relatively little attention from the research community. In this paper, we solely focus on the problem of decoding given a trained neural machine translation model. Instead of trying to build a new decoding algorithm for any specific decoding objective, we propose the idea of trainable decoding algorithm in which we train a decoding algorithm to find a translation that maximizes an arbitrary decoding ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02429","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":"2026-05-18T00:51:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mtn3p1OEaXxWUPLscnQbp/ZVCRfUDHo2jdV5qEfEg+T+zblDww5iqm5iqJW7ScwoVNr4Ad3EBk8nIvwBNPiAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:59:33.006619Z"},"content_sha256":"68e8eed5425aaea636c6c77643713c0cc21194a8751730896de40eb76b205bfb","schema_version":"1.0","event_id":"sha256:68e8eed5425aaea636c6c77643713c0cc21194a8751730896de40eb76b205bfb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRYBQJDIKLDNETG55YIJIDXELI/bundle.json","state_url":"https://pith.science/pith/PRYBQJDIKLDNETG55YIJIDXELI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRYBQJDIKLDNETG55YIJIDXELI/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":"2026-05-26T14:59:33Z","links":{"resolver":"https://pith.science/pith/PRYBQJDIKLDNETG55YIJIDXELI","bundle":"https://pith.science/pith/PRYBQJDIKLDNETG55YIJIDXELI/bundle.json","state":"https://pith.science/pith/PRYBQJDIKLDNETG55YIJIDXELI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRYBQJDIKLDNETG55YIJIDXELI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PRYBQJDIKLDNETG55YIJIDXELI","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":"9a7a5707cffc7f3b359ff5fd1b8042e65bfa1f22f21dc22db9eaa743ed00404e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T13:56:16Z","title_canon_sha256":"39cec7f339b57d4bc9c0d764f99b898675bb10758d5de2ce3a6672686e5b561f"},"schema_version":"1.0","source":{"id":"1702.02429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02429","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02429v1","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02429","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"PRYBQJDIKLDN","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PRYBQJDIKLDNETG5","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PRYBQJDI","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:68e8eed5425aaea636c6c77643713c0cc21194a8751730896de40eb76b205bfb","target":"graph","created_at":"2026-05-18T00:51:05Z","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":"Recent research in neural machine translation has largely focused on two aspects; neural network architectures and end-to-end learning algorithms. The problem of decoding, however, has received relatively little attention from the research community. In this paper, we solely focus on the problem of decoding given a trained neural machine translation model. Instead of trying to build a new decoding algorithm for any specific decoding objective, we propose the idea of trainable decoding algorithm in which we train a decoding algorithm to find a translation that maximizes an arbitrary decoding ob","authors_text":"Jiatao Gu, Kyunghyun Cho, Victor O.K. Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T13:56:16Z","title":"Trainable Greedy Decoding for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02429","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":"sha256:07fde9a5f3f95f11984e924c3f33c5143909ba072847494e8a4ec3ac10554703","target":"record","created_at":"2026-05-18T00:51:05Z","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":"9a7a5707cffc7f3b359ff5fd1b8042e65bfa1f22f21dc22db9eaa743ed00404e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T13:56:16Z","title_canon_sha256":"39cec7f339b57d4bc9c0d764f99b898675bb10758d5de2ce3a6672686e5b561f"},"schema_version":"1.0","source":{"id":"1702.02429","kind":"arxiv","version":1}},"canonical_sha256":"7c7018246852c6d24cddee10940ee45a29eb6774e29615b8419add253f9befde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c7018246852c6d24cddee10940ee45a29eb6774e29615b8419add253f9befde","first_computed_at":"2026-05-18T00:51:05.956349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:05.956349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7/hrDnejln82+yIHvOPmoZC/pVOD1os7MlDNlKHkCvZFGD8l0lILc2azG2EDy2to9Nt4OmYgVO/7qVqJ7CUOAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:05.956922Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.02429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07fde9a5f3f95f11984e924c3f33c5143909ba072847494e8a4ec3ac10554703","sha256:68e8eed5425aaea636c6c77643713c0cc21194a8751730896de40eb76b205bfb"],"state_sha256":"00c7cf4e7fb9033759eb7f581c32c2c7a1bfb7c5ae861444cd0605a6119511d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3i3X/luUwDOdHp0W2TR2UhE2TpkTF85Rjt5EXm7+51I62toZFX/wGtWgbDQoH8DE2OAK604UqFP524sxIhSCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T14:59:33.010494Z","bundle_sha256":"2db26ee6f0222c3697751f1cac178b4221667105b7f30bd4d9d6ed2cb47ca649"}}