{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JMM6WYRDNLFG7NHPTYAYRKQC4D","short_pith_number":"pith:JMM6WYRD","canonical_record":{"source":{"id":"1909.02074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T19:54:06Z","cross_cats_sorted":[],"title_canon_sha256":"ab2724eb6e6950bf31223211c6059be6af84d07fee4e77a97a9737b7a4dbe0dc","abstract_canon_sha256":"4f4f56dad1fd656fe51297ab8c85ced68f64f0ef1fad1a8ff29fd36ec36ca2f4"},"schema_version":"1.0"},"canonical_sha256":"4b19eb62236aca6fb4ef9e0188aa02e0d4f0343871390c50c633ffa7ee574c23","source":{"kind":"arxiv","id":"1909.02074","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02074","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02074v1","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02074","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"JMM6WYRDNLFG","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"JMM6WYRDNLFG7NHP","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"JMM6WYRD","created_at":"2026-07-05T00:02:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JMM6WYRDNLFG7NHPTYAYRKQC4D","target":"record","payload":{"canonical_record":{"source":{"id":"1909.02074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T19:54:06Z","cross_cats_sorted":[],"title_canon_sha256":"ab2724eb6e6950bf31223211c6059be6af84d07fee4e77a97a9737b7a4dbe0dc","abstract_canon_sha256":"4f4f56dad1fd656fe51297ab8c85ced68f64f0ef1fad1a8ff29fd36ec36ca2f4"},"schema_version":"1.0"},"canonical_sha256":"4b19eb62236aca6fb4ef9e0188aa02e0d4f0343871390c50c633ffa7ee574c23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:30.023386Z","signature_b64":"IEy3lvKHHEPB7eYuprf/dJeTg6lGcvRMQYfBZsXdQm7xZAc1hLfn6iJVmcP9sAo5W5i2twrkBBQ10y3QAs9FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b19eb62236aca6fb4ef9e0188aa02e0d4f0343871390c50c633ffa7ee574c23","last_reissued_at":"2026-07-05T00:02:30.022895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:30.022895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.02074","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":"2026-07-05T00:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V7hghZNUnonGZNDVD5zW+PhrymXeDTHUfHuZU3ZVfxMkibxTPHRMuC3KsSi3Z0jAd05KbMptgH5bZTS0ptlyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:43:10.510446Z"},"content_sha256":"06bb1588f2451fc484e9a0f39314245084bc78ab271b5f23f7b79e375b8cb493","schema_version":"1.0","event_id":"sha256:06bb1588f2451fc484e9a0f39314245084bc78ab271b5f23f7b79e375b8cb493"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JMM6WYRDNLFG7NHPTYAYRKQC4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jointly Learning to Align and Translate with Transformer Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Matthias Paulik, Sarthak Garg, Stephan Peitz, Udhyakumar Nallasamy","submitted_at":"2019-09-04T19:54:06Z","abstract_excerpt":"The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches. However, on the closely related task of word alignment, traditional statistical word alignment models often remain the go-to solution. In this paper, we present an approach to train a Transformer model to produce both accurate translations and alignments. We extract discrete alignments from the attention probabilities learnt during regular neural machine translation model training and leverage them in a multi-task framework to opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02074","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/1909.02074/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":"2026-07-05T00:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SCMHqBUZdec6YqrJ5IDRDG74FTu2A158O0ab4Tu0m7VSZMbeQCIST2fRRi0LPCrevSkRThqDa7oJG4k/YeYiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:43:10.510812Z"},"content_sha256":"bc784ba0816c4330e07de50c5568bc919e35507a3850891f64ba3d75f9ea6407","schema_version":"1.0","event_id":"sha256:bc784ba0816c4330e07de50c5568bc919e35507a3850891f64ba3d75f9ea6407"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMM6WYRDNLFG7NHPTYAYRKQC4D/bundle.json","state_url":"https://pith.science/pith/JMM6WYRDNLFG7NHPTYAYRKQC4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMM6WYRDNLFG7NHPTYAYRKQC4D/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":"2026-07-07T08:43:10Z","links":{"resolver":"https://pith.science/pith/JMM6WYRDNLFG7NHPTYAYRKQC4D","bundle":"https://pith.science/pith/JMM6WYRDNLFG7NHPTYAYRKQC4D/bundle.json","state":"https://pith.science/pith/JMM6WYRDNLFG7NHPTYAYRKQC4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMM6WYRDNLFG7NHPTYAYRKQC4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JMM6WYRDNLFG7NHPTYAYRKQC4D","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":"4f4f56dad1fd656fe51297ab8c85ced68f64f0ef1fad1a8ff29fd36ec36ca2f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T19:54:06Z","title_canon_sha256":"ab2724eb6e6950bf31223211c6059be6af84d07fee4e77a97a9737b7a4dbe0dc"},"schema_version":"1.0","source":{"id":"1909.02074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02074","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02074v1","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02074","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"JMM6WYRDNLFG","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"JMM6WYRDNLFG7NHP","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"JMM6WYRD","created_at":"2026-07-05T00:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:bc784ba0816c4330e07de50c5568bc919e35507a3850891f64ba3d75f9ea6407","target":"graph","created_at":"2026-07-05T00:02:30Z","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/1909.02074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches. However, on the closely related task of word alignment, traditional statistical word alignment models often remain the go-to solution. In this paper, we present an approach to train a Transformer model to produce both accurate translations and alignments. We extract discrete alignments from the attention probabilities learnt during regular neural machine translation model training and leverage them in a multi-task framework to opt","authors_text":"Matthias Paulik, Sarthak Garg, Stephan Peitz, Udhyakumar Nallasamy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T19:54:06Z","title":"Jointly Learning to Align and Translate with Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02074","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":"sha256:06bb1588f2451fc484e9a0f39314245084bc78ab271b5f23f7b79e375b8cb493","target":"record","created_at":"2026-07-05T00:02:30Z","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":"4f4f56dad1fd656fe51297ab8c85ced68f64f0ef1fad1a8ff29fd36ec36ca2f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T19:54:06Z","title_canon_sha256":"ab2724eb6e6950bf31223211c6059be6af84d07fee4e77a97a9737b7a4dbe0dc"},"schema_version":"1.0","source":{"id":"1909.02074","kind":"arxiv","version":1}},"canonical_sha256":"4b19eb62236aca6fb4ef9e0188aa02e0d4f0343871390c50c633ffa7ee574c23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b19eb62236aca6fb4ef9e0188aa02e0d4f0343871390c50c633ffa7ee574c23","first_computed_at":"2026-07-05T00:02:30.022895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:30.022895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IEy3lvKHHEPB7eYuprf/dJeTg6lGcvRMQYfBZsXdQm7xZAc1hLfn6iJVmcP9sAo5W5i2twrkBBQ10y3QAs9FBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:30.023386Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06bb1588f2451fc484e9a0f39314245084bc78ab271b5f23f7b79e375b8cb493","sha256:bc784ba0816c4330e07de50c5568bc919e35507a3850891f64ba3d75f9ea6407"],"state_sha256":"20ab408f02dc441021eb873886ffcbc3acbb6772002a124e1a0d0692e88254b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C7GK5mqdGf2k6XkC2fPI5iNMmcRDqueE6gd4nUPo4iDkoCfWFQBrqp98xosje4CwhNUcefg6QZSkBLT58hK3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:43:10.512744Z","bundle_sha256":"49b86a7619d3f73428e5aeda8a1b217d0eb3e55847be6e96f5df663037609695"}}