{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TUYHKAFRPV3QXWLIFSRPT74LXB","short_pith_number":"pith:TUYHKAFR","canonical_record":{"source":{"id":"2004.08728","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-18T23:10:36Z","cross_cats_sorted":[],"title_canon_sha256":"ef21ebe84f31bcba7149937ef4127e5e198b3c8b51b13791484d915acaaace17","abstract_canon_sha256":"aa0f1581817aeb9839659cd93ceba9f38c6186eea8c34fd78a1afa8d562d6b58"},"schema_version":"1.0"},"canonical_sha256":"9d307500b17d770bd9682ca2f9ff8bb8573fffbe008fc4fe3f6589b1f41afe4c","source":{"kind":"arxiv","id":"2004.08728","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.08728","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"arxiv_version","alias_value":"2004.08728v4","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08728","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_12","alias_value":"TUYHKAFRPV3Q","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_16","alias_value":"TUYHKAFRPV3QXWLI","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_8","alias_value":"TUYHKAFR","created_at":"2026-07-05T02:32:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TUYHKAFRPV3QXWLIFSRPT74LXB","target":"record","payload":{"canonical_record":{"source":{"id":"2004.08728","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-18T23:10:36Z","cross_cats_sorted":[],"title_canon_sha256":"ef21ebe84f31bcba7149937ef4127e5e198b3c8b51b13791484d915acaaace17","abstract_canon_sha256":"aa0f1581817aeb9839659cd93ceba9f38c6186eea8c34fd78a1afa8d562d6b58"},"schema_version":"1.0"},"canonical_sha256":"9d307500b17d770bd9682ca2f9ff8bb8573fffbe008fc4fe3f6589b1f41afe4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:32.037431Z","signature_b64":"PnMwuQXQZ6jHOOd/EVRdRBeKbZ5gJMyyH8pesnLcfrEn6e5jc5NemBIXXYuLwL0qwDOD3lo4JZ0H2+0FMZh+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d307500b17d770bd9682ca2f9ff8bb8573fffbe008fc4fe3f6589b1f41afe4c","last_reissued_at":"2026-07-05T02:32:32.036926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:32.036926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.08728","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:32:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3eBQ2hHZVRokoJwUXh80vM1FTCqq9Qs7pPIPEqSegipigg/J7gV6UM0mS5FAuPZ4YSzmkpoPeVnKFjw0w6WqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:12:59.624802Z"},"content_sha256":"2aa44cb747cb497a6b013fd0674e57e164dd939ada6be6242eb248659f1e0624","schema_version":"1.0","event_id":"sha256:2aa44cb747cb497a6b013fd0674e57e164dd939ada6be6242eb248659f1e0624"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TUYHKAFRPV3QXWLIFSRPT74LXB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fran\\c{c}ois Yvon, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Philipp Dufter","submitted_at":"2020-04-18T23:10:36Z","abstract_excerpt":"Word alignments are useful for tasks like statistical and neural machine translation (NMT) and cross-lingual annotation projection. Statistical word aligners perform well, as do methods that extract alignments jointly with translations in NMT. However, most approaches require parallel training data, and quality decreases as less training data is available. We propose word alignment methods that require no parallel data. The key idea is to leverage multilingual word embeddings, both static and contextualized, for word alignment. Our multilingual embeddings are created from monolingual data only"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08728","kind":"arxiv","version":4},"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/2004.08728/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":"2026-07-05T02:32:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8I6imSfgxWefnU3ItfJ8eUXhEVLkNJoLMUE13kOLZ8YJMfjMu+q02bipgReAYXii+4Nsvee5ezA82n5O/Fq0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:12:59.625666Z"},"content_sha256":"2f0825dd87d4126321468ebdb63a4c1fed245aedeb05e9d4873fd8e90f391f87","schema_version":"1.0","event_id":"sha256:2f0825dd87d4126321468ebdb63a4c1fed245aedeb05e9d4873fd8e90f391f87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUYHKAFRPV3QXWLIFSRPT74LXB/bundle.json","state_url":"https://pith.science/pith/TUYHKAFRPV3QXWLIFSRPT74LXB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUYHKAFRPV3QXWLIFSRPT74LXB/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":"2026-08-09T12:12:59Z","links":{"resolver":"https://pith.science/pith/TUYHKAFRPV3QXWLIFSRPT74LXB","bundle":"https://pith.science/pith/TUYHKAFRPV3QXWLIFSRPT74LXB/bundle.json","state":"https://pith.science/pith/TUYHKAFRPV3QXWLIFSRPT74LXB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUYHKAFRPV3QXWLIFSRPT74LXB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TUYHKAFRPV3QXWLIFSRPT74LXB","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":"aa0f1581817aeb9839659cd93ceba9f38c6186eea8c34fd78a1afa8d562d6b58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-18T23:10:36Z","title_canon_sha256":"ef21ebe84f31bcba7149937ef4127e5e198b3c8b51b13791484d915acaaace17"},"schema_version":"1.0","source":{"id":"2004.08728","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.08728","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"arxiv_version","alias_value":"2004.08728v4","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08728","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_12","alias_value":"TUYHKAFRPV3Q","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_16","alias_value":"TUYHKAFRPV3QXWLI","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_8","alias_value":"TUYHKAFR","created_at":"2026-07-05T02:32:32Z"}],"graph_snapshots":[{"event_id":"sha256:2f0825dd87d4126321468ebdb63a4c1fed245aedeb05e9d4873fd8e90f391f87","target":"graph","created_at":"2026-07-05T02:32:32Z","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/2004.08728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word alignments are useful for tasks like statistical and neural machine translation (NMT) and cross-lingual annotation projection. Statistical word aligners perform well, as do methods that extract alignments jointly with translations in NMT. However, most approaches require parallel training data, and quality decreases as less training data is available. We propose word alignment methods that require no parallel data. The key idea is to leverage multilingual word embeddings, both static and contextualized, for word alignment. Our multilingual embeddings are created from monolingual data only","authors_text":"Fran\\c{c}ois Yvon, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Philipp Dufter","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-18T23:10:36Z","title":"SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08728","kind":"arxiv","version":4},"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":"sha256:2aa44cb747cb497a6b013fd0674e57e164dd939ada6be6242eb248659f1e0624","target":"record","created_at":"2026-07-05T02:32:32Z","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":"aa0f1581817aeb9839659cd93ceba9f38c6186eea8c34fd78a1afa8d562d6b58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-18T23:10:36Z","title_canon_sha256":"ef21ebe84f31bcba7149937ef4127e5e198b3c8b51b13791484d915acaaace17"},"schema_version":"1.0","source":{"id":"2004.08728","kind":"arxiv","version":4}},"canonical_sha256":"9d307500b17d770bd9682ca2f9ff8bb8573fffbe008fc4fe3f6589b1f41afe4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d307500b17d770bd9682ca2f9ff8bb8573fffbe008fc4fe3f6589b1f41afe4c","first_computed_at":"2026-07-05T02:32:32.036926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:32.036926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PnMwuQXQZ6jHOOd/EVRdRBeKbZ5gJMyyH8pesnLcfrEn6e5jc5NemBIXXYuLwL0qwDOD3lo4JZ0H2+0FMZh+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:32.037431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.08728","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2aa44cb747cb497a6b013fd0674e57e164dd939ada6be6242eb248659f1e0624","sha256:2f0825dd87d4126321468ebdb63a4c1fed245aedeb05e9d4873fd8e90f391f87"],"state_sha256":"3321f9be18880b331c934f3b5f2425468531ff54c6d74b3f5ba7f7bb224a2702"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mW+P0L5FaDBYwgJV1OV4UV5vhaJrcNTEW6l6E1RE7g1LmuGO/xEGqijobzzVeWZBNM6jJhTkSHW9lUrezdI4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:12:59.631069Z","bundle_sha256":"867a999227ef32a82057ce3359f68760a93ca8accae938c2a40e7c25bab75659"}}