{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H4AL4DY56JDS3IQU2NFN6FVBXS","short_pith_number":"pith:H4AL4DY5","canonical_record":{"source":{"id":"2101.08231","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-20T17:54:47Z","cross_cats_sorted":[],"title_canon_sha256":"2ff1440a2192246e9e292356dacda40327969c70653473bc787fdb5e6de06a1c","abstract_canon_sha256":"67fe564029698f05a4c8fb0bcb6e0838b9a11512235f842a85bafeb4856ff323"},"schema_version":"1.0"},"canonical_sha256":"3f00be0f1df2472da214d34adf16a1bc9d155095a3f77d91728f25a6d892e09b","source":{"kind":"arxiv","id":"2101.08231","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08231","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08231v4","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08231","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"H4AL4DY56JDS","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"H4AL4DY56JDS3IQU","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"H4AL4DY5","created_at":"2026-07-05T03:05:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H4AL4DY56JDS3IQU2NFN6FVBXS","target":"record","payload":{"canonical_record":{"source":{"id":"2101.08231","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-20T17:54:47Z","cross_cats_sorted":[],"title_canon_sha256":"2ff1440a2192246e9e292356dacda40327969c70653473bc787fdb5e6de06a1c","abstract_canon_sha256":"67fe564029698f05a4c8fb0bcb6e0838b9a11512235f842a85bafeb4856ff323"},"schema_version":"1.0"},"canonical_sha256":"3f00be0f1df2472da214d34adf16a1bc9d155095a3f77d91728f25a6d892e09b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:11.577173Z","signature_b64":"wH6ZTsFASFhs02zdhcGkJohn82bTCInbAgQ6+m6zvNrSYCebW6058vCaMtbG+HDL7bmLp0qjueWBwVH+Fg2tDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f00be0f1df2472da214d34adf16a1bc9d155095a3f77d91728f25a6d892e09b","last_reissued_at":"2026-07-05T03:05:11.576723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:11.576723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.08231","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":"2026-07-05T03:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/RRA4bFoFFQQH3jxAOLSpth4pI0eBgGb69h9yM8iuitpR3Y9dN07RG5cPw8SBZ0DP96ewU/D/nI9DqJR4xa0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:32:26.425844Z"},"content_sha256":"27b99b2405cb9e7faa51f4960e0ba59ffb92ef2dde2b28097dbad1aa9a4371d1","schema_version":"1.0","event_id":"sha256:27b99b2405cb9e7faa51f4960e0ba59ffb92ef2dde2b28097dbad1aa9a4371d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H4AL4DY56JDS3IQU2NFN6FVBXS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Zi-Yi Dou","submitted_at":"2021-01-20T17:54:47Z","abstract_excerpt":"Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great majority of past work on word alignment has worked by performing unsupervised learning on parallel texts. Recently, however, other work has demonstrated that pre-trained contextualized word embeddings derived from multilingually trained language models (LMs) prove an attractive alternative, achieving competitive results on the word alignment task even in the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08231","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/2101.08231/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":"2026-07-05T03:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"McWYlGa9ZGnf0is50N5QK+FzRnSgRE5w6OHzyg5j5/8tkqvE2zDuCyiVxhRL4KnvK7jqt1v7qbl73cAgC+7zAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:32:26.426546Z"},"content_sha256":"300b7afd53c7c6d813366993bf02c4b99737bf091eba3e3ce646b08a67f11e2e","schema_version":"1.0","event_id":"sha256:300b7afd53c7c6d813366993bf02c4b99737bf091eba3e3ce646b08a67f11e2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H4AL4DY56JDS3IQU2NFN6FVBXS/bundle.json","state_url":"https://pith.science/pith/H4AL4DY56JDS3IQU2NFN6FVBXS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H4AL4DY56JDS3IQU2NFN6FVBXS/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":"2026-08-19T19:32:26Z","links":{"resolver":"https://pith.science/pith/H4AL4DY56JDS3IQU2NFN6FVBXS","bundle":"https://pith.science/pith/H4AL4DY56JDS3IQU2NFN6FVBXS/bundle.json","state":"https://pith.science/pith/H4AL4DY56JDS3IQU2NFN6FVBXS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H4AL4DY56JDS3IQU2NFN6FVBXS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H4AL4DY56JDS3IQU2NFN6FVBXS","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":"67fe564029698f05a4c8fb0bcb6e0838b9a11512235f842a85bafeb4856ff323","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-20T17:54:47Z","title_canon_sha256":"2ff1440a2192246e9e292356dacda40327969c70653473bc787fdb5e6de06a1c"},"schema_version":"1.0","source":{"id":"2101.08231","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08231","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08231v4","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08231","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"H4AL4DY56JDS","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"H4AL4DY56JDS3IQU","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"H4AL4DY5","created_at":"2026-07-05T03:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:300b7afd53c7c6d813366993bf02c4b99737bf091eba3e3ce646b08a67f11e2e","target":"graph","created_at":"2026-07-05T03:05:11Z","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/2101.08231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great majority of past work on word alignment has worked by performing unsupervised learning on parallel texts. Recently, however, other work has demonstrated that pre-trained contextualized word embeddings derived from multilingually trained language models (LMs) prove an attractive alternative, achieving competitive results on the word alignment task even in the a","authors_text":"Graham Neubig, Zi-Yi Dou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-20T17:54:47Z","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08231","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":"sha256:27b99b2405cb9e7faa51f4960e0ba59ffb92ef2dde2b28097dbad1aa9a4371d1","target":"record","created_at":"2026-07-05T03:05:11Z","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":"67fe564029698f05a4c8fb0bcb6e0838b9a11512235f842a85bafeb4856ff323","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-20T17:54:47Z","title_canon_sha256":"2ff1440a2192246e9e292356dacda40327969c70653473bc787fdb5e6de06a1c"},"schema_version":"1.0","source":{"id":"2101.08231","kind":"arxiv","version":4}},"canonical_sha256":"3f00be0f1df2472da214d34adf16a1bc9d155095a3f77d91728f25a6d892e09b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f00be0f1df2472da214d34adf16a1bc9d155095a3f77d91728f25a6d892e09b","first_computed_at":"2026-07-05T03:05:11.576723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:11.576723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wH6ZTsFASFhs02zdhcGkJohn82bTCInbAgQ6+m6zvNrSYCebW6058vCaMtbG+HDL7bmLp0qjueWBwVH+Fg2tDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:11.577173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.08231","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27b99b2405cb9e7faa51f4960e0ba59ffb92ef2dde2b28097dbad1aa9a4371d1","sha256:300b7afd53c7c6d813366993bf02c4b99737bf091eba3e3ce646b08a67f11e2e"],"state_sha256":"5d06a8be816a312053864f95442bda5b557bd3642b69bd501583022a125e6874"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RX+VPNdcvdoot/QJOgVt8g0HxxYN1L7djDNIhw1kfAfT9/4NWDsahDemEQq2q7zHvvyoQxOk+/ZVQUNp9RdvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:32:26.432202Z","bundle_sha256":"0be27f216f8da93711cf3fe0459ddc8c26190ac8fc1b3ed20b5392c4093b0820"}}