{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:O7CGRPYDGBYQEUGZY72I6EEKIM","short_pith_number":"pith:O7CGRPYD","canonical_record":{"source":{"id":"1707.09443","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-07-29T00:46:23Z","cross_cats_sorted":[],"title_canon_sha256":"d453e7e23cb873e31bb0c501f664e5ea5c8d1ddf108f8cf24c7f026af91fcb58","abstract_canon_sha256":"e6e94e479509d920f4faa2bfc248220dbee11e6467629604c74322f24c066275"},"schema_version":"1.0"},"canonical_sha256":"77c468bf0330710250d9c7f48f108a433c2c907b21653862d795bd91ee3b5d1e","source":{"kind":"arxiv","id":"1707.09443","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09443","created_at":"2026-05-18T00:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09443v1","created_at":"2026-05-18T00:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09443","created_at":"2026-05-18T00:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"O7CGRPYDGBYQ","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"O7CGRPYDGBYQEUGZ","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"O7CGRPYD","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:O7CGRPYDGBYQEUGZY72I6EEKIM","target":"record","payload":{"canonical_record":{"source":{"id":"1707.09443","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-07-29T00:46:23Z","cross_cats_sorted":[],"title_canon_sha256":"d453e7e23cb873e31bb0c501f664e5ea5c8d1ddf108f8cf24c7f026af91fcb58","abstract_canon_sha256":"e6e94e479509d920f4faa2bfc248220dbee11e6467629604c74322f24c066275"},"schema_version":"1.0"},"canonical_sha256":"77c468bf0330710250d9c7f48f108a433c2c907b21653862d795bd91ee3b5d1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:11.250190Z","signature_b64":"Z9GlR6NVbWclwaQSb99AnUf9N6YQmlNbhNQY9WRJFNeZi4ETk9BtU7+PLQ2g5iT8PuRBQoHY9KB36DWn5cDdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77c468bf0330710250d9c7f48f108a433c2c907b21653862d795bd91ee3b5d1e","last_reissued_at":"2026-05-18T00:39:11.249528Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:11.249528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.09443","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":"2026-05-18T00:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sQH9+8fs5mn4l2ga/Gs9iBiO/c0Xgv4Dtc9AUJFFd0NciAhLjqvfMJ8h32WYSYGbVaXWCRmCiWXQRYBlljv6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:13:08.851632Z"},"content_sha256":"d52139bb28b9986dff8a690f11acb9c45012f8b9a8092a39c22beebe8e5d80be","schema_version":"1.0","event_id":"sha256:d52139bb28b9986dff8a690f11acb9c45012f8b9a8092a39c22beebe8e5d80be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:O7CGRPYDGBYQEUGZY72I6EEKIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bilingual Document Alignment with Latent Semantic Indexing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ulrich Germann","submitted_at":"2017-07-29T00:46:23Z","abstract_excerpt":"We apply cross-lingual Latent Semantic Indexing to the Bilingual Document Alignment Task at WMT16. Reduced-rank singular value decomposition of a bilingual term-document matrix derived from known English/French page pairs in the training data allows us to map monolingual documents into a joint semantic space. Two variants of cosine similarity between the vectors that place each document into the joint semantic space are combined with a measure of string similarity between corresponding URLs to produce 1:1 alignments of English/French web pages in a variety of domains. The system achieves a rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09443","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":"2026-05-18T00:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"naZIJ23R9D7ZFFKA7e0ljWU7wIEniEsPOTvlhwm2LXiDLduIAM4KAiSzN5hdIfyQ7bOo1APfjsC9j/4j3+NnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:13:08.851968Z"},"content_sha256":"2bf71c1047b7860c15f706831db9660a174781641bb4833c9ffb6593dd8119c7","schema_version":"1.0","event_id":"sha256:2bf71c1047b7860c15f706831db9660a174781641bb4833c9ffb6593dd8119c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7CGRPYDGBYQEUGZY72I6EEKIM/bundle.json","state_url":"https://pith.science/pith/O7CGRPYDGBYQEUGZY72I6EEKIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7CGRPYDGBYQEUGZY72I6EEKIM/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":"2026-06-01T17:13:08Z","links":{"resolver":"https://pith.science/pith/O7CGRPYDGBYQEUGZY72I6EEKIM","bundle":"https://pith.science/pith/O7CGRPYDGBYQEUGZY72I6EEKIM/bundle.json","state":"https://pith.science/pith/O7CGRPYDGBYQEUGZY72I6EEKIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7CGRPYDGBYQEUGZY72I6EEKIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:O7CGRPYDGBYQEUGZY72I6EEKIM","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":"e6e94e479509d920f4faa2bfc248220dbee11e6467629604c74322f24c066275","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-07-29T00:46:23Z","title_canon_sha256":"d453e7e23cb873e31bb0c501f664e5ea5c8d1ddf108f8cf24c7f026af91fcb58"},"schema_version":"1.0","source":{"id":"1707.09443","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09443","created_at":"2026-05-18T00:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09443v1","created_at":"2026-05-18T00:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09443","created_at":"2026-05-18T00:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"O7CGRPYDGBYQ","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"O7CGRPYDGBYQEUGZ","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"O7CGRPYD","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:2bf71c1047b7860c15f706831db9660a174781641bb4833c9ffb6593dd8119c7","target":"graph","created_at":"2026-05-18T00:39:11Z","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"},"paper":{"abstract_excerpt":"We apply cross-lingual Latent Semantic Indexing to the Bilingual Document Alignment Task at WMT16. Reduced-rank singular value decomposition of a bilingual term-document matrix derived from known English/French page pairs in the training data allows us to map monolingual documents into a joint semantic space. Two variants of cosine similarity between the vectors that place each document into the joint semantic space are combined with a measure of string similarity between corresponding URLs to produce 1:1 alignments of English/French web pages in a variety of domains. The system achieves a rec","authors_text":"Ulrich Germann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-07-29T00:46:23Z","title":"Bilingual Document Alignment with Latent Semantic Indexing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09443","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:d52139bb28b9986dff8a690f11acb9c45012f8b9a8092a39c22beebe8e5d80be","target":"record","created_at":"2026-05-18T00:39:11Z","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":"e6e94e479509d920f4faa2bfc248220dbee11e6467629604c74322f24c066275","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-07-29T00:46:23Z","title_canon_sha256":"d453e7e23cb873e31bb0c501f664e5ea5c8d1ddf108f8cf24c7f026af91fcb58"},"schema_version":"1.0","source":{"id":"1707.09443","kind":"arxiv","version":1}},"canonical_sha256":"77c468bf0330710250d9c7f48f108a433c2c907b21653862d795bd91ee3b5d1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77c468bf0330710250d9c7f48f108a433c2c907b21653862d795bd91ee3b5d1e","first_computed_at":"2026-05-18T00:39:11.249528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:11.249528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z9GlR6NVbWclwaQSb99AnUf9N6YQmlNbhNQY9WRJFNeZi4ETk9BtU7+PLQ2g5iT8PuRBQoHY9KB36DWn5cDdAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:11.250190Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.09443","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d52139bb28b9986dff8a690f11acb9c45012f8b9a8092a39c22beebe8e5d80be","sha256:2bf71c1047b7860c15f706831db9660a174781641bb4833c9ffb6593dd8119c7"],"state_sha256":"c71b44280e6986c652f3d83dae7b42e1cd3d0656999fe2e3a41ba1500c76b73a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fAx2E8TJ5UfmhBSPldeBjkHTPQvzxpes7eCBY6XKPJJMTNr/UgrEgkewhByGaJ1AbHTYX3f6T4/iiEBLW6DACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:13:08.853897Z","bundle_sha256":"9fa312850af74347f9d17e6b167f33dd8e49edae38fb1aedbf334af18303261b"}}