{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZDOGVWXIS532KJY7AY25XN3EFI","short_pith_number":"pith:ZDOGVWXI","canonical_record":{"source":{"id":"2306.05644","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T03:11:42Z","cross_cats_sorted":[],"title_canon_sha256":"8223dc1514aae3d0db8a14ac5d09721e718ecf1fa4257db26e78852c3773e950","abstract_canon_sha256":"f070374bc2fa75e0ac71d077a62de394c1371e899b4ece9f79152ee71facc95b"},"schema_version":"1.0"},"canonical_sha256":"c8dc6adae89777a5271f0635dbb7642a2487464170de365185522cadbf513833","source":{"kind":"arxiv","id":"2306.05644","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05644","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05644v2","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05644","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZDOGVWXIS532","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZDOGVWXIS532KJY7","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZDOGVWXI","created_at":"2026-07-05T07:02:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZDOGVWXIS532KJY7AY25XN3EFI","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05644","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T03:11:42Z","cross_cats_sorted":[],"title_canon_sha256":"8223dc1514aae3d0db8a14ac5d09721e718ecf1fa4257db26e78852c3773e950","abstract_canon_sha256":"f070374bc2fa75e0ac71d077a62de394c1371e899b4ece9f79152ee71facc95b"},"schema_version":"1.0"},"canonical_sha256":"c8dc6adae89777a5271f0635dbb7642a2487464170de365185522cadbf513833","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:30.075717Z","signature_b64":"R/YQmzzxhCRg4yfAHYFConskzhmm+RIK0aAEu7HgDObQbv0glLtr9V9llg0UVPvawYbZo6QKf131wvkNgOAFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8dc6adae89777a5271f0635dbb7642a2487464170de365185522cadbf513833","last_reissued_at":"2026-07-05T07:02:30.075306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:30.075306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05644","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mCT8oV9a5fKVOVBFa+k73hIZVoeFpGV5/r1+H2GbKNLAGi+b9kAMQ9k92VUeCWws1WENqb4T/5MeSJT1kKWQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:16:32.260645Z"},"content_sha256":"bc51f34cb184adf560acc553bd440c21e95ba2d9d153ca83291cf39c11c682b0","schema_version":"1.0","event_id":"sha256:bc51f34cb184adf560acc553bd440c21e95ba2d9d153ca83291cf39c11c682b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZDOGVWXIS532KJY7AY25XN3EFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Masaaki Nagata, Qiyu Wu, Yoshimasa Tsuruoka","submitted_at":"2023-06-09T03:11:42Z","abstract_excerpt":"Most existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness. Here, to mitigate the dependence on manual data, we broaden the source of supervision by relaxing the requirement for correct, fully-aligned, and parallel sentences. Specifically, we make noisy, partially aligned, and non-parallel paragraphs. We then use such a large-scale weakly-supervised dataset for word alignment pre-training via span prediction. Extensive experiments with various settings empirically demonstrate that our approach, which is named WSPAlign, is an effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05644","kind":"arxiv","version":2},"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/2306.05644/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":"2026-07-05T07:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qUf0zrva3rT5N9Ht355F7WETAGHN/Nbt6ykVmBtrnt2LwdA+UzuwaMytUyDLWKCJCuie1rP8AN6ElHLLXmn+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:16:32.261161Z"},"content_sha256":"e0ea238e10db0c71b2ee5f4fbfcaf58d1a0a5ed660cd5a6e6135c29207f40453","schema_version":"1.0","event_id":"sha256:e0ea238e10db0c71b2ee5f4fbfcaf58d1a0a5ed660cd5a6e6135c29207f40453"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDOGVWXIS532KJY7AY25XN3EFI/bundle.json","state_url":"https://pith.science/pith/ZDOGVWXIS532KJY7AY25XN3EFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDOGVWXIS532KJY7AY25XN3EFI/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":"2026-08-06T08:16:32Z","links":{"resolver":"https://pith.science/pith/ZDOGVWXIS532KJY7AY25XN3EFI","bundle":"https://pith.science/pith/ZDOGVWXIS532KJY7AY25XN3EFI/bundle.json","state":"https://pith.science/pith/ZDOGVWXIS532KJY7AY25XN3EFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDOGVWXIS532KJY7AY25XN3EFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZDOGVWXIS532KJY7AY25XN3EFI","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":"f070374bc2fa75e0ac71d077a62de394c1371e899b4ece9f79152ee71facc95b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T03:11:42Z","title_canon_sha256":"8223dc1514aae3d0db8a14ac5d09721e718ecf1fa4257db26e78852c3773e950"},"schema_version":"1.0","source":{"id":"2306.05644","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05644","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05644v2","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05644","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZDOGVWXIS532","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZDOGVWXIS532KJY7","created_at":"2026-07-05T07:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZDOGVWXI","created_at":"2026-07-05T07:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:e0ea238e10db0c71b2ee5f4fbfcaf58d1a0a5ed660cd5a6e6135c29207f40453","target":"graph","created_at":"2026-07-05T07:02:30Z","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/2306.05644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness. Here, to mitigate the dependence on manual data, we broaden the source of supervision by relaxing the requirement for correct, fully-aligned, and parallel sentences. Specifically, we make noisy, partially aligned, and non-parallel paragraphs. We then use such a large-scale weakly-supervised dataset for word alignment pre-training via span prediction. Extensive experiments with various settings empirically demonstrate that our approach, which is named WSPAlign, is an effect","authors_text":"Masaaki Nagata, Qiyu Wu, Yoshimasa Tsuruoka","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T03:11:42Z","title":"WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05644","kind":"arxiv","version":2},"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:bc51f34cb184adf560acc553bd440c21e95ba2d9d153ca83291cf39c11c682b0","target":"record","created_at":"2026-07-05T07:02:30Z","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":"f070374bc2fa75e0ac71d077a62de394c1371e899b4ece9f79152ee71facc95b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T03:11:42Z","title_canon_sha256":"8223dc1514aae3d0db8a14ac5d09721e718ecf1fa4257db26e78852c3773e950"},"schema_version":"1.0","source":{"id":"2306.05644","kind":"arxiv","version":2}},"canonical_sha256":"c8dc6adae89777a5271f0635dbb7642a2487464170de365185522cadbf513833","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8dc6adae89777a5271f0635dbb7642a2487464170de365185522cadbf513833","first_computed_at":"2026-07-05T07:02:30.075306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:30.075306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R/YQmzzxhCRg4yfAHYFConskzhmm+RIK0aAEu7HgDObQbv0glLtr9V9llg0UVPvawYbZo6QKf131wvkNgOAFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:30.075717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05644","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc51f34cb184adf560acc553bd440c21e95ba2d9d153ca83291cf39c11c682b0","sha256:e0ea238e10db0c71b2ee5f4fbfcaf58d1a0a5ed660cd5a6e6135c29207f40453"],"state_sha256":"000d8a7cbcddbbfb22466ad4d8d724d62b7e77a38a1e1a75adbb5ac2c46c9595"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NWvekHI8nRxF0H7PJuC90sxXmS00YbrSUWgDoApof0htIVwdNY+uMbz2YGa60yJFOI6LE5sAoLYD4fDJTvy9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:16:32.264877Z","bundle_sha256":"0f8b464d4d9a0f0cd38c60fb0a2069e6bbe97066ce074acde99a99e577cd6376"}}