{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MHEASA2M2SHJD7JBN45ENLC2M7","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":"c3b16ce9dc4c16c510167aadb79bc16fc2a25e5cb163f2d8e045662b6dbfd5f2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T10:27:59Z","title_canon_sha256":"d44432d11b557e5e931b8109ab644b95b7d59df8946b62b614a3a2e9a79701ac"},"schema_version":"1.0","source":{"id":"2606.10675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10675","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10675v1","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10675","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"MHEASA2M2SHJ","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"MHEASA2M2SHJD7JB","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"MHEASA2M","created_at":"2026-06-10T01:10:33Z"}],"graph_snapshots":[{"event_id":"sha256:0c8a86df3318b805081a897f5571fbfe1a8b374f4c3137dc2d4bbe887dbdb77c","target":"graph","created_at":"2026-06-10T01:10:33Z","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/2606.10675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a method for accurate multilingual word-level forced alignment, consisting of an alignment encoder and a learned alignment decoder. The encoder integrates two representations: one from the Massively Multilingual Speech (MMS) model and another from a self-supervised phoneme boundary detector (UnSupSeg). It learns to fuse them and to estimate word-boundary probabilities over long temporal contexts. The alignment decoder is a learned dynamic programming that combines encoder outputs with segmental features over the MMS and UnSupSeg representations to infer final word boundaries. Traine","authors_text":"Joseph Keshet, Meidan Zehavi, Rotem Rousso, Roy Weber","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T10:27:59Z","title":"Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10675","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:b79a555a6acf648d49de488df1c7c97236ef3808a01d2e7c0c58cb1cc17d0c5f","target":"record","created_at":"2026-06-10T01:10:33Z","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":"c3b16ce9dc4c16c510167aadb79bc16fc2a25e5cb163f2d8e045662b6dbfd5f2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T10:27:59Z","title_canon_sha256":"d44432d11b557e5e931b8109ab644b95b7d59df8946b62b614a3a2e9a79701ac"},"schema_version":"1.0","source":{"id":"2606.10675","kind":"arxiv","version":1}},"canonical_sha256":"61c809034cd48e91fd216f3a46ac5a67d75619c454206012ac1c1770e8346015","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61c809034cd48e91fd216f3a46ac5a67d75619c454206012ac1c1770e8346015","first_computed_at":"2026-06-10T01:10:33.637075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:33.637075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PxQgiAEPmsDhhp3eAkR7jvtfKY0VpcAl87L9iJ4XyyfDw13yzz0pWOIIswZcmKLvBZY8h7Xuzxqh0hwKHxxCDg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:33.637942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b79a555a6acf648d49de488df1c7c97236ef3808a01d2e7c0c58cb1cc17d0c5f","sha256:0c8a86df3318b805081a897f5571fbfe1a8b374f4c3137dc2d4bbe887dbdb77c"],"state_sha256":"2767a775ef31f5c973f7fb25a66a0c4ab3bbc42de3534694abea301e9d8bf560"}