{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZABTB2LCH4ULRAQLZAXWPSXLS5","short_pith_number":"pith:ZABTB2LC","schema_version":"1.0","canonical_sha256":"c80330e9623f28b8820bc82f67caeb977e8dfd343de338adcb36b7be0885e112","source":{"kind":"arxiv","id":"2406.05930","version":2},"attestation_state":"computed","paper":{"title":"Semisupervised Neural Proto-Language Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David R. Mortensen, Liang Lu, Peirong Xie","submitted_at":"2024-06-09T22:46:41Z","abstract_excerpt":"Existing work implementing comparative reconstruction of ancestral languages (proto-languages) has usually required full supervision. However, historical reconstruction models are only of practical value if they can be trained with a limited amount of labeled data. We propose a semisupervised historical reconstruction task in which the model is trained on only a small amount of labeled data (cognate sets with proto-forms) and a large amount of unlabeled data (cognate sets without proto-forms). We propose a neural architecture for comparative reconstruction (DPD-BiReconstructor) incorporating a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.05930","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T22:46:41Z","cross_cats_sorted":[],"title_canon_sha256":"7f8136e28f9623c6b161551e624c297000d0dce916ce4a2960fe0709a747ae43","abstract_canon_sha256":"3d3343edfa53fd4b31cfb8380c7126f2309c4221aaf94446749e27e07b4f50e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:36.473449Z","signature_b64":"S+/h5qhsWITdrynmYmKQL1QAPEyzs0ud1SChJ7BcA5NS457QsK4ku22oLUzP2RcvvIaHYxYUYdjmrY5nGEeTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c80330e9623f28b8820bc82f67caeb977e8dfd343de338adcb36b7be0885e112","last_reissued_at":"2026-07-05T08:54:36.473038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:36.473038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semisupervised Neural Proto-Language Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David R. Mortensen, Liang Lu, Peirong Xie","submitted_at":"2024-06-09T22:46:41Z","abstract_excerpt":"Existing work implementing comparative reconstruction of ancestral languages (proto-languages) has usually required full supervision. However, historical reconstruction models are only of practical value if they can be trained with a limited amount of labeled data. We propose a semisupervised historical reconstruction task in which the model is trained on only a small amount of labeled data (cognate sets with proto-forms) and a large amount of unlabeled data (cognate sets without proto-forms). We propose a neural architecture for comparative reconstruction (DPD-BiReconstructor) incorporating a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05930","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/2406.05930/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.05930","created_at":"2026-07-05T08:54:36.473090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05930v2","created_at":"2026-07-05T08:54:36.473090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05930","created_at":"2026-07-05T08:54:36.473090+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZABTB2LCH4UL","created_at":"2026-07-05T08:54:36.473090+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZABTB2LCH4ULRAQL","created_at":"2026-07-05T08:54:36.473090+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZABTB2LC","created_at":"2026-07-05T08:54:36.473090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5","json":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5.json","graph_json":"https://pith.science/api/pith-number/ZABTB2LCH4ULRAQLZAXWPSXLS5/graph.json","events_json":"https://pith.science/api/pith-number/ZABTB2LCH4ULRAQLZAXWPSXLS5/events.json","paper":"https://pith.science/paper/ZABTB2LC"},"agent_actions":{"view_html":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5","download_json":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5.json","view_paper":"https://pith.science/paper/ZABTB2LC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05930&json=true","fetch_graph":"https://pith.science/api/pith-number/ZABTB2LCH4ULRAQLZAXWPSXLS5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZABTB2LCH4ULRAQLZAXWPSXLS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5/action/storage_attestation","attest_author":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5/action/author_attestation","sign_citation":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5/action/citation_signature","submit_replication":"https://pith.science/pith/ZABTB2LCH4ULRAQLZAXWPSXLS5/action/replication_record"}},"created_at":"2026-07-05T08:54:36.473090+00:00","updated_at":"2026-07-05T08:54:36.473090+00:00"}