{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4KSPQLLUDI7HB6CSNGJXWYJGHS","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":"5fe85a5a87de98deafca06dad3fed5decdeba66a2a58d4bdde1f752c79c8514d","cross_cats_sorted":["q-bio.PE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T16:14:20Z","title_canon_sha256":"82022f1ba7b19e1dda47b3581e07459a3e76970be04496d6e9207fccde67f345"},"schema_version":"1.0","source":{"id":"2507.00911","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00911","created_at":"2026-07-05T11:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00911v1","created_at":"2026-07-05T11:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00911","created_at":"2026-07-05T11:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"4KSPQLLUDI7H","created_at":"2026-07-05T11:30:17Z"},{"alias_kind":"pith_short_16","alias_value":"4KSPQLLUDI7HB6CS","created_at":"2026-07-05T11:30:17Z"},{"alias_kind":"pith_short_8","alias_value":"4KSPQLLU","created_at":"2026-07-05T11:30:17Z"}],"graph_snapshots":[{"event_id":"sha256:72c20fee33beaf9658796b07281d41dce495f3da28a71cf0d1e1b8a58b23c63c","target":"graph","created_at":"2026-07-05T11:30:17Z","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/2507.00911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To fully exploit the potential of computational phylogenetic methods for cognate data one needs to leverage specific (complex) models an machine learning-based techniques. However, both approaches require datasets that are substantially larger than the manually collected cognate data currently available. To the best of our knowledge, there exists no feasible approach to automatically generate larger cognate datasets. We substantiate this claim by automatically extracting datasets from BabelNet, a large multilingual encyclopedic dictionary. We demonstrate that phylogenetic inferences on the res","authors_text":"Alexandros Stamatakis, Luise H\\\"auser","cross_cats":["q-bio.PE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T16:14:20Z","title":"The Cognate Data Bottleneck in Language Phylogenetics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00911","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":"sha256:9d8302c4fc4bcb110e90ba3ab3b06d605b3a8d812b6e33f462af8d967618f7e3","target":"record","created_at":"2026-07-05T11:30:17Z","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":"5fe85a5a87de98deafca06dad3fed5decdeba66a2a58d4bdde1f752c79c8514d","cross_cats_sorted":["q-bio.PE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T16:14:20Z","title_canon_sha256":"82022f1ba7b19e1dda47b3581e07459a3e76970be04496d6e9207fccde67f345"},"schema_version":"1.0","source":{"id":"2507.00911","kind":"arxiv","version":1}},"canonical_sha256":"e2a4f82d741a3e70f85269937b61263c897283d00e5dde639ced41a456e63f1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2a4f82d741a3e70f85269937b61263c897283d00e5dde639ced41a456e63f1c","first_computed_at":"2026-07-05T11:30:17.417128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:17.417128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/msJ3nj5pyfE/sscut0cLOh+5HzE2i9Uvp6tXFHZXAcxFzXbHgSoZLwascXrzwdeNeROXKrvNQipRm8RF8coCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:17.417606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00911","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d8302c4fc4bcb110e90ba3ab3b06d605b3a8d812b6e33f462af8d967618f7e3","sha256:72c20fee33beaf9658796b07281d41dce495f3da28a71cf0d1e1b8a58b23c63c"],"state_sha256":"f7f4124474b5475213f1011b1ba486b94d9b8fd3e0305ac4b173a6de7cf47e41"}