{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4KSPQLLUDI7HB6CSNGJXWYJGHS","short_pith_number":"pith:4KSPQLLU","canonical_record":{"source":{"id":"2507.00911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T16:14:20Z","cross_cats_sorted":["q-bio.PE"],"title_canon_sha256":"82022f1ba7b19e1dda47b3581e07459a3e76970be04496d6e9207fccde67f345","abstract_canon_sha256":"5fe85a5a87de98deafca06dad3fed5decdeba66a2a58d4bdde1f752c79c8514d"},"schema_version":"1.0"},"canonical_sha256":"e2a4f82d741a3e70f85269937b61263c897283d00e5dde639ced41a456e63f1c","source":{"kind":"arxiv","id":"2507.00911","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4KSPQLLUDI7HB6CSNGJXWYJGHS","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T16:14:20Z","cross_cats_sorted":["q-bio.PE"],"title_canon_sha256":"82022f1ba7b19e1dda47b3581e07459a3e76970be04496d6e9207fccde67f345","abstract_canon_sha256":"5fe85a5a87de98deafca06dad3fed5decdeba66a2a58d4bdde1f752c79c8514d"},"schema_version":"1.0"},"canonical_sha256":"e2a4f82d741a3e70f85269937b61263c897283d00e5dde639ced41a456e63f1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:17.417606Z","signature_b64":"/msJ3nj5pyfE/sscut0cLOh+5HzE2i9Uvp6tXFHZXAcxFzXbHgSoZLwascXrzwdeNeROXKrvNQipRm8RF8coCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2a4f82d741a3e70f85269937b61263c897283d00e5dde639ced41a456e63f1c","last_reissued_at":"2026-07-05T11:30:17.417128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:17.417128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00911","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":"2026-07-05T11:30:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZM7EDESZ7jj4yvjJIvSqT/YTKVKiuDzYAP9M4XA3+T/dFoxP6jdBw10JVipCV5kr3hQU5TvIWl/tVBSVEesCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:34:33.529075Z"},"content_sha256":"9d8302c4fc4bcb110e90ba3ab3b06d605b3a8d812b6e33f462af8d967618f7e3","schema_version":"1.0","event_id":"sha256:9d8302c4fc4bcb110e90ba3ab3b06d605b3a8d812b6e33f462af8d967618f7e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4KSPQLLUDI7HB6CSNGJXWYJGHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Cognate Data Bottleneck in Language Phylogenetics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.PE"],"primary_cat":"cs.CL","authors_text":"Alexandros Stamatakis, Luise H\\\"auser","submitted_at":"2025-07-01T16:14:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00911","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.00911/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":"2026-07-05T11:30:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H5ANESW8ybyGMT8ORz3WUshg9jzJGSaQuPLi7KWLXxkfKNTO+tZll05880ZonQlW7Njlgi5CalMwWSa/GrxxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:34:33.529962Z"},"content_sha256":"72c20fee33beaf9658796b07281d41dce495f3da28a71cf0d1e1b8a58b23c63c","schema_version":"1.0","event_id":"sha256:72c20fee33beaf9658796b07281d41dce495f3da28a71cf0d1e1b8a58b23c63c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KSPQLLUDI7HB6CSNGJXWYJGHS/bundle.json","state_url":"https://pith.science/pith/4KSPQLLUDI7HB6CSNGJXWYJGHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KSPQLLUDI7HB6CSNGJXWYJGHS/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":"2026-08-07T19:34:33Z","links":{"resolver":"https://pith.science/pith/4KSPQLLUDI7HB6CSNGJXWYJGHS","bundle":"https://pith.science/pith/4KSPQLLUDI7HB6CSNGJXWYJGHS/bundle.json","state":"https://pith.science/pith/4KSPQLLUDI7HB6CSNGJXWYJGHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KSPQLLUDI7HB6CSNGJXWYJGHS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXrUg6TycYBnlwmOsWpUlGRM5F4/RrENWaKBIblFaGSYHXuxvjd7j0lX2qRzNm0Rw9uqZXaX7xajBZuroQLtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:34:33.539327Z","bundle_sha256":"62a6f8f19a0fb1782ccc44888fe43855c927474074c3020dcd834070c2115784"}}