{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EGBINOPFOFKC3OWEZBDUI6TZA7","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":"95bd50c3792c551151784b58623596b9c64f6a07f5ef0b11a43e07854d3477de","cross_cats_sorted":["cs.DL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T15:20:13Z","title_canon_sha256":"d4df9051395b355cd2abc0708e7b238384ca6fb99b61659e9d1d62c12706f838"},"schema_version":"1.0","source":{"id":"2607.24542","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24542","created_at":"2026-07-28T02:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24542v1","created_at":"2026-07-28T02:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24542","created_at":"2026-07-28T02:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"EGBINOPFOFKC","created_at":"2026-07-28T02:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"EGBINOPFOFKC3OWE","created_at":"2026-07-28T02:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"EGBINOPF","created_at":"2026-07-28T02:24:09Z"}],"graph_snapshots":[{"event_id":"sha256:eaac531e96eef1c62aa05b3b811f717757229ee3e0904feb8289c1fce8f3be86","target":"graph","created_at":"2026-07-28T02:24:09Z","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/2607.24542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Text Recognition (ATR) now supplies digital humanities with large volumes of unstructured, heterogeneous, and often noisy text in ancient languages. Downstream semantic analysestext reuse identification, alignment, and semantic search-rely on sentence embeddings, yet existing methods transfer poorly to ancient languages: generic multilingual encoders underperform, specialized language models yield anisotropic representation spaces, and labeled similarity data is unavailable. We study two fully unsupervised strategies - TSDAE and contrastive sentence embedding (CSE) - that adapt a spe","authors_text":"CNRS), HiSoMA, Th{\\'e}otime de la Selle (ISC","cross_cats":["cs.DL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T15:20:13Z","title":"From transcription to semantic corpus analysis: unsupervised learning of sentence representations for ancient languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24542","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:b8da114af25cd411f3974f1cb2e34625f72607745b90c0fda1fcb6665f0502de","target":"record","created_at":"2026-07-28T02:24:09Z","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":"95bd50c3792c551151784b58623596b9c64f6a07f5ef0b11a43e07854d3477de","cross_cats_sorted":["cs.DL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T15:20:13Z","title_canon_sha256":"d4df9051395b355cd2abc0708e7b238384ca6fb99b61659e9d1d62c12706f838"},"schema_version":"1.0","source":{"id":"2607.24542","kind":"arxiv","version":1}},"canonical_sha256":"218286b9e571542dbac4c847447a7907fe53a6ee70db74a5f5205ee8d82bd020","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"218286b9e571542dbac4c847447a7907fe53a6ee70db74a5f5205ee8d82bd020","first_computed_at":"2026-07-28T02:24:09.073948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:24:09.073948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"31bMbCXPEEY5gQwELOIZEDXbBCfHSNy9vtV71wTYB9Po+z4ZfEo4ib+n8l4E3yn1yE5MP//89FY6zN3YFER8CQ==","signature_status":"signed_v1","signed_at":"2026-07-28T02:24:09.074765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24542","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8da114af25cd411f3974f1cb2e34625f72607745b90c0fda1fcb6665f0502de","sha256:eaac531e96eef1c62aa05b3b811f717757229ee3e0904feb8289c1fce8f3be86"],"state_sha256":"85e35b91ddbca85137ab6157c4cf4557ad0fe58e480f53d53f0cc3e61d795317"}