{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EGBINOPFOFKC3OWEZBDUI6TZA7","short_pith_number":"pith:EGBINOPF","schema_version":"1.0","canonical_sha256":"218286b9e571542dbac4c847447a7907fe53a6ee70db74a5f5205ee8d82bd020","source":{"kind":"arxiv","id":"2607.24542","version":1},"attestation_state":"computed","paper":{"title":"From transcription to semantic corpus analysis: unsupervised learning of sentence representations for ancient languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.CL","authors_text":"CNRS), HiSoMA, Th{\\'e}otime de la Selle (ISC","submitted_at":"2026-07-27T15:20:13Z","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"},"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":"2607.24542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T15:20:13Z","cross_cats_sorted":["cs.DL","cs.IR"],"title_canon_sha256":"d4df9051395b355cd2abc0708e7b238384ca6fb99b61659e9d1d62c12706f838","abstract_canon_sha256":"95bd50c3792c551151784b58623596b9c64f6a07f5ef0b11a43e07854d3477de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:09.074765Z","signature_b64":"31bMbCXPEEY5gQwELOIZEDXbBCfHSNy9vtV71wTYB9Po+z4ZfEo4ib+n8l4E3yn1yE5MP//89FY6zN3YFER8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"218286b9e571542dbac4c847447a7907fe53a6ee70db74a5f5205ee8d82bd020","last_reissued_at":"2026-07-28T02:24:09.073948Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:09.073948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From transcription to semantic corpus analysis: unsupervised learning of sentence representations for ancient languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.CL","authors_text":"CNRS), HiSoMA, Th{\\'e}otime de la Selle (ISC","submitted_at":"2026-07-27T15:20:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24542","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/2607.24542/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":"2607.24542","created_at":"2026-07-28T02:24:09.074362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24542v1","created_at":"2026-07-28T02:24:09.074362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24542","created_at":"2026-07-28T02:24:09.074362+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGBINOPFOFKC","created_at":"2026-07-28T02:24:09.074362+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGBINOPFOFKC3OWE","created_at":"2026-07-28T02:24:09.074362+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGBINOPF","created_at":"2026-07-28T02:24:09.074362+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/EGBINOPFOFKC3OWEZBDUI6TZA7","json":"https://pith.science/pith/EGBINOPFOFKC3OWEZBDUI6TZA7.json","graph_json":"https://pith.science/api/pith-number/EGBINOPFOFKC3OWEZBDUI6TZA7/graph.json","events_json":"https://pith.science/api/pith-number/EGBINOPFOFKC3OWEZBDUI6TZA7/events.json","paper":"https://pith.science/paper/EGBINOPF"},"agent_actions":{"view_html":"https://pith.science/pith/EGBINOPFOFKC3OWEZBDUI6TZA7","download_json":"https://pith.science/pith/EGBINOPFOFKC3OWEZBDUI6TZA7.json","view_paper":"https://pith.science/paper/EGBINOPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24542&json=true","fetch_graph":"https://pith.science/api/pith-number/EGBINOPFOFKC3OWEZBDUI6TZA7/graph.json","fetch_events":"https://pith.science/api/pith-number/EGBINOPFOFKC3OWEZBDUI6TZA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGBINOPFOFKC3OWEZBDUI6TZA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGBINOPFOFKC3OWEZBDUI6TZA7/action/storage_attestation","attest_author":"https://pith.science/pith/EGBINOPFOFKC3OWEZBDUI6TZA7/action/author_attestation","sign_citation":"https://pith.science/pith/EGBINOPFOFKC3OWEZBDUI6TZA7/action/citation_signature","submit_replication":"https://pith.science/pith/EGBINOPFOFKC3OWEZBDUI6TZA7/action/replication_record"}},"created_at":"2026-07-28T02:24:09.074362+00:00","updated_at":"2026-07-28T02:24:09.074362+00:00"}