{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XJL46NYRYCXZXJDLIVFZJIIJVS","short_pith_number":"pith:XJL46NYR","schema_version":"1.0","canonical_sha256":"ba57cf3711c0af9ba46b454b94a109ac8986b67a5e3b28eca860c90f4abf1538","source":{"kind":"arxiv","id":"2603.02803","version":2},"attestation_state":"computed","paper":{"title":"Structure-Aware Text Recognition for Ancient Greek Critical Editions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonia Karamolegkou, Beno\\^it Sagot, Nicolas Angleraud, Thibault Cl\\'erice","submitted_at":"2026-03-03T09:42:43Z","abstract_excerpt":"Recent advances in visual language models (VLMs) have transformed end-to-end document understanding. However, their ability to interpret the complex layout semantics of historical scholarly texts remains limited. This paper investigates structure-aware text recognition for Ancient Greek critical editions, which have dense reference hierarchies and extensive marginal annotations. We introduce two novel resources: (i) a large-scale synthetic corpus of 185,000 page images generated from TEI/XML sources with controlled typographic and layout variation, and (ii) a curated benchmark of real scanned "},"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":"2603.02803","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-03T09:42:43Z","cross_cats_sorted":[],"title_canon_sha256":"1209b60daeeb9c98988c48f0f4fcf7b45407016a8b0116add6a4007706c8c93d","abstract_canon_sha256":"486f9e714936ae67e6a9e8215332def089ba5e23d155c13abdcf874179ef10ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:42.212703Z","signature_b64":"Mm9SzmV31KnjllLrvNY23DQVVSDZ77qjTPNLjJpFHU7SH9yaGwFGraaxFgIWa2KrEcG2p+8nrZE/WwcEje2SCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba57cf3711c0af9ba46b454b94a109ac8986b67a5e3b28eca860c90f4abf1538","last_reissued_at":"2026-05-29T02:05:42.212186Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:42.212186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-Aware Text Recognition for Ancient Greek Critical Editions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonia Karamolegkou, Beno\\^it Sagot, Nicolas Angleraud, Thibault Cl\\'erice","submitted_at":"2026-03-03T09:42:43Z","abstract_excerpt":"Recent advances in visual language models (VLMs) have transformed end-to-end document understanding. However, their ability to interpret the complex layout semantics of historical scholarly texts remains limited. This paper investigates structure-aware text recognition for Ancient Greek critical editions, which have dense reference hierarchies and extensive marginal annotations. We introduce two novel resources: (i) a large-scale synthetic corpus of 185,000 page images generated from TEI/XML sources with controlled typographic and layout variation, and (ii) a curated benchmark of real scanned "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.02803","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/2603.02803/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":"2603.02803","created_at":"2026-05-29T02:05:42.212249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.02803v2","created_at":"2026-05-29T02:05:42.212249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02803","created_at":"2026-05-29T02:05:42.212249+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJL46NYRYCXZ","created_at":"2026-05-29T02:05:42.212249+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJL46NYRYCXZXJDL","created_at":"2026-05-29T02:05:42.212249+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJL46NYR","created_at":"2026-05-29T02:05:42.212249+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/XJL46NYRYCXZXJDLIVFZJIIJVS","json":"https://pith.science/pith/XJL46NYRYCXZXJDLIVFZJIIJVS.json","graph_json":"https://pith.science/api/pith-number/XJL46NYRYCXZXJDLIVFZJIIJVS/graph.json","events_json":"https://pith.science/api/pith-number/XJL46NYRYCXZXJDLIVFZJIIJVS/events.json","paper":"https://pith.science/paper/XJL46NYR"},"agent_actions":{"view_html":"https://pith.science/pith/XJL46NYRYCXZXJDLIVFZJIIJVS","download_json":"https://pith.science/pith/XJL46NYRYCXZXJDLIVFZJIIJVS.json","view_paper":"https://pith.science/paper/XJL46NYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.02803&json=true","fetch_graph":"https://pith.science/api/pith-number/XJL46NYRYCXZXJDLIVFZJIIJVS/graph.json","fetch_events":"https://pith.science/api/pith-number/XJL46NYRYCXZXJDLIVFZJIIJVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJL46NYRYCXZXJDLIVFZJIIJVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJL46NYRYCXZXJDLIVFZJIIJVS/action/storage_attestation","attest_author":"https://pith.science/pith/XJL46NYRYCXZXJDLIVFZJIIJVS/action/author_attestation","sign_citation":"https://pith.science/pith/XJL46NYRYCXZXJDLIVFZJIIJVS/action/citation_signature","submit_replication":"https://pith.science/pith/XJL46NYRYCXZXJDLIVFZJIIJVS/action/replication_record"}},"created_at":"2026-05-29T02:05:42.212249+00:00","updated_at":"2026-05-29T02:05:42.212249+00:00"}