{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SQM5QB5HBQ2KJJH5TSBIAAXSEN","short_pith_number":"pith:SQM5QB5H","schema_version":"1.0","canonical_sha256":"9419d807a70c34a4a4fd9c828002f223586af35b725996439a37ed663c9ea79f","source":{"kind":"arxiv","id":"2605.16338","version":1},"attestation_state":"computed","paper":{"title":"Vidya: An AI-Driven Modular Pipeline for Archival Automation and Semantic Metadata Enrichment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Cloter Migliorini Filho, Edson Armando Silva, Julia Graciela Machado, Marcella Scoczynski","submitted_at":"2026-05-07T11:21:24Z","abstract_excerpt":"The large-scale digitization of historical archives has created a paradox: \"dark data\"-digital objects lacking metadata for retrieval. Manual archival description is slow and expensive, limiting discovery and reuse. We propose Vidya, a modular pipeline that orchestrates Large Language Models (LLMs) and FOSS tools to automate semantic enrichment and archival ingestion at scale. Vidya constrains generations using YAML-defined ontologies and Pydantic validation, producing deterministic, structured JSON outputs from probabilistic models. Developed at Laboratory for Digital Humanities and Innovatio"},"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":"2605.16338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-05-07T11:21:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9e321ed2ade1a9cf7dc7df834ec0db410a2162142367d64b71caef6e40de2c65","abstract_canon_sha256":"da0d1f862ca19280dcc22045f3e2ffa0d4e74b0545059c96062770d08d362481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:17.392513Z","signature_b64":"/lGPbDPRtQnPWJxRmC6aIHPoqk4bKqHUZX3MgKLDMZtwoRWDhkTHuf6TDUiKmNoWUGAVCu8fgYs/KsEADJXwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9419d807a70c34a4a4fd9c828002f223586af35b725996439a37ed663c9ea79f","last_reissued_at":"2026-05-20T00:02:17.391989Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:17.391989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vidya: An AI-Driven Modular Pipeline for Archival Automation and Semantic Metadata Enrichment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Cloter Migliorini Filho, Edson Armando Silva, Julia Graciela Machado, Marcella Scoczynski","submitted_at":"2026-05-07T11:21:24Z","abstract_excerpt":"The large-scale digitization of historical archives has created a paradox: \"dark data\"-digital objects lacking metadata for retrieval. Manual archival description is slow and expensive, limiting discovery and reuse. We propose Vidya, a modular pipeline that orchestrates Large Language Models (LLMs) and FOSS tools to automate semantic enrichment and archival ingestion at scale. Vidya constrains generations using YAML-defined ontologies and Pydantic validation, producing deterministic, structured JSON outputs from probabilistic models. Developed at Laboratory for Digital Humanities and Innovatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16338","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/2605.16338/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":"2605.16338","created_at":"2026-05-20T00:02:17.392066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16338v1","created_at":"2026-05-20T00:02:17.392066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16338","created_at":"2026-05-20T00:02:17.392066+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQM5QB5HBQ2K","created_at":"2026-05-20T00:02:17.392066+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQM5QB5HBQ2KJJH5","created_at":"2026-05-20T00:02:17.392066+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQM5QB5H","created_at":"2026-05-20T00:02:17.392066+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/SQM5QB5HBQ2KJJH5TSBIAAXSEN","json":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN.json","graph_json":"https://pith.science/api/pith-number/SQM5QB5HBQ2KJJH5TSBIAAXSEN/graph.json","events_json":"https://pith.science/api/pith-number/SQM5QB5HBQ2KJJH5TSBIAAXSEN/events.json","paper":"https://pith.science/paper/SQM5QB5H"},"agent_actions":{"view_html":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN","download_json":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN.json","view_paper":"https://pith.science/paper/SQM5QB5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16338&json=true","fetch_graph":"https://pith.science/api/pith-number/SQM5QB5HBQ2KJJH5TSBIAAXSEN/graph.json","fetch_events":"https://pith.science/api/pith-number/SQM5QB5HBQ2KJJH5TSBIAAXSEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/action/storage_attestation","attest_author":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/action/author_attestation","sign_citation":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/action/citation_signature","submit_replication":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/action/replication_record"}},"created_at":"2026-05-20T00:02:17.392066+00:00","updated_at":"2026-05-20T00:02:17.392066+00:00"}