{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SQM5QB5HBQ2KJJH5TSBIAAXSEN","short_pith_number":"pith:SQM5QB5H","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"},"canonical_sha256":"9419d807a70c34a4a4fd9c828002f223586af35b725996439a37ed663c9ea79f","source":{"kind":"arxiv","id":"2605.16338","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16338","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16338v1","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16338","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"SQM5QB5HBQ2K","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"SQM5QB5HBQ2KJJH5","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"SQM5QB5H","created_at":"2026-05-20T00:02:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SQM5QB5HBQ2KJJH5TSBIAAXSEN","target":"record","payload":{"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"},"canonical_sha256":"9419d807a70c34a4a4fd9c828002f223586af35b725996439a37ed663c9ea79f","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"},"source_kind":"arxiv","source_id":"2605.16338","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":"2026-05-20T00:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0b/mJ38dJPSRZGIKVhgI8+Ht8n7xj/jneSj93fB0g2tgq/TUUIrder1leDMQj/61mhB4rXO7UDhbsorwawZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:45:01.136595Z"},"content_sha256":"15681ea8fb956abf1149ff24d3c45b20356895d1b94149286aebc711d5225478","schema_version":"1.0","event_id":"sha256:15681ea8fb956abf1149ff24d3c45b20356895d1b94149286aebc711d5225478"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SQM5QB5HBQ2KJJH5TSBIAAXSEN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AJ6f6cMRkxX7J+SSvc3AMj/n+aXJLoa2dZXG3dKdhQkJJQ3U4xUo2l6iO1wc1K+Vv4Z4/hIw4Oit0D/hw8I0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:45:01.136981Z"},"content_sha256":"e0f62677a444da397db2bc1d26de35990d7df183cf552482c19d2a5d27ab0833","schema_version":"1.0","event_id":"sha256:e0f62677a444da397db2bc1d26de35990d7df183cf552482c19d2a5d27ab0833"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/bundle.json","state_url":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/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":"2026-06-05T09:45:01Z","links":{"resolver":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN","bundle":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/bundle.json","state":"https://pith.science/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQM5QB5HBQ2KJJH5TSBIAAXSEN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SQM5QB5HBQ2KJJH5TSBIAAXSEN","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":"da0d1f862ca19280dcc22045f3e2ffa0d4e74b0545059c96062770d08d362481","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-05-07T11:21:24Z","title_canon_sha256":"9e321ed2ade1a9cf7dc7df834ec0db410a2162142367d64b71caef6e40de2c65"},"schema_version":"1.0","source":{"id":"2605.16338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16338","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16338v1","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16338","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"SQM5QB5HBQ2K","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"SQM5QB5HBQ2KJJH5","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"SQM5QB5H","created_at":"2026-05-20T00:02:17Z"}],"graph_snapshots":[{"event_id":"sha256:e0f62677a444da397db2bc1d26de35990d7df183cf552482c19d2a5d27ab0833","target":"graph","created_at":"2026-05-20T00:02:17Z","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/2605.16338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cloter Migliorini Filho, Edson Armando Silva, Julia Graciela Machado, Marcella Scoczynski","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-05-07T11:21:24Z","title":"Vidya: An AI-Driven Modular Pipeline for Archival Automation and Semantic Metadata Enrichment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16338","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":"sha256:15681ea8fb956abf1149ff24d3c45b20356895d1b94149286aebc711d5225478","target":"record","created_at":"2026-05-20T00:02:17Z","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":"da0d1f862ca19280dcc22045f3e2ffa0d4e74b0545059c96062770d08d362481","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-05-07T11:21:24Z","title_canon_sha256":"9e321ed2ade1a9cf7dc7df834ec0db410a2162142367d64b71caef6e40de2c65"},"schema_version":"1.0","source":{"id":"2605.16338","kind":"arxiv","version":1}},"canonical_sha256":"9419d807a70c34a4a4fd9c828002f223586af35b725996439a37ed663c9ea79f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9419d807a70c34a4a4fd9c828002f223586af35b725996439a37ed663c9ea79f","first_computed_at":"2026-05-20T00:02:17.391989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:17.391989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/lGPbDPRtQnPWJxRmC6aIHPoqk4bKqHUZX3MgKLDMZtwoRWDhkTHuf6TDUiKmNoWUGAVCu8fgYs/KsEADJXwDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:17.392513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15681ea8fb956abf1149ff24d3c45b20356895d1b94149286aebc711d5225478","sha256:e0f62677a444da397db2bc1d26de35990d7df183cf552482c19d2a5d27ab0833"],"state_sha256":"c643ed5989f85cc82e2de20d8f7cd073b4c3c74f4f061bc3b336ab6602aebd3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsSMZduGCqv1a9pzfBC7vAYCK6fnXbObZPGomIODYpnp20EirIwV8Z5WjRYyAjc3+7sg6/GXGxanqS5GoYTyCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T09:45:01.139096Z","bundle_sha256":"cee3d40f45b986c71d41585a7c639f5e8d17e3372f43c05489f17593117aa17c"}}