{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7HJGEKUN5L4SVGJUUI74COYCVI","short_pith_number":"pith:7HJGEKUN","canonical_record":{"source":{"id":"2507.21114","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-11T08:30:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"f7d0ae89a2060c216ae51b95c64644526b10a408c1f1a6d0fc178654e8b9e6fc","abstract_canon_sha256":"1c67bd51d0f628ea92e7c0ba125c0d3839add78e68764b90da52cadb11d1a909"},"schema_version":"1.0"},"canonical_sha256":"f9d2622a8deaf92a9934a23fc13b02aa2ccdcdced06174d96cf047e217435614","source":{"kind":"arxiv","id":"2507.21114","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21114","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21114v4","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21114","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"7HJGEKUN5L4S","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"7HJGEKUN5L4SVGJU","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"7HJGEKUN","created_at":"2026-05-26T02:03:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7HJGEKUN5L4SVGJUUI74COYCVI","target":"record","payload":{"canonical_record":{"source":{"id":"2507.21114","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-11T08:30:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"f7d0ae89a2060c216ae51b95c64644526b10a408c1f1a6d0fc178654e8b9e6fc","abstract_canon_sha256":"1c67bd51d0f628ea92e7c0ba125c0d3839add78e68764b90da52cadb11d1a909"},"schema_version":"1.0"},"canonical_sha256":"f9d2622a8deaf92a9934a23fc13b02aa2ccdcdced06174d96cf047e217435614","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:52.871471Z","signature_b64":"PgPSyuch2MF5H04zUPxLTkp3Qo1a+qsUDhNxrfIeNf/qwzAQsg8rbhXtdbzTjddwP7O/piK7Ospg/Zaf4wOdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9d2622a8deaf92a9934a23fc13b02aa2ccdcdced06174d96cf047e217435614","last_reissued_at":"2026-05-26T02:03:52.870609Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:52.870609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.21114","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vuC+3FzJfpl5knJc9CbDHdTpIYDRCkQo9Uhn9LlNb4U3l6mkOUhQBBWHPAM5dv2nZ/tzjeDvX5CE7O6fLCJMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:25:39.380419Z"},"content_sha256":"77dd24b64f4112eed63e48cd65bb6d1313bfbaed8501ee50f1bd4f58d92bb472","schema_version":"1.0","event_id":"sha256:77dd24b64f4112eed63e48cd65bb6d1313bfbaed8501ee50f1bd4f58d92bb472"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7HJGEKUN5L4SVGJUUI74COYCVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Page image classification for content-specific data processing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"An image classification system sorts historical document pages by content to enable tailored processing pipelines.","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.IR","authors_text":"Kateryna Lutsai, Pavel Stra\\v{n}\\'ak","submitted_at":"2025-07-11T08:30:12Z","abstract_excerpt":"Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges for manual sorting and analysis. These archives contain diverse content, including various text types (handwritten, typed, printed), graphical elements (drawings, maps, photos), and layouts (plain text, tables, forms). Efficiently processing this heterogeneous data requires automated methods to categorize pages based on their content, enabling tailored downstream analysis pipelines. This project addresses this need by developing and evaluating an image "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a standard image classifier trained on historical page images can reliably separate the described content types at a level useful for downstream specialized pipelines, without the abstract providing any accuracy figures, dataset details, or error analysis to support this.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Develops an image classification system for historical document pages to support content-specific analysis pipelines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An image classification system sorts historical document pages by content to enable tailored processing pipelines.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3ee4201e603842cec07c1227db113feb728c0986021a6e92ea254e611b8930d0"},"source":{"id":"2507.21114","kind":"arxiv","version":4},"verdict":{"id":"1fea8cb9-61fb-4e90-9698-9e61a782d2e5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T05:57:34.317724Z","strongest_claim":"This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics).","one_line_summary":"Develops an image classification system for historical document pages to support content-specific analysis pipelines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a standard image classifier trained on historical page images can reliably separate the described content types at a level useful for downstream specialized pipelines, without the abstract providing any accuracy figures, dataset details, or error analysis to support this.","pith_extraction_headline":"An image classification system sorts historical document pages by content to enable tailored processing pipelines."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.21114/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":"1fea8cb9-61fb-4e90-9698-9e61a782d2e5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WYonw+K1SrFgGqk5+nyZFanQFX24SK7wycAa8l5XU4DDIQ11W72wf09ageKVCJTM98VjrUXZiKLTnQh5nAHtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:25:39.381086Z"},"content_sha256":"fb2fcf507892dcf054b412f6a90a9b6bc9fd2f622a68809c03eb96b41054fbbe","schema_version":"1.0","event_id":"sha256:fb2fcf507892dcf054b412f6a90a9b6bc9fd2f622a68809c03eb96b41054fbbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HJGEKUN5L4SVGJUUI74COYCVI/bundle.json","state_url":"https://pith.science/pith/7HJGEKUN5L4SVGJUUI74COYCVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HJGEKUN5L4SVGJUUI74COYCVI/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":"2026-06-05T23:25:39Z","links":{"resolver":"https://pith.science/pith/7HJGEKUN5L4SVGJUUI74COYCVI","bundle":"https://pith.science/pith/7HJGEKUN5L4SVGJUUI74COYCVI/bundle.json","state":"https://pith.science/pith/7HJGEKUN5L4SVGJUUI74COYCVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HJGEKUN5L4SVGJUUI74COYCVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7HJGEKUN5L4SVGJUUI74COYCVI","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":"1c67bd51d0f628ea92e7c0ba125c0d3839add78e68764b90da52cadb11d1a909","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-11T08:30:12Z","title_canon_sha256":"f7d0ae89a2060c216ae51b95c64644526b10a408c1f1a6d0fc178654e8b9e6fc"},"schema_version":"1.0","source":{"id":"2507.21114","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21114","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21114v4","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21114","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"7HJGEKUN5L4S","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"7HJGEKUN5L4SVGJU","created_at":"2026-05-26T02:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"7HJGEKUN","created_at":"2026-05-26T02:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:fb2fcf507892dcf054b412f6a90a9b6bc9fd2f622a68809c03eb96b41054fbbe","target":"graph","created_at":"2026-05-26T02:03:52Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a standard image classifier trained on historical page images can reliably separate the described content types at a level useful for downstream specialized pipelines, without the abstract providing any accuracy figures, dataset details, or error analysis to support this."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Develops an image classification system for historical document pages to support content-specific analysis pipelines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An image classification system sorts historical document pages by content to enable tailored processing pipelines."}],"snapshot_sha256":"3ee4201e603842cec07c1227db113feb728c0986021a6e92ea254e611b8930d0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.21114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges for manual sorting and analysis. These archives contain diverse content, including various text types (handwritten, typed, printed), graphical elements (drawings, maps, photos), and layouts (plain text, tables, forms). Efficiently processing this heterogeneous data requires automated methods to categorize pages based on their content, enabling tailored downstream analysis pipelines. This project addresses this need by developing and evaluating an image ","authors_text":"Kateryna Lutsai, Pavel Stra\\v{n}\\'ak","cross_cats":["cs.AI","cs.CV"],"headline":"An image classification system sorts historical document pages by content to enable tailored processing pipelines.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-11T08:30:12Z","title":"Page image classification for content-specific data processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21114","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-19T05:57:34.317724Z","id":"1fea8cb9-61fb-4e90-9698-9e61a782d2e5","model_set":{"reader":"grok-4.3"},"one_line_summary":"Develops an image classification system for historical document pages to support content-specific analysis pipelines.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"An image classification system sorts historical document pages by content to enable tailored processing pipelines.","strongest_claim":"This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics).","weakest_assumption":"That a standard image classifier trained on historical page images can reliably separate the described content types at a level useful for downstream specialized pipelines, without the abstract providing any accuracy figures, dataset details, or error analysis to support this."}},"verdict_id":"1fea8cb9-61fb-4e90-9698-9e61a782d2e5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:77dd24b64f4112eed63e48cd65bb6d1313bfbaed8501ee50f1bd4f58d92bb472","target":"record","created_at":"2026-05-26T02:03:52Z","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":"1c67bd51d0f628ea92e7c0ba125c0d3839add78e68764b90da52cadb11d1a909","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-11T08:30:12Z","title_canon_sha256":"f7d0ae89a2060c216ae51b95c64644526b10a408c1f1a6d0fc178654e8b9e6fc"},"schema_version":"1.0","source":{"id":"2507.21114","kind":"arxiv","version":4}},"canonical_sha256":"f9d2622a8deaf92a9934a23fc13b02aa2ccdcdced06174d96cf047e217435614","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9d2622a8deaf92a9934a23fc13b02aa2ccdcdced06174d96cf047e217435614","first_computed_at":"2026-05-26T02:03:52.870609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:03:52.870609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PgPSyuch2MF5H04zUPxLTkp3Qo1a+qsUDhNxrfIeNf/qwzAQsg8rbhXtdbzTjddwP7O/piK7Ospg/Zaf4wOdBA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:03:52.871471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21114","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77dd24b64f4112eed63e48cd65bb6d1313bfbaed8501ee50f1bd4f58d92bb472","sha256:fb2fcf507892dcf054b412f6a90a9b6bc9fd2f622a68809c03eb96b41054fbbe"],"state_sha256":"b3d777e915f5be1e1ee7aa5107fc6f5796cd9153e8fb65f8243fc8af43e29709"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6ubj8LrtZFGZo3PrDes6LhhGR0AdQ4BG60ZzZYGKPinF5kptdpesnWhqHtEu/J5r67UNQYg6mHEWBnx2TdcBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T23:25:39.384396Z","bundle_sha256":"bfdc020e8c035d16b5d22ac5b49ea7d70c42301e0db68c6e6d9b59636b44fb27"}}