{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BE2WYRAQWC5DVFGJU2DEXJAYQP","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":"20a46a53a10c8574dac5e9d89a52985bb1307e4b2676e3ec5764ee2c97f77c72","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T17:20:00Z","title_canon_sha256":"dbdfbc5649a29be3b28e51362a893311b979d42cefac1b84e0174552ccba6283"},"schema_version":"1.0","source":{"id":"2501.05497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05497","created_at":"2026-07-05T09:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05497v1","created_at":"2026-07-05T09:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05497","created_at":"2026-07-05T09:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"BE2WYRAQWC5D","created_at":"2026-07-05T09:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"BE2WYRAQWC5DVFGJ","created_at":"2026-07-05T09:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"BE2WYRAQ","created_at":"2026-07-05T09:59:24Z"}],"graph_snapshots":[{"event_id":"sha256:40d07a6a918b0f4371b237bba72243ed6550d8229e301a6aabe0dce3df875908","target":"graph","created_at":"2026-07-05T09:59:24Z","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/2501.05497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document layout understanding is a field of study that analyzes the spatial arrangement of information in a document hoping to understand its structure and layout. Models such as LayoutLM (and its subsequent iterations) can understand semi-structured documents with SotA results; however, the lack of open semi-structured data is a limitation in itself. While semi-structured data is common in everyday life (balance sheets, purchase orders, receipts), there is a lack of public datasets for training machine learning models for this type of document. In this investigation we propose a method to gen","authors_text":"Clemens Havas, Pablo Melendez","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T17:20:00Z","title":"Spatial Information Integration in Small Language Models for Document Layout Generation and Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05497","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:b6f1150f4e59c505de9706b1d5587d9bab70c4f66bedbf0d4b3d55d11fa77ee3","target":"record","created_at":"2026-07-05T09:59:24Z","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":"20a46a53a10c8574dac5e9d89a52985bb1307e4b2676e3ec5764ee2c97f77c72","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T17:20:00Z","title_canon_sha256":"dbdfbc5649a29be3b28e51362a893311b979d42cefac1b84e0174552ccba6283"},"schema_version":"1.0","source":{"id":"2501.05497","kind":"arxiv","version":1}},"canonical_sha256":"09356c4410b0ba3a94c9a6864ba41883ee4ad90d09bed9041bd8856f22839f01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09356c4410b0ba3a94c9a6864ba41883ee4ad90d09bed9041bd8856f22839f01","first_computed_at":"2026-07-05T09:59:24.333034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:24.333034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QHcwiVwxVeO0J924bsOCdwMZUGRcb6sbId1r8kWjaey7iunPaisxdz48wiDtZE2ezRW6WpWsYVjbdwizBRF/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:24.333479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6f1150f4e59c505de9706b1d5587d9bab70c4f66bedbf0d4b3d55d11fa77ee3","sha256:40d07a6a918b0f4371b237bba72243ed6550d8229e301a6aabe0dce3df875908"],"state_sha256":"e28faf2a8eabb0fc1b06e3b5c0d07088ab84aab7aeba95b9e7df5531afe73f03"}