{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BE2WYRAQWC5DVFGJU2DEXJAYQP","short_pith_number":"pith:BE2WYRAQ","schema_version":"1.0","canonical_sha256":"09356c4410b0ba3a94c9a6864ba41883ee4ad90d09bed9041bd8856f22839f01","source":{"kind":"arxiv","id":"2501.05497","version":1},"attestation_state":"computed","paper":{"title":"Spatial Information Integration in Small Language Models for Document Layout Generation and Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Clemens Havas, Pablo Melendez","submitted_at":"2025-01-09T17:20:00Z","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"},"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":"2501.05497","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T17:20:00Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"dbdfbc5649a29be3b28e51362a893311b979d42cefac1b84e0174552ccba6283","abstract_canon_sha256":"20a46a53a10c8574dac5e9d89a52985bb1307e4b2676e3ec5764ee2c97f77c72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:24.333479Z","signature_b64":"QHcwiVwxVeO0J924bsOCdwMZUGRcb6sbId1r8kWjaey7iunPaisxdz48wiDtZE2ezRW6WpWsYVjbdwizBRF/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09356c4410b0ba3a94c9a6864ba41883ee4ad90d09bed9041bd8856f22839f01","last_reissued_at":"2026-07-05T09:59:24.333034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:24.333034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial Information Integration in Small Language Models for Document Layout Generation and Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Clemens Havas, Pablo Melendez","submitted_at":"2025-01-09T17:20:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05497","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/2501.05497/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":"2501.05497","created_at":"2026-07-05T09:59:24.333099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05497v1","created_at":"2026-07-05T09:59:24.333099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05497","created_at":"2026-07-05T09:59:24.333099+00:00"},{"alias_kind":"pith_short_12","alias_value":"BE2WYRAQWC5D","created_at":"2026-07-05T09:59:24.333099+00:00"},{"alias_kind":"pith_short_16","alias_value":"BE2WYRAQWC5DVFGJ","created_at":"2026-07-05T09:59:24.333099+00:00"},{"alias_kind":"pith_short_8","alias_value":"BE2WYRAQ","created_at":"2026-07-05T09:59:24.333099+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/BE2WYRAQWC5DVFGJU2DEXJAYQP","json":"https://pith.science/pith/BE2WYRAQWC5DVFGJU2DEXJAYQP.json","graph_json":"https://pith.science/api/pith-number/BE2WYRAQWC5DVFGJU2DEXJAYQP/graph.json","events_json":"https://pith.science/api/pith-number/BE2WYRAQWC5DVFGJU2DEXJAYQP/events.json","paper":"https://pith.science/paper/BE2WYRAQ"},"agent_actions":{"view_html":"https://pith.science/pith/BE2WYRAQWC5DVFGJU2DEXJAYQP","download_json":"https://pith.science/pith/BE2WYRAQWC5DVFGJU2DEXJAYQP.json","view_paper":"https://pith.science/paper/BE2WYRAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05497&json=true","fetch_graph":"https://pith.science/api/pith-number/BE2WYRAQWC5DVFGJU2DEXJAYQP/graph.json","fetch_events":"https://pith.science/api/pith-number/BE2WYRAQWC5DVFGJU2DEXJAYQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BE2WYRAQWC5DVFGJU2DEXJAYQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BE2WYRAQWC5DVFGJU2DEXJAYQP/action/storage_attestation","attest_author":"https://pith.science/pith/BE2WYRAQWC5DVFGJU2DEXJAYQP/action/author_attestation","sign_citation":"https://pith.science/pith/BE2WYRAQWC5DVFGJU2DEXJAYQP/action/citation_signature","submit_replication":"https://pith.science/pith/BE2WYRAQWC5DVFGJU2DEXJAYQP/action/replication_record"}},"created_at":"2026-07-05T09:59:24.333099+00:00","updated_at":"2026-07-05T09:59:24.333099+00:00"}