{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GOA7PX4SPL434QT2P53C2KGLVI","short_pith_number":"pith:GOA7PX4S","schema_version":"1.0","canonical_sha256":"3381f7df927af9be427a7f762d28cbaa06045ebf61789b7657990884210f5309","source":{"kind":"arxiv","id":"2412.03590","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amit Agarwal, Bhargava Kumar, Hitesh Patel, Priyaranjan Pattnayak, Srikant Panda, Tejaswini Kumar","submitted_at":"2024-11-27T21:15:02Z","abstract_excerpt":"The development of robust Document AI models has been constrained by limited access to high-quality, labeled datasets, primarily due to data privacy concerns, scarcity, and the high cost of manual annotation. Traditional methods of synthetic data generation, such as text and image augmentation, have proven effective for increasing data diversity but often fail to capture the complex layout structures present in real world documents. This paper proposes a novel approach to synthetic document layout generation using Graph Neural Networks (GNNs). By representing document elements (e.g., text bloc"},"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":"2412.03590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T21:15:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e061358808894627bb1babefe667af9d4b229dd51c99f77455046c884db1d9ae","abstract_canon_sha256":"02a80225198aa3fdd719b44a94de4c858fa74b1ba6d474371979495c0fc915c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:38.139674Z","signature_b64":"W6wODkHWugvVDcJIztnutqYw/UCchqGvWbeBrFUDmAxTut/qjPZJsgep//gcLkVm26uBpJqdSQKTPyuDKwgeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3381f7df927af9be427a7f762d28cbaa06045ebf61789b7657990884210f5309","last_reissued_at":"2026-07-05T09:44:38.139075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:38.139075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amit Agarwal, Bhargava Kumar, Hitesh Patel, Priyaranjan Pattnayak, Srikant Panda, Tejaswini Kumar","submitted_at":"2024-11-27T21:15:02Z","abstract_excerpt":"The development of robust Document AI models has been constrained by limited access to high-quality, labeled datasets, primarily due to data privacy concerns, scarcity, and the high cost of manual annotation. Traditional methods of synthetic data generation, such as text and image augmentation, have proven effective for increasing data diversity but often fail to capture the complex layout structures present in real world documents. This paper proposes a novel approach to synthetic document layout generation using Graph Neural Networks (GNNs). By representing document elements (e.g., text bloc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03590","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/2412.03590/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":"2412.03590","created_at":"2026-07-05T09:44:38.139134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03590v1","created_at":"2026-07-05T09:44:38.139134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03590","created_at":"2026-07-05T09:44:38.139134+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOA7PX4SPL43","created_at":"2026-07-05T09:44:38.139134+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOA7PX4SPL434QT2","created_at":"2026-07-05T09:44:38.139134+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOA7PX4S","created_at":"2026-07-05T09:44:38.139134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06362","citing_title":"MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI","json":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI.json","graph_json":"https://pith.science/api/pith-number/GOA7PX4SPL434QT2P53C2KGLVI/graph.json","events_json":"https://pith.science/api/pith-number/GOA7PX4SPL434QT2P53C2KGLVI/events.json","paper":"https://pith.science/paper/GOA7PX4S"},"agent_actions":{"view_html":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI","download_json":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI.json","view_paper":"https://pith.science/paper/GOA7PX4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03590&json=true","fetch_graph":"https://pith.science/api/pith-number/GOA7PX4SPL434QT2P53C2KGLVI/graph.json","fetch_events":"https://pith.science/api/pith-number/GOA7PX4SPL434QT2P53C2KGLVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/action/storage_attestation","attest_author":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/action/author_attestation","sign_citation":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/action/citation_signature","submit_replication":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/action/replication_record"}},"created_at":"2026-07-05T09:44:38.139134+00:00","updated_at":"2026-07-05T09:44:38.139134+00:00"}