{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GOA7PX4SPL434QT2P53C2KGLVI","short_pith_number":"pith:GOA7PX4S","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"},"canonical_sha256":"3381f7df927af9be427a7f762d28cbaa06045ebf61789b7657990884210f5309","source":{"kind":"arxiv","id":"2412.03590","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03590","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03590v1","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03590","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"GOA7PX4SPL43","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"pith_short_16","alias_value":"GOA7PX4SPL434QT2","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"pith_short_8","alias_value":"GOA7PX4S","created_at":"2026-07-05T09:44:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GOA7PX4SPL434QT2P53C2KGLVI","target":"record","payload":{"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"},"canonical_sha256":"3381f7df927af9be427a7f762d28cbaa06045ebf61789b7657990884210f5309","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"},"source_kind":"arxiv","source_id":"2412.03590","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":"2026-07-05T09:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eeY4hfI8x/7SU1K8cyLtg2hsiCjvUy8+33WBbLB4jyOQNAspQe3E5HRaTNBlt+0u0a7xDPtED0icuIF1PVIGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:57:08.166386Z"},"content_sha256":"b2e1fdb5d81d40faf4674f31fb6501e3436e5637521360486beb2eca56f748e4","schema_version":"1.0","event_id":"sha256:b2e1fdb5d81d40faf4674f31fb6501e3436e5637521360486beb2eca56f748e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GOA7PX4SPL434QT2P53C2KGLVI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0RWUH0pUj3rrV35uiFZncad2qiybNVlM1UM/1JuVoOSaFpeGPLmCmzkTdq4Xv5TB0J79lIeJaAjfWf+xO+PWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:57:08.166928Z"},"content_sha256":"6eb27ecf3a7f762aa4f15f17fb672e0fbbc29ca2dd86af6fa28845df99fc268a","schema_version":"1.0","event_id":"sha256:6eb27ecf3a7f762aa4f15f17fb672e0fbbc29ca2dd86af6fa28845df99fc268a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/bundle.json","state_url":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GOA7PX4SPL434QT2P53C2KGLVI/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":"2026-08-08T09:57:08Z","links":{"resolver":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI","bundle":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/bundle.json","state":"https://pith.science/pith/GOA7PX4SPL434QT2P53C2KGLVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GOA7PX4SPL434QT2P53C2KGLVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GOA7PX4SPL434QT2P53C2KGLVI","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":"02a80225198aa3fdd719b44a94de4c858fa74b1ba6d474371979495c0fc915c5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T21:15:02Z","title_canon_sha256":"e061358808894627bb1babefe667af9d4b229dd51c99f77455046c884db1d9ae"},"schema_version":"1.0","source":{"id":"2412.03590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03590","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03590v1","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03590","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"GOA7PX4SPL43","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"pith_short_16","alias_value":"GOA7PX4SPL434QT2","created_at":"2026-07-05T09:44:38Z"},{"alias_kind":"pith_short_8","alias_value":"GOA7PX4S","created_at":"2026-07-05T09:44:38Z"}],"graph_snapshots":[{"event_id":"sha256:6eb27ecf3a7f762aa4f15f17fb672e0fbbc29ca2dd86af6fa28845df99fc268a","target":"graph","created_at":"2026-07-05T09:44:38Z","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/2412.03590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Amit Agarwal, Bhargava Kumar, Hitesh Patel, Priyaranjan Pattnayak, Srikant Panda, Tejaswini Kumar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T21:15:02Z","title":"Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03590","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:b2e1fdb5d81d40faf4674f31fb6501e3436e5637521360486beb2eca56f748e4","target":"record","created_at":"2026-07-05T09:44:38Z","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":"02a80225198aa3fdd719b44a94de4c858fa74b1ba6d474371979495c0fc915c5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T21:15:02Z","title_canon_sha256":"e061358808894627bb1babefe667af9d4b229dd51c99f77455046c884db1d9ae"},"schema_version":"1.0","source":{"id":"2412.03590","kind":"arxiv","version":1}},"canonical_sha256":"3381f7df927af9be427a7f762d28cbaa06045ebf61789b7657990884210f5309","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3381f7df927af9be427a7f762d28cbaa06045ebf61789b7657990884210f5309","first_computed_at":"2026-07-05T09:44:38.139075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:38.139075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W6wODkHWugvVDcJIztnutqYw/UCchqGvWbeBrFUDmAxTut/qjPZJsgep//gcLkVm26uBpJqdSQKTPyuDKwgeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:38.139674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2e1fdb5d81d40faf4674f31fb6501e3436e5637521360486beb2eca56f748e4","sha256:6eb27ecf3a7f762aa4f15f17fb672e0fbbc29ca2dd86af6fa28845df99fc268a"],"state_sha256":"9bcc2728be681d7e6b6451b2d4ec336180ee6d5e6f433393c2e3d108ebd53589"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GQZ7xglOGgw8RqqxOam1dU1GhqZs9h0yu9mydHc+HBemOZW/LQ+3Butqzbnjr4rE/qyvzCcZcrFunf6nh57AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:57:08.170121Z","bundle_sha256":"800c1c71743787d70ee0b5d0b433ba0c6ae285d26994337d2924accff0b478e4"}}