{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HFPPP4MQ2PKUGZ5RDTB6MQLWV7","short_pith_number":"pith:HFPPP4MQ","canonical_record":{"source":{"id":"2411.14957","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T14:16:09Z","cross_cats_sorted":[],"title_canon_sha256":"457b95daaf9bec244c549137a65b4fdce3975ef59bc38ae6a7b9b4bad004779e","abstract_canon_sha256":"fb8cb398fdcafd20e613fab336ba2a1e709cc812472051cf7e0cd6a952f217e5"},"schema_version":"1.0"},"canonical_sha256":"395ef7f190d3d54367b11cc3e64176aff8100c2b2bcd228cf8c5893d51c1cd5a","source":{"kind":"arxiv","id":"2411.14957","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14957","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14957v2","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14957","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"pith_short_12","alias_value":"HFPPP4MQ2PKU","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"pith_short_16","alias_value":"HFPPP4MQ2PKUGZ5R","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"pith_short_8","alias_value":"HFPPP4MQ","created_at":"2026-07-05T09:40:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HFPPP4MQ2PKUGZ5RDTB6MQLWV7","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14957","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T14:16:09Z","cross_cats_sorted":[],"title_canon_sha256":"457b95daaf9bec244c549137a65b4fdce3975ef59bc38ae6a7b9b4bad004779e","abstract_canon_sha256":"fb8cb398fdcafd20e613fab336ba2a1e709cc812472051cf7e0cd6a952f217e5"},"schema_version":"1.0"},"canonical_sha256":"395ef7f190d3d54367b11cc3e64176aff8100c2b2bcd228cf8c5893d51c1cd5a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:00.997578Z","signature_b64":"o7tBVa4hkzYuFiKOPIPg276s1+PoQsfzjKjyDVIIQWsKoqBBN+EBICRZgFtshhl+E6QSvLFFh/W2BuXUJCRFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"395ef7f190d3d54367b11cc3e64176aff8100c2b2bcd228cf8c5893d51c1cd5a","last_reissued_at":"2026-07-05T09:40:00.997132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:00.997132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14957","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:40:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LivDx3dgRcxGf3h3CIrsMHrLQSE01CvbMGfHkOcmWAL+hb9HWfO1ffGsgm8mdQ6Tbsyclyb35sJvLRq6IEQaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:17:16.269327Z"},"content_sha256":"35602e2e95b06bd6d75bf622dc647406fc88ad28953242981660b407f6668c80","schema_version":"1.0","event_id":"sha256:35602e2e95b06bd6d75bf622dc647406fc88ad28953242981660b407f6668c80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HFPPP4MQ2PKUGZ5RDTB6MQLWV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Information Extraction from Heterogeneous Documents without Ground Truth Labels using Synthetic Label Generation and Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aniket Bhattacharyya, Anurag Tripathi","submitted_at":"2024-11-22T14:16:09Z","abstract_excerpt":"Invoices and receipts submitted by employees are visually rich documents (VRDs) with textual, visual and layout information. To protect against the risk of fraud and abuse, it is crucial for organizations to efficiently extract desired information from submitted receipts. This helps in the assessment of key factors such as appropriateness of the expense claim, adherence to spending and transaction policies, the validity of the receipt, as well as downstream anomaly detection at various levels. These documents are heterogeneous, with multiple formats and languages, uploaded with different image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14957","kind":"arxiv","version":2},"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/2411.14957/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":"2026-07-05T09:40:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"je4GOqw8OtiY+HqfTOOi6nCRFu0Oz9cKGOuThZQ5pcmXF0+W9fV6lzrXHZyxm0SddBdfS9pHhJU9ce4G4XKvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:17:16.269697Z"},"content_sha256":"05b6db0eb70ac2bc26f35256ec0c40b124b29fbe5a85cbfa0c27785e557027ff","schema_version":"1.0","event_id":"sha256:05b6db0eb70ac2bc26f35256ec0c40b124b29fbe5a85cbfa0c27785e557027ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFPPP4MQ2PKUGZ5RDTB6MQLWV7/bundle.json","state_url":"https://pith.science/pith/HFPPP4MQ2PKUGZ5RDTB6MQLWV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFPPP4MQ2PKUGZ5RDTB6MQLWV7/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":"2026-08-12T23:17:16Z","links":{"resolver":"https://pith.science/pith/HFPPP4MQ2PKUGZ5RDTB6MQLWV7","bundle":"https://pith.science/pith/HFPPP4MQ2PKUGZ5RDTB6MQLWV7/bundle.json","state":"https://pith.science/pith/HFPPP4MQ2PKUGZ5RDTB6MQLWV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFPPP4MQ2PKUGZ5RDTB6MQLWV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HFPPP4MQ2PKUGZ5RDTB6MQLWV7","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":"fb8cb398fdcafd20e613fab336ba2a1e709cc812472051cf7e0cd6a952f217e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T14:16:09Z","title_canon_sha256":"457b95daaf9bec244c549137a65b4fdce3975ef59bc38ae6a7b9b4bad004779e"},"schema_version":"1.0","source":{"id":"2411.14957","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14957","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14957v2","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14957","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"pith_short_12","alias_value":"HFPPP4MQ2PKU","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"pith_short_16","alias_value":"HFPPP4MQ2PKUGZ5R","created_at":"2026-07-05T09:40:00Z"},{"alias_kind":"pith_short_8","alias_value":"HFPPP4MQ","created_at":"2026-07-05T09:40:00Z"}],"graph_snapshots":[{"event_id":"sha256:05b6db0eb70ac2bc26f35256ec0c40b124b29fbe5a85cbfa0c27785e557027ff","target":"graph","created_at":"2026-07-05T09:40:00Z","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/2411.14957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Invoices and receipts submitted by employees are visually rich documents (VRDs) with textual, visual and layout information. To protect against the risk of fraud and abuse, it is crucial for organizations to efficiently extract desired information from submitted receipts. This helps in the assessment of key factors such as appropriateness of the expense claim, adherence to spending and transaction policies, the validity of the receipt, as well as downstream anomaly detection at various levels. These documents are heterogeneous, with multiple formats and languages, uploaded with different image","authors_text":"Aniket Bhattacharyya, Anurag Tripathi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T14:16:09Z","title":"Information Extraction from Heterogeneous Documents without Ground Truth Labels using Synthetic Label Generation and Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14957","kind":"arxiv","version":2},"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":"sha256:35602e2e95b06bd6d75bf622dc647406fc88ad28953242981660b407f6668c80","target":"record","created_at":"2026-07-05T09:40:00Z","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":"fb8cb398fdcafd20e613fab336ba2a1e709cc812472051cf7e0cd6a952f217e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T14:16:09Z","title_canon_sha256":"457b95daaf9bec244c549137a65b4fdce3975ef59bc38ae6a7b9b4bad004779e"},"schema_version":"1.0","source":{"id":"2411.14957","kind":"arxiv","version":2}},"canonical_sha256":"395ef7f190d3d54367b11cc3e64176aff8100c2b2bcd228cf8c5893d51c1cd5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"395ef7f190d3d54367b11cc3e64176aff8100c2b2bcd228cf8c5893d51c1cd5a","first_computed_at":"2026-07-05T09:40:00.997132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:00.997132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o7tBVa4hkzYuFiKOPIPg276s1+PoQsfzjKjyDVIIQWsKoqBBN+EBICRZgFtshhl+E6QSvLFFh/W2BuXUJCRFBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:00.997578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14957","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35602e2e95b06bd6d75bf622dc647406fc88ad28953242981660b407f6668c80","sha256:05b6db0eb70ac2bc26f35256ec0c40b124b29fbe5a85cbfa0c27785e557027ff"],"state_sha256":"11cc9575efb19e3f48ed61d026ec5a5c7726c8817b72c4f40a9cd2bc6d56651d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1X28KFYrxCeAhUgNdY9NqY8opYrtWLwMSYD431QRUbnyJjwTbxcarUUazgUHYiud1CP8oanD/myxOA1kYwnBDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:17:16.272083Z","bundle_sha256":"a4a4afcb261d5b1dcbe906bfb5c8ad778d3f0513e0e9b436a09dfc041d258e4e"}}