{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EA4DSCZMAPLRJBEKOQOMAFZPFZ","short_pith_number":"pith:EA4DSCZM","canonical_record":{"source":{"id":"2404.00439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T18:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"bc7beadd54da38f551a51c9574268c4d8fbec470a9f82f510f984296e95d3160","abstract_canon_sha256":"a051242ecadf0a28bf732e9c13f3487cd3799854ebbac2d1bb906cefaeeb713a"},"schema_version":"1.0"},"canonical_sha256":"2038390b2c03d714848a741cc0172f2e57c8bb216be3fe77bb2af8552ba5374e","source":{"kind":"arxiv","id":"2404.00439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00439","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00439v1","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00439","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_12","alias_value":"EA4DSCZMAPLR","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_16","alias_value":"EA4DSCZMAPLRJBEK","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_8","alias_value":"EA4DSCZM","created_at":"2026-07-05T08:02:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EA4DSCZMAPLRJBEKOQOMAFZPFZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.00439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T18:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"bc7beadd54da38f551a51c9574268c4d8fbec470a9f82f510f984296e95d3160","abstract_canon_sha256":"a051242ecadf0a28bf732e9c13f3487cd3799854ebbac2d1bb906cefaeeb713a"},"schema_version":"1.0"},"canonical_sha256":"2038390b2c03d714848a741cc0172f2e57c8bb216be3fe77bb2af8552ba5374e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:33.354021Z","signature_b64":"4TjjCCxDTtXk655DUgPSOKHvb5z6lce+x5K3FsPgtQs66FecjKpbO6fcCxEMy8N+9JIi5tvZ4y0yuWvA9ST1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2038390b2c03d714848a741cc0172f2e57c8bb216be3fe77bb2af8552ba5374e","last_reissued_at":"2026-07-05T08:02:33.353624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:33.353624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.00439","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":"2026-07-05T08:02:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mlxHSv1C6wKdN+hCCsoystnAVlv2C46kkoqgSDUWuS9obPkdSIX5WO6gDKLGkhr/byW43zas291uiHZEcIxWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:39:19.927736Z"},"content_sha256":"182b5e85ffd35c2dde6e20b82d5670bc04270d920947bad0945ff44da7bd3661","schema_version":"1.0","event_id":"sha256:182b5e85ffd35c2dde6e20b82d5670bc04270d920947bad0945ff44da7bd3661"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EA4DSCZMAPLRJBEKOQOMAFZPFZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Nguyen, Dheeraj Mekala, Jingbo Shang, Zilong Wang","submitted_at":"2024-03-30T18:11:39Z","abstract_excerpt":"The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists in businesses due to specific hurdles. These include the complexity of working with PDF formats that necessitate parsing text and layout information for curating training data and the lack of privacy-preserving annotation tools. This paper introduces DOCMASTER, a unified platform designed for annotating PDF documents, model training, and inference, tailored to document question-answering. The annotation interface enab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00439","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/2404.00439/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":"2026-07-05T08:02:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z/QbPyJBKD8hTAXH58MEIH/RZMXXLJORtj0E9UTGKbAZIN9sO12pkcRvM9ASi39YJTIzjt4ipIEcGDVLpwrOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:39:19.928104Z"},"content_sha256":"f1cafa2a82059d697e2b5e506a761fcacea5b2a8a485ae93146a75666639036a","schema_version":"1.0","event_id":"sha256:f1cafa2a82059d697e2b5e506a761fcacea5b2a8a485ae93146a75666639036a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EA4DSCZMAPLRJBEKOQOMAFZPFZ/bundle.json","state_url":"https://pith.science/pith/EA4DSCZMAPLRJBEKOQOMAFZPFZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EA4DSCZMAPLRJBEKOQOMAFZPFZ/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":"2026-07-31T20:39:19Z","links":{"resolver":"https://pith.science/pith/EA4DSCZMAPLRJBEKOQOMAFZPFZ","bundle":"https://pith.science/pith/EA4DSCZMAPLRJBEKOQOMAFZPFZ/bundle.json","state":"https://pith.science/pith/EA4DSCZMAPLRJBEKOQOMAFZPFZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EA4DSCZMAPLRJBEKOQOMAFZPFZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EA4DSCZMAPLRJBEKOQOMAFZPFZ","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":"a051242ecadf0a28bf732e9c13f3487cd3799854ebbac2d1bb906cefaeeb713a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T18:11:39Z","title_canon_sha256":"bc7beadd54da38f551a51c9574268c4d8fbec470a9f82f510f984296e95d3160"},"schema_version":"1.0","source":{"id":"2404.00439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00439","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00439v1","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00439","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_12","alias_value":"EA4DSCZMAPLR","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_16","alias_value":"EA4DSCZMAPLRJBEK","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_8","alias_value":"EA4DSCZM","created_at":"2026-07-05T08:02:33Z"}],"graph_snapshots":[{"event_id":"sha256:f1cafa2a82059d697e2b5e506a761fcacea5b2a8a485ae93146a75666639036a","target":"graph","created_at":"2026-07-05T08:02:33Z","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/2404.00439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists in businesses due to specific hurdles. These include the complexity of working with PDF formats that necessitate parsing text and layout information for curating training data and the lack of privacy-preserving annotation tools. This paper introduces DOCMASTER, a unified platform designed for annotating PDF documents, model training, and inference, tailored to document question-answering. The annotation interface enab","authors_text":"Alex Nguyen, Dheeraj Mekala, Jingbo Shang, Zilong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T18:11:39Z","title":"DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00439","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":"sha256:182b5e85ffd35c2dde6e20b82d5670bc04270d920947bad0945ff44da7bd3661","target":"record","created_at":"2026-07-05T08:02:33Z","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":"a051242ecadf0a28bf732e9c13f3487cd3799854ebbac2d1bb906cefaeeb713a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T18:11:39Z","title_canon_sha256":"bc7beadd54da38f551a51c9574268c4d8fbec470a9f82f510f984296e95d3160"},"schema_version":"1.0","source":{"id":"2404.00439","kind":"arxiv","version":1}},"canonical_sha256":"2038390b2c03d714848a741cc0172f2e57c8bb216be3fe77bb2af8552ba5374e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2038390b2c03d714848a741cc0172f2e57c8bb216be3fe77bb2af8552ba5374e","first_computed_at":"2026-07-05T08:02:33.353624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:33.353624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4TjjCCxDTtXk655DUgPSOKHvb5z6lce+x5K3FsPgtQs66FecjKpbO6fcCxEMy8N+9JIi5tvZ4y0yuWvA9ST1Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:33.354021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:182b5e85ffd35c2dde6e20b82d5670bc04270d920947bad0945ff44da7bd3661","sha256:f1cafa2a82059d697e2b5e506a761fcacea5b2a8a485ae93146a75666639036a"],"state_sha256":"813b4f5a65a429080d9839bd7288e5007ca343d730fc2a0e90efdf4557c1541b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JEaAU8hw4nkCGQ5TMV807DwR/J6EbK+wAbyJSK2T5fHmJZd9ORL6WYw24XmgsFCOOn6akse4TGsZ5Z2ox+h7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T20:39:19.931506Z","bundle_sha256":"fe63ec44af30daaecea6c2c7ca55424730e11d40c8eb821666e521714a6cb749"}}