{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XUSEJK3VQFEJI7QFD2U7IG6RYE","short_pith_number":"pith:XUSEJK3V","canonical_record":{"source":{"id":"2605.18818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T13:07:34Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"7060dd99915bef2b4253f3b3881b2b62fa835cc7e78e151c57a821f7f80b6392","abstract_canon_sha256":"43ee902a52fda7313af8dfd73da050e74d5ea7176942798361c9068c47e3dde5"},"schema_version":"1.0"},"canonical_sha256":"bd2444ab758148947e051ea9f41bd1c13011fff5b0295a6aae7f31bba2d86b23","source":{"kind":"arxiv","id":"2605.18818","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18818","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18818v1","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18818","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"XUSEJK3VQFEJ","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"XUSEJK3VQFEJI7QF","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"XUSEJK3V","created_at":"2026-05-20T00:06:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XUSEJK3VQFEJI7QFD2U7IG6RYE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T13:07:34Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"7060dd99915bef2b4253f3b3881b2b62fa835cc7e78e151c57a821f7f80b6392","abstract_canon_sha256":"43ee902a52fda7313af8dfd73da050e74d5ea7176942798361c9068c47e3dde5"},"schema_version":"1.0"},"canonical_sha256":"bd2444ab758148947e051ea9f41bd1c13011fff5b0295a6aae7f31bba2d86b23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:24.208945Z","signature_b64":"RwGW+RL5asGTOOURwgh2A1wpL0S1nt+yeBIxMcRdURnwpahIji/AFwUuKNVqDYGm8sU6FMUonQNVWKeaymiLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd2444ab758148947e051ea9f41bd1c13011fff5b0295a6aae7f31bba2d86b23","last_reissued_at":"2026-05-20T00:06:24.208115Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:24.208115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18818","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":"2026-05-20T00:06:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FjlF3yhv21zaUqFVvMsz1nztyc4l3MWX/qh1cYyfOJ1ZFS5sjYH8W7R+f596aIW4Yj+9RiiMpU11yFeAVT+KBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:56:55.910643Z"},"content_sha256":"25be1c27772c26618dcebd4beaaeea8b907f95fe46f6015a4ea1d767d006dd41","schema_version":"1.0","event_id":"sha256:25be1c27772c26618dcebd4beaaeea8b907f95fe46f6015a4ea1d767d006dd41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XUSEJK3VQFEJI7QFD2U7IG6RYE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Benjamin Bengfort, Ben Johnson, Devon Slonaker, Joyce Rigelo, Michael Wharton, Patrick Deziel, Prema Roman, Steve Kramer, Steve Veldman, Vahid Eyorokon, Yao Fehlis, Zhangzhang Si","submitted_at":"2026-05-12T13:07:34Z","abstract_excerpt":"Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To close that gap, we present a microservice architecture that encapsulates pipelines of multiple models for classification, optical character recognition (OCR), and large language model structured field extraction as well as our experience running this pipeline on thousands of multi-page documents per hour. We describe our primary design decisions, including a hybrid classification, separation of GPU-bound inference fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18818","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/2605.18818/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":"2026-05-20T00:06:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RO+AjMBcefoJauwDYfZhSF+SFeyFa+cQsHfqSJ5yvts7mq7mf3NDbCDdFFdMwM/pzwA8eEkCQKnIg25vKmUiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:56:55.911394Z"},"content_sha256":"c7f59890aee782c3cea293228d2e2b52bae64dbfc662b29f4e840165ef787715","schema_version":"1.0","event_id":"sha256:c7f59890aee782c3cea293228d2e2b52bae64dbfc662b29f4e840165ef787715"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUSEJK3VQFEJI7QFD2U7IG6RYE/bundle.json","state_url":"https://pith.science/pith/XUSEJK3VQFEJI7QFD2U7IG6RYE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUSEJK3VQFEJI7QFD2U7IG6RYE/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":"2026-05-26T06:56:55Z","links":{"resolver":"https://pith.science/pith/XUSEJK3VQFEJI7QFD2U7IG6RYE","bundle":"https://pith.science/pith/XUSEJK3VQFEJI7QFD2U7IG6RYE/bundle.json","state":"https://pith.science/pith/XUSEJK3VQFEJI7QFD2U7IG6RYE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUSEJK3VQFEJI7QFD2U7IG6RYE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XUSEJK3VQFEJI7QFD2U7IG6RYE","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":"43ee902a52fda7313af8dfd73da050e74d5ea7176942798361c9068c47e3dde5","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T13:07:34Z","title_canon_sha256":"7060dd99915bef2b4253f3b3881b2b62fa835cc7e78e151c57a821f7f80b6392"},"schema_version":"1.0","source":{"id":"2605.18818","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18818","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18818v1","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18818","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"XUSEJK3VQFEJ","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"XUSEJK3VQFEJI7QF","created_at":"2026-05-20T00:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"XUSEJK3V","created_at":"2026-05-20T00:06:24Z"}],"graph_snapshots":[{"event_id":"sha256:c7f59890aee782c3cea293228d2e2b52bae64dbfc662b29f4e840165ef787715","target":"graph","created_at":"2026-05-20T00:06:24Z","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/2605.18818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To close that gap, we present a microservice architecture that encapsulates pipelines of multiple models for classification, optical character recognition (OCR), and large language model structured field extraction as well as our experience running this pipeline on thousands of multi-page documents per hour. We describe our primary design decisions, including a hybrid classification, separation of GPU-bound inference fr","authors_text":"Benjamin Bengfort, Ben Johnson, Devon Slonaker, Joyce Rigelo, Michael Wharton, Patrick Deziel, Prema Roman, Steve Kramer, Steve Veldman, Vahid Eyorokon, Yao Fehlis, Zhangzhang Si","cross_cats":["cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T13:07:34Z","title":"Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18818","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":"sha256:25be1c27772c26618dcebd4beaaeea8b907f95fe46f6015a4ea1d767d006dd41","target":"record","created_at":"2026-05-20T00:06:24Z","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":"43ee902a52fda7313af8dfd73da050e74d5ea7176942798361c9068c47e3dde5","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T13:07:34Z","title_canon_sha256":"7060dd99915bef2b4253f3b3881b2b62fa835cc7e78e151c57a821f7f80b6392"},"schema_version":"1.0","source":{"id":"2605.18818","kind":"arxiv","version":1}},"canonical_sha256":"bd2444ab758148947e051ea9f41bd1c13011fff5b0295a6aae7f31bba2d86b23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd2444ab758148947e051ea9f41bd1c13011fff5b0295a6aae7f31bba2d86b23","first_computed_at":"2026-05-20T00:06:24.208115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:24.208115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RwGW+RL5asGTOOURwgh2A1wpL0S1nt+yeBIxMcRdURnwpahIji/AFwUuKNVqDYGm8sU6FMUonQNVWKeaymiLDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:24.208945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18818","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25be1c27772c26618dcebd4beaaeea8b907f95fe46f6015a4ea1d767d006dd41","sha256:c7f59890aee782c3cea293228d2e2b52bae64dbfc662b29f4e840165ef787715"],"state_sha256":"0359fbf2b3d86abd0c425a692857859a2ca477d55c34191686da02007d45d3e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4SB6RTW7JrayZY6ITrwXqDUSso1PKxqS/GsKC9r5q9yOeuupSMW/X+XGpZBD9ksMySIZZxh96RhI/1MFu+/MCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:56:55.915227Z","bundle_sha256":"6ce5797db513df154d26a9654f0eb9189dac4c3d79bfeb6781ca7f07a2fd167d"}}