{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DJHL4PS4CLDXV6HXFHAI5FWLF5","short_pith_number":"pith:DJHL4PS4","canonical_record":{"source":{"id":"2212.10047","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T07:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"6dd390853f7bd8d10a39909d7b9c8ca235048edb5520dede9d590cf4dcec0b8f","abstract_canon_sha256":"0ec38f151109872db9dca3f9a25e32cbe8ad1de02d36ae976e3612c936632a00"},"schema_version":"1.0"},"canonical_sha256":"1a4ebe3e5c12c77af8f729c08e96cb2f6c788f05614846f4fa4467011f04b4d2","source":{"kind":"arxiv","id":"2212.10047","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10047","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10047v2","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10047","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"pith_short_12","alias_value":"DJHL4PS4CLDX","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"DJHL4PS4CLDXV6HX","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"DJHL4PS4","created_at":"2026-07-05T05:27:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DJHL4PS4CLDXV6HXFHAI5FWLF5","target":"record","payload":{"canonical_record":{"source":{"id":"2212.10047","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T07:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"6dd390853f7bd8d10a39909d7b9c8ca235048edb5520dede9d590cf4dcec0b8f","abstract_canon_sha256":"0ec38f151109872db9dca3f9a25e32cbe8ad1de02d36ae976e3612c936632a00"},"schema_version":"1.0"},"canonical_sha256":"1a4ebe3e5c12c77af8f729c08e96cb2f6c788f05614846f4fa4467011f04b4d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:36.893416Z","signature_b64":"nQe5rXfukgs6DJzOs9ueylQTY7LsmssDqRbndRvMlwgGTJOKj/VGTloI6cNHd4Vnkwko/QdExbyBrih2GlGACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4ebe3e5c12c77af8f729c08e96cb2f6c788f05614846f4fa4467011f04b4d2","last_reissued_at":"2026-07-05T05:27:36.892978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:36.892978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.10047","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":"2026-07-05T05:27:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rVweE73uMpWdheGox/v2mm9oVdR4pSA1C+WaL9d9vNGG4S+W7zbxdZeYOU9ngtRU5lnzFDWkpYtTFlOzm19pBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:00:05.374429Z"},"content_sha256":"dfbfc80c511f5109e38dd40b8590a94508413fba8b66462b006c5efebd5f5dfc","schema_version":"1.0","event_id":"sha256:dfbfc80c511f5109e38dd40b8590a94508413fba8b66462b006c5efebd5f5dfc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DJHL4PS4CLDXV6HXFHAI5FWLF5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Augmentation Strategy for Visually Rich Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"James B. Wendt, Jing Xie, Sandeep Tata, Seth Ebner, Yichao Zhou","submitted_at":"2022-12-20T07:44:25Z","abstract_excerpt":"Many business workflows require extracting important fields from form-like documents (e.g. bank statements, bills of lading, purchase orders, etc.). Recent techniques for automating this task work well only when trained with large datasets. In this work we propose a novel data augmentation technique to improve performance when training data is scarce, e.g. 10-250 documents. Our technique, which we call FieldSwap, works by swapping out the key phrases of a source field with the key phrases of a target field to generate new synthetic examples of the target field for use in training. We demonstra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10047","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/2212.10047/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":"2026-07-05T05:27:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gUfOkXPKmMfoNrVx6I1MRprSR5hV4zwQmu/k2Fa2sbB+h+muMLuEjyyoIdAN8rtqKbkBrUyOG2eCHWXqeOcqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:00:05.374937Z"},"content_sha256":"af1a99f08c6a7655cd60d9e2e63563a970207a9e963054dd4cde645a9cf590f3","schema_version":"1.0","event_id":"sha256:af1a99f08c6a7655cd60d9e2e63563a970207a9e963054dd4cde645a9cf590f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DJHL4PS4CLDXV6HXFHAI5FWLF5/bundle.json","state_url":"https://pith.science/pith/DJHL4PS4CLDXV6HXFHAI5FWLF5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DJHL4PS4CLDXV6HXFHAI5FWLF5/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":"2026-08-17T16:00:05Z","links":{"resolver":"https://pith.science/pith/DJHL4PS4CLDXV6HXFHAI5FWLF5","bundle":"https://pith.science/pith/DJHL4PS4CLDXV6HXFHAI5FWLF5/bundle.json","state":"https://pith.science/pith/DJHL4PS4CLDXV6HXFHAI5FWLF5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DJHL4PS4CLDXV6HXFHAI5FWLF5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DJHL4PS4CLDXV6HXFHAI5FWLF5","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":"0ec38f151109872db9dca3f9a25e32cbe8ad1de02d36ae976e3612c936632a00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T07:44:25Z","title_canon_sha256":"6dd390853f7bd8d10a39909d7b9c8ca235048edb5520dede9d590cf4dcec0b8f"},"schema_version":"1.0","source":{"id":"2212.10047","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10047","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10047v2","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10047","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"pith_short_12","alias_value":"DJHL4PS4CLDX","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"DJHL4PS4CLDXV6HX","created_at":"2026-07-05T05:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"DJHL4PS4","created_at":"2026-07-05T05:27:36Z"}],"graph_snapshots":[{"event_id":"sha256:af1a99f08c6a7655cd60d9e2e63563a970207a9e963054dd4cde645a9cf590f3","target":"graph","created_at":"2026-07-05T05:27:36Z","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/2212.10047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many business workflows require extracting important fields from form-like documents (e.g. bank statements, bills of lading, purchase orders, etc.). Recent techniques for automating this task work well only when trained with large datasets. In this work we propose a novel data augmentation technique to improve performance when training data is scarce, e.g. 10-250 documents. Our technique, which we call FieldSwap, works by swapping out the key phrases of a source field with the key phrases of a target field to generate new synthetic examples of the target field for use in training. We demonstra","authors_text":"James B. Wendt, Jing Xie, Sandeep Tata, Seth Ebner, Yichao Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T07:44:25Z","title":"An Augmentation Strategy for Visually Rich Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10047","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:dfbfc80c511f5109e38dd40b8590a94508413fba8b66462b006c5efebd5f5dfc","target":"record","created_at":"2026-07-05T05:27:36Z","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":"0ec38f151109872db9dca3f9a25e32cbe8ad1de02d36ae976e3612c936632a00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T07:44:25Z","title_canon_sha256":"6dd390853f7bd8d10a39909d7b9c8ca235048edb5520dede9d590cf4dcec0b8f"},"schema_version":"1.0","source":{"id":"2212.10047","kind":"arxiv","version":2}},"canonical_sha256":"1a4ebe3e5c12c77af8f729c08e96cb2f6c788f05614846f4fa4467011f04b4d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a4ebe3e5c12c77af8f729c08e96cb2f6c788f05614846f4fa4467011f04b4d2","first_computed_at":"2026-07-05T05:27:36.892978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:36.892978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nQe5rXfukgs6DJzOs9ueylQTY7LsmssDqRbndRvMlwgGTJOKj/VGTloI6cNHd4Vnkwko/QdExbyBrih2GlGACg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:36.893416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10047","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfbfc80c511f5109e38dd40b8590a94508413fba8b66462b006c5efebd5f5dfc","sha256:af1a99f08c6a7655cd60d9e2e63563a970207a9e963054dd4cde645a9cf590f3"],"state_sha256":"4290436fcc7b6394cd0983984e03cefe8a25a5a2ae826ce8d7faaced4d34607c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6EeABuQqR6KdWSQ9SGKzzUfcJSQh+KcvhKdnMwsRgGiORbKFJHq/BsInHyO6o/6w8Q+hck8q501rNXfoD+3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:00:05.386351Z","bundle_sha256":"db9ff4350441b446dde6efd0e6b00be85b5d1f78e17d2d63209c5c671189693f"}}