{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AW3T3FI7HLCHM4ZCNOQEK4FKSQ","short_pith_number":"pith:AW3T3FI7","canonical_record":{"source":{"id":"2110.04282","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-08T17:50:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9426022d53bd1816602949adb37eb49bacf3140db71d867afc186090229b2a1","abstract_canon_sha256":"b233682d336895d0ebf3d04ba60b8b03df91612fbc3b63345812d9f272110682"},"schema_version":"1.0"},"canonical_sha256":"05b73d951f3ac47673226ba04570aa9403331a02371107f47267a89ea9f8cc9a","source":{"kind":"arxiv","id":"2110.04282","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04282","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04282v2","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04282","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"AW3T3FI7HLCH","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"AW3T3FI7HLCHM4ZC","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"AW3T3FI7","created_at":"2026-07-05T04:13:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AW3T3FI7HLCHM4ZCNOQEK4FKSQ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04282","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-08T17:50:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9426022d53bd1816602949adb37eb49bacf3140db71d867afc186090229b2a1","abstract_canon_sha256":"b233682d336895d0ebf3d04ba60b8b03df91612fbc3b63345812d9f272110682"},"schema_version":"1.0"},"canonical_sha256":"05b73d951f3ac47673226ba04570aa9403331a02371107f47267a89ea9f8cc9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:43.780088Z","signature_b64":"yfeWOurns4rcm+yn6U6jdYUwr2i3qpqmLAomMoVXug6DzdqIWDflN+BcDEPPnIjfjpWy0WK57X5TTNXkGxo9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05b73d951f3ac47673226ba04570aa9403331a02371107f47267a89ea9f8cc9a","last_reissued_at":"2026-07-05T04:13:43.779629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:43.779629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04282","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":"2026-07-05T04:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrTwLydtEzcp06OPMJjvyNvNkZOsQ3aH4rfUJfKm3sJo/gO3wnnXN/zRGD6CGiiJD0QNlQGyv38pO+bAYXcPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:25:37.321250Z"},"content_sha256":"440ac1fc5e82fb6e31dc759e9ea45be9a0c7c9738752e04e4746a35f90d2817b","schema_version":"1.0","event_id":"sha256:440ac1fc5e82fb6e31dc759e9ea45be9a0c7c9738752e04e4746a35f90d2817b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AW3T3FI7HLCHM4ZCNOQEK4FKSQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Field Extraction from Forms with Unlabeled Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Kazuma Hashimoto, Mingfei Gao, Nikhil Naik, Ran Xu, Zeyuan Chen","submitted_at":"2021-10-08T17:50:12Z","abstract_excerpt":"We propose a novel framework to conduct field extraction from forms with unlabeled data. To bootstrap the training process, we develop a rule-based method for mining noisy pseudo-labels from unlabeled forms. Using the supervisory signal from the pseudo-labels, we extract a discriminative token representation from a transformer-based model by modeling the interaction between text in the form. To prevent the model from overfitting to label noise, we introduce a refinement module based on a progressive pseudo-label ensemble. Experimental results demonstrate the effectiveness of our framework."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04282","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/2110.04282/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":"2026-07-05T04:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8i+dG43R0iw6mB1X5tbEMHJqEfXf2B5GfHIFINyqANQvoGxZrDp01VMVqcmg8iYK8p2fuzuRrgindoeN8PtrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:25:37.322139Z"},"content_sha256":"38653ef290fe382f18b05481c12414a0605c1534c3b2e8e337097e4f793ff249","schema_version":"1.0","event_id":"sha256:38653ef290fe382f18b05481c12414a0605c1534c3b2e8e337097e4f793ff249"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AW3T3FI7HLCHM4ZCNOQEK4FKSQ/bundle.json","state_url":"https://pith.science/pith/AW3T3FI7HLCHM4ZCNOQEK4FKSQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AW3T3FI7HLCHM4ZCNOQEK4FKSQ/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":"2026-08-14T19:25:37Z","links":{"resolver":"https://pith.science/pith/AW3T3FI7HLCHM4ZCNOQEK4FKSQ","bundle":"https://pith.science/pith/AW3T3FI7HLCHM4ZCNOQEK4FKSQ/bundle.json","state":"https://pith.science/pith/AW3T3FI7HLCHM4ZCNOQEK4FKSQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AW3T3FI7HLCHM4ZCNOQEK4FKSQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AW3T3FI7HLCHM4ZCNOQEK4FKSQ","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":"b233682d336895d0ebf3d04ba60b8b03df91612fbc3b63345812d9f272110682","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-08T17:50:12Z","title_canon_sha256":"d9426022d53bd1816602949adb37eb49bacf3140db71d867afc186090229b2a1"},"schema_version":"1.0","source":{"id":"2110.04282","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04282","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04282v2","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04282","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"AW3T3FI7HLCH","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"AW3T3FI7HLCHM4ZC","created_at":"2026-07-05T04:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"AW3T3FI7","created_at":"2026-07-05T04:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:38653ef290fe382f18b05481c12414a0605c1534c3b2e8e337097e4f793ff249","target":"graph","created_at":"2026-07-05T04:13:43Z","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/2110.04282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel framework to conduct field extraction from forms with unlabeled data. To bootstrap the training process, we develop a rule-based method for mining noisy pseudo-labels from unlabeled forms. Using the supervisory signal from the pseudo-labels, we extract a discriminative token representation from a transformer-based model by modeling the interaction between text in the form. To prevent the model from overfitting to label noise, we introduce a refinement module based on a progressive pseudo-label ensemble. Experimental results demonstrate the effectiveness of our framework.","authors_text":"Caiming Xiong, Kazuma Hashimoto, Mingfei Gao, Nikhil Naik, Ran Xu, Zeyuan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-08T17:50:12Z","title":"Field Extraction from Forms with Unlabeled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04282","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":"sha256:440ac1fc5e82fb6e31dc759e9ea45be9a0c7c9738752e04e4746a35f90d2817b","target":"record","created_at":"2026-07-05T04:13:43Z","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":"b233682d336895d0ebf3d04ba60b8b03df91612fbc3b63345812d9f272110682","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-08T17:50:12Z","title_canon_sha256":"d9426022d53bd1816602949adb37eb49bacf3140db71d867afc186090229b2a1"},"schema_version":"1.0","source":{"id":"2110.04282","kind":"arxiv","version":2}},"canonical_sha256":"05b73d951f3ac47673226ba04570aa9403331a02371107f47267a89ea9f8cc9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05b73d951f3ac47673226ba04570aa9403331a02371107f47267a89ea9f8cc9a","first_computed_at":"2026-07-05T04:13:43.779629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:43.779629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yfeWOurns4rcm+yn6U6jdYUwr2i3qpqmLAomMoVXug6DzdqIWDflN+BcDEPPnIjfjpWy0WK57X5TTNXkGxo9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:43.780088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04282","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:440ac1fc5e82fb6e31dc759e9ea45be9a0c7c9738752e04e4746a35f90d2817b","sha256:38653ef290fe382f18b05481c12414a0605c1534c3b2e8e337097e4f793ff249"],"state_sha256":"39e9b0c86c2baaabcf49a90f6f46f6d6d1408207d622cf9671cb14f90cf8ddca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LZZPeZJjUWkJZCdm5ZeJ/KUYvt+jBJpk9mOMoa4sdye8VGwqs9q1bksZ+6hxm0W6qMMLaWeLSyoyGn3dPXUsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:25:37.330582Z","bundle_sha256":"2b64fe6c964078b52c7e4b793d16d75026f8adf4ddd104a94c5ff01ae2faacf5"}}