{"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"}