{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2HZDKP4XBD4H6JCVXRQLZQZJZE","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":"820176a1914bf2f7f8b7ace5c60af5fe014023cfff5713d81d34ce7c72c51147","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T15:09:44Z","title_canon_sha256":"3cb11b69a595fd9385ce9b44d96c1808aff4953bf429902e711194dbf1f92ee6"},"schema_version":"1.0","source":{"id":"2412.09341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09341","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09341v1","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09341","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"2HZDKP4XBD4H","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"2HZDKP4XBD4H6JCV","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"2HZDKP4X","created_at":"2026-07-05T09:48:23Z"}],"graph_snapshots":[{"event_id":"sha256:3eb30ba8064bd38bb2557e658ae0ef253847855f60730c1285aed22d0f1701bd","target":"graph","created_at":"2026-07-05T09:48:23Z","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/2412.09341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generic pre-trained neural networks may struggle to produce good results in specialized domains like finance and insurance. This is due to a domain mismatch between training data and downstream tasks, as in-domain data are often scarce due to privacy constraints. In this work, we compare different pre-training strategies for LayoutLM. We show that using domain-relevant documents improves results on a named-entity recognition (NER) problem using a novel dataset of anonymized insurance-related financial documents called Payslips. Moreover, we show that we can achieve competitive results using a ","authors_text":"Antoine Ly, Benno Uthayasooriyar, Caio Corro, Franck Vermet","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T15:09:44Z","title":"Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09341","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:aba1044caba501872a8a768c6e5539a444d21c5b4b07e83964ab734ab725d304","target":"record","created_at":"2026-07-05T09:48:23Z","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":"820176a1914bf2f7f8b7ace5c60af5fe014023cfff5713d81d34ce7c72c51147","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T15:09:44Z","title_canon_sha256":"3cb11b69a595fd9385ce9b44d96c1808aff4953bf429902e711194dbf1f92ee6"},"schema_version":"1.0","source":{"id":"2412.09341","kind":"arxiv","version":1}},"canonical_sha256":"d1f2353f9708f87f2455bc60bcc329c9170ab723743c01711e1cd99aaf82a704","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1f2353f9708f87f2455bc60bcc329c9170ab723743c01711e1cd99aaf82a704","first_computed_at":"2026-07-05T09:48:23.415250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:23.415250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jIENrdO48HXj8Aw6qzWCjMvqVTeKhkh3ou2TtwAGa+Ks8M8aNABWJGK7EhxKOdywqKZ0ZQ+MZqDQtt1w5KOICg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:23.415693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aba1044caba501872a8a768c6e5539a444d21c5b4b07e83964ab734ab725d304","sha256:3eb30ba8064bd38bb2557e658ae0ef253847855f60730c1285aed22d0f1701bd"],"state_sha256":"b4a5455cd672ad35d4ec5d6ca9acfc45a4816d6760cb62d8b3678df29bbe3741"}