{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KT36TTRHG2VH57TBXJX27RTFCL","short_pith_number":"pith:KT36TTRH","canonical_record":{"source":{"id":"1912.07095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-15T19:33:25Z","cross_cats_sorted":[],"title_canon_sha256":"d413366d1b5f5f56559f49e089e47e517e859d59e1e129d8f75c87632306b7d0","abstract_canon_sha256":"68ab73dd1a4cbebee9388818e6abe56042433149ae331d274fe922c7de34238e"},"schema_version":"1.0"},"canonical_sha256":"54f7e9ce2736aa7efe61ba6fafc66512e888fbc6cfa9902b6c90968d6e93758d","source":{"kind":"arxiv","id":"1912.07095","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.07095","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"1912.07095v1","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07095","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"KT36TTRHG2VH","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"KT36TTRHG2VH57TB","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"KT36TTRH","created_at":"2026-07-05T00:26:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KT36TTRHG2VH57TBXJX27RTFCL","target":"record","payload":{"canonical_record":{"source":{"id":"1912.07095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-15T19:33:25Z","cross_cats_sorted":[],"title_canon_sha256":"d413366d1b5f5f56559f49e089e47e517e859d59e1e129d8f75c87632306b7d0","abstract_canon_sha256":"68ab73dd1a4cbebee9388818e6abe56042433149ae331d274fe922c7de34238e"},"schema_version":"1.0"},"canonical_sha256":"54f7e9ce2736aa7efe61ba6fafc66512e888fbc6cfa9902b6c90968d6e93758d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:18.476006Z","signature_b64":"4wVa6fwmDeGHAnH6qXRimqwkB1knesQv794wckocs67E64q2gQYKgJV0S09TVjeJc2fMFAqXf4Nq8HEMrGopAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54f7e9ce2736aa7efe61ba6fafc66512e888fbc6cfa9902b6c90968d6e93758d","last_reissued_at":"2026-07-05T00:26:18.475567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:18.475567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.07095","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":"2026-07-05T00:26:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VO+T9RAWA2N62YBeeDG3pmPJl7w99tdCIe5Zfe+QlHe5u4AnYQpooVYCfBPlr+GpYCXsVqHHFl6NxVO++YAqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:21:50.338937Z"},"content_sha256":"90f54a773d177c684289befd41f45daef6f24bd9aea4a44b16b4326ae57977a9","schema_version":"1.0","event_id":"sha256:90f54a773d177c684289befd41f45daef6f24bd9aea4a44b16b4326ae57977a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KT36TTRHG2VH57TBXJX27RTFCL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Named Entity Recognition with Truecasing Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Nitish Gupta, Stephen Mayhew","submitted_at":"2019-12-15T19:33:25Z","abstract_excerpt":"Although modern named entity recognition (NER) systems show impressive performance on standard datasets, they perform poorly when presented with noisy data. In particular, capitalization is a strong signal for entities in many languages, and even state of the art models overfit to this feature, with drastically lower performance on uncapitalized text. In this work, we address the problem of robustness of NER systems in data with noisy or uncertain casing, using a pretraining objective that predicts casing in text, or a truecaser, leveraging unlabeled data. The pretrained truecaser is combined "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07095","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/1912.07095/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":"2026-07-05T00:26:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DeppKKDw1K73ixtds0bnmZJWPMRq8s1VIXpm+1548Iec9ZE4YIRO2amzK4btGVzq+RFd5kvuGc+6rmXCpcijDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:21:50.339316Z"},"content_sha256":"972a33dd50ea4eb4df31d9d95825ae3a83c9d3ac22a554cc0c275b336ae4ae08","schema_version":"1.0","event_id":"sha256:972a33dd50ea4eb4df31d9d95825ae3a83c9d3ac22a554cc0c275b336ae4ae08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KT36TTRHG2VH57TBXJX27RTFCL/bundle.json","state_url":"https://pith.science/pith/KT36TTRHG2VH57TBXJX27RTFCL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KT36TTRHG2VH57TBXJX27RTFCL/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":"2026-08-05T11:21:50Z","links":{"resolver":"https://pith.science/pith/KT36TTRHG2VH57TBXJX27RTFCL","bundle":"https://pith.science/pith/KT36TTRHG2VH57TBXJX27RTFCL/bundle.json","state":"https://pith.science/pith/KT36TTRHG2VH57TBXJX27RTFCL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KT36TTRHG2VH57TBXJX27RTFCL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KT36TTRHG2VH57TBXJX27RTFCL","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":"68ab73dd1a4cbebee9388818e6abe56042433149ae331d274fe922c7de34238e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-15T19:33:25Z","title_canon_sha256":"d413366d1b5f5f56559f49e089e47e517e859d59e1e129d8f75c87632306b7d0"},"schema_version":"1.0","source":{"id":"1912.07095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.07095","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"1912.07095v1","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07095","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"KT36TTRHG2VH","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"KT36TTRHG2VH57TB","created_at":"2026-07-05T00:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"KT36TTRH","created_at":"2026-07-05T00:26:18Z"}],"graph_snapshots":[{"event_id":"sha256:972a33dd50ea4eb4df31d9d95825ae3a83c9d3ac22a554cc0c275b336ae4ae08","target":"graph","created_at":"2026-07-05T00:26:18Z","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/1912.07095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although modern named entity recognition (NER) systems show impressive performance on standard datasets, they perform poorly when presented with noisy data. In particular, capitalization is a strong signal for entities in many languages, and even state of the art models overfit to this feature, with drastically lower performance on uncapitalized text. In this work, we address the problem of robustness of NER systems in data with noisy or uncertain casing, using a pretraining objective that predicts casing in text, or a truecaser, leveraging unlabeled data. The pretrained truecaser is combined ","authors_text":"Dan Roth, Nitish Gupta, Stephen Mayhew","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-15T19:33:25Z","title":"Robust Named Entity Recognition with Truecasing Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07095","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":"sha256:90f54a773d177c684289befd41f45daef6f24bd9aea4a44b16b4326ae57977a9","target":"record","created_at":"2026-07-05T00:26:18Z","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":"68ab73dd1a4cbebee9388818e6abe56042433149ae331d274fe922c7de34238e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-15T19:33:25Z","title_canon_sha256":"d413366d1b5f5f56559f49e089e47e517e859d59e1e129d8f75c87632306b7d0"},"schema_version":"1.0","source":{"id":"1912.07095","kind":"arxiv","version":1}},"canonical_sha256":"54f7e9ce2736aa7efe61ba6fafc66512e888fbc6cfa9902b6c90968d6e93758d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54f7e9ce2736aa7efe61ba6fafc66512e888fbc6cfa9902b6c90968d6e93758d","first_computed_at":"2026-07-05T00:26:18.475567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:26:18.475567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4wVa6fwmDeGHAnH6qXRimqwkB1knesQv794wckocs67E64q2gQYKgJV0S09TVjeJc2fMFAqXf4Nq8HEMrGopAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:26:18.476006Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.07095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90f54a773d177c684289befd41f45daef6f24bd9aea4a44b16b4326ae57977a9","sha256:972a33dd50ea4eb4df31d9d95825ae3a83c9d3ac22a554cc0c275b336ae4ae08"],"state_sha256":"108cf014f9dc34913e52c33833a6051f24026e4d7d2742ae3f23e59c7704e35e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m4W9zijBS3uYz6q4dy+5XL6lSiRs5kZUUCuck48VRegAmDhWSUdr4q8V+ggX7o+UeXSRD+6GNARwiJ50aRmYBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:21:50.342038Z","bundle_sha256":"44b36f6480078bab2cb13b33fcf735f68a8935226b90198f800660f099bfe3f8"}}