{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MGKIMSCC4NSHRIZQ7C3ONOLQTF","short_pith_number":"pith:MGKIMSCC","canonical_record":{"source":{"id":"1903.12008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T14:33:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b74e80ff53f2da0c7219fab3af98d37b02f2368e9067e49651b612ceb96938e","abstract_canon_sha256":"e7b6e8e1d45cd35ba2f64a303c682ec019ef9023d80421369c142b881f5921d8"},"schema_version":"1.0"},"canonical_sha256":"6194864842e36478a330f8b6e6b97099524c0805756b9977a0f7d1c8c1b46be7","source":{"kind":"arxiv","id":"1903.12008","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.12008","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"arxiv_version","alias_value":"1903.12008v1","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12008","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"pith_short_12","alias_value":"MGKIMSCC4NSH","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MGKIMSCC4NSHRIZQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MGKIMSCC","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MGKIMSCC4NSHRIZQ7C3ONOLQTF","target":"record","payload":{"canonical_record":{"source":{"id":"1903.12008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T14:33:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b74e80ff53f2da0c7219fab3af98d37b02f2368e9067e49651b612ceb96938e","abstract_canon_sha256":"e7b6e8e1d45cd35ba2f64a303c682ec019ef9023d80421369c142b881f5921d8"},"schema_version":"1.0"},"canonical_sha256":"6194864842e36478a330f8b6e6b97099524c0805756b9977a0f7d1c8c1b46be7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:38.320787Z","signature_b64":"wCexv9PLVvYAiJXXPNnKUfEerisfZRMWNUcxPIAUx6bBjMuNjLlzgR7nz9/IOv+C+Y0/PW1rRv2nRJfeaHPnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6194864842e36478a330f8b6e6b97099524c0805756b9977a0f7d1c8c1b46be7","last_reissued_at":"2026-05-17T23:49:38.320199Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:38.320199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.12008","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":"2026-05-17T23:49:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cmGHtICIPFocVvOrQODWlYjCPT5vdhhE21c4uAf/+Ky+qHhZfeNfqBK+bh/WG8qTr53XRGTLYOVzKapMhnZtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:10:38.047138Z"},"content_sha256":"7eac487b6f9fa8ab238660371e2274a13c28308bdb0971776de1eab501e51350","schema_version":"1.0","event_id":"sha256:7eac487b6f9fa8ab238660371e2274a13c28308bdb0971776de1eab501e51350"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MGKIMSCC4NSHRIZQ7C3ONOLQTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Debjit Paul, Dietrich Klakow, Michael A. Hedderich, Mittul Singh","submitted_at":"2019-03-28T14:33:50Z","abstract_excerpt":"In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is less effective due to unreliable annotations created using self-labeling of unlabeled data. We propose to combine self-training with noise handling on the self-labeled data. Directly estimating noise on the combined clean training set and self-labeled data can lead to corruption of the clean data and hence, performs worse. Thus, we propose the Clean and Noi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.12008","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":""},"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":"2026-05-17T23:49:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CMonTQKhvUywEOQuejMgODMKJaU5NtCxoyIwXYSWDf/lXVWogzHxOJXmw/dpjssfBE0hsU/a6k5qjkOLVwU8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:10:38.047549Z"},"content_sha256":"34af0ce88ec59ddf0b1644a16cfa0f693eb4fddd87ad6e43384bb6afa15dee45","schema_version":"1.0","event_id":"sha256:34af0ce88ec59ddf0b1644a16cfa0f693eb4fddd87ad6e43384bb6afa15dee45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGKIMSCC4NSHRIZQ7C3ONOLQTF/bundle.json","state_url":"https://pith.science/pith/MGKIMSCC4NSHRIZQ7C3ONOLQTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGKIMSCC4NSHRIZQ7C3ONOLQTF/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":"2026-05-28T20:10:38Z","links":{"resolver":"https://pith.science/pith/MGKIMSCC4NSHRIZQ7C3ONOLQTF","bundle":"https://pith.science/pith/MGKIMSCC4NSHRIZQ7C3ONOLQTF/bundle.json","state":"https://pith.science/pith/MGKIMSCC4NSHRIZQ7C3ONOLQTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGKIMSCC4NSHRIZQ7C3ONOLQTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MGKIMSCC4NSHRIZQ7C3ONOLQTF","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":"e7b6e8e1d45cd35ba2f64a303c682ec019ef9023d80421369c142b881f5921d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T14:33:50Z","title_canon_sha256":"4b74e80ff53f2da0c7219fab3af98d37b02f2368e9067e49651b612ceb96938e"},"schema_version":"1.0","source":{"id":"1903.12008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.12008","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"arxiv_version","alias_value":"1903.12008v1","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12008","created_at":"2026-05-17T23:49:38Z"},{"alias_kind":"pith_short_12","alias_value":"MGKIMSCC4NSH","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MGKIMSCC4NSHRIZQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MGKIMSCC","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:34af0ce88ec59ddf0b1644a16cfa0f693eb4fddd87ad6e43384bb6afa15dee45","target":"graph","created_at":"2026-05-17T23:49:38Z","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"},"paper":{"abstract_excerpt":"In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is less effective due to unreliable annotations created using self-labeling of unlabeled data. We propose to combine self-training with noise handling on the self-labeled data. Directly estimating noise on the combined clean training set and self-labeled data can lead to corruption of the clean data and hence, performs worse. Thus, we propose the Clean and Noi","authors_text":"Debjit Paul, Dietrich Klakow, Michael A. Hedderich, Mittul Singh","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T14:33:50Z","title":"Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.12008","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":"sha256:7eac487b6f9fa8ab238660371e2274a13c28308bdb0971776de1eab501e51350","target":"record","created_at":"2026-05-17T23:49:38Z","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":"e7b6e8e1d45cd35ba2f64a303c682ec019ef9023d80421369c142b881f5921d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T14:33:50Z","title_canon_sha256":"4b74e80ff53f2da0c7219fab3af98d37b02f2368e9067e49651b612ceb96938e"},"schema_version":"1.0","source":{"id":"1903.12008","kind":"arxiv","version":1}},"canonical_sha256":"6194864842e36478a330f8b6e6b97099524c0805756b9977a0f7d1c8c1b46be7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6194864842e36478a330f8b6e6b97099524c0805756b9977a0f7d1c8c1b46be7","first_computed_at":"2026-05-17T23:49:38.320199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:38.320199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wCexv9PLVvYAiJXXPNnKUfEerisfZRMWNUcxPIAUx6bBjMuNjLlzgR7nz9/IOv+C+Y0/PW1rRv2nRJfeaHPnAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:38.320787Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.12008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eac487b6f9fa8ab238660371e2274a13c28308bdb0971776de1eab501e51350","sha256:34af0ce88ec59ddf0b1644a16cfa0f693eb4fddd87ad6e43384bb6afa15dee45"],"state_sha256":"8d91692e57512e9e402f64f59d0a1ff73af6e7fb394c1f635fcb26588e3a4768"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jimlTL38/bVw8cZyDydxoFnEcDUC878viuLaQeAe/R8kqCSAmTdvQGCU0KOKugY/NORUMy88mo/S12QFfDtvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:10:38.050659Z","bundle_sha256":"a42ab4d1f35c29464669cc6da96da62926c308fde12e83e34eed2b5ac3e639d0"}}