{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5BAXPXXPGYAQHAT2LRJN7SC2YG","short_pith_number":"pith:5BAXPXXP","canonical_record":{"source":{"id":"1905.01566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-04T23:22:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d8da4e94a3f2f316d4adb7416f377c31b7bcbae2f007de926fb6a4b056e2a07","abstract_canon_sha256":"4e85cdaadfcf84810bc1c4924a0f1f9395bf9376ea6cb04b2ab87bc89d22e662"},"schema_version":"1.0"},"canonical_sha256":"e84177deef360103827a5c52dfc85ac1a9ddcbf968ea864765eb88f2fde131c8","source":{"kind":"arxiv","id":"1905.01566","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01566","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01566v1","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01566","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"5BAXPXXPGYAQ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5BAXPXXPGYAQHAT2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5BAXPXXP","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5BAXPXXPGYAQHAT2LRJN7SC2YG","target":"record","payload":{"canonical_record":{"source":{"id":"1905.01566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-04T23:22:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d8da4e94a3f2f316d4adb7416f377c31b7bcbae2f007de926fb6a4b056e2a07","abstract_canon_sha256":"4e85cdaadfcf84810bc1c4924a0f1f9395bf9376ea6cb04b2ab87bc89d22e662"},"schema_version":"1.0"},"canonical_sha256":"e84177deef360103827a5c52dfc85ac1a9ddcbf968ea864765eb88f2fde131c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:58.164120Z","signature_b64":"1zmd4c8jXtXC8YipjfJp+niRQVrkuszTO2cFB0yHU9NxicMD621e3FMmCHD0Wwijq1JfQN5niRu5piA7qK5TDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e84177deef360103827a5c52dfc85ac1a9ddcbf968ea864765eb88f2fde131c8","last_reissued_at":"2026-05-17T23:46:58.163513Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:58.163513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.01566","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":"2026-05-17T23:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H59p2qHRK2syNiKpGJIGdm22KVUFflIuzFH21J/EBIhkQH7VsrzN7UfQX0CT+CI5mxX9fjDxv7tK5jd6jLSaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:14:35.328339Z"},"content_sha256":"2a8e6be05b09deb5bbc80fa8e2587df973b9c08aa665ce433b47650da7c5deb8","schema_version":"1.0","event_id":"sha256:2a8e6be05b09deb5bbc80fa8e2587df973b9c08aa665ce433b47650da7c5deb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5BAXPXXPGYAQHAT2LRJN7SC2YG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Denoise Distantly-Labeled Data for Entity Typing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Yasumasa Onoe","submitted_at":"2019-05-04T23:22:51Z","abstract_excerpt":"Distantly-labeled data can be used to scale up training of statistical models, but it is typically noisy and that noise can vary with the distant labeling technique. In this work, we propose a two-stage procedure for handling this type of data: denoise it with a learned model, then train our final model on clean and denoised distant data with standard supervised training. Our denoising approach consists of two parts. First, a filtering function discards examples from the distantly labeled data that are wholly unusable. Second, a relabeling function repairs noisy labels for the retained example"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01566","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":"2026-05-17T23:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQbjhS+Am/WRagvYZbfvJ1bCBlzKLZUk9P0m47AP4itHX9+S2tdMDurmcDPlyVXELX+hStHNJKyaDTC5q7gfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:14:35.328690Z"},"content_sha256":"29c35602eae915020a64afec274781457eda59f6e014ae39dbf25d2f6c510983","schema_version":"1.0","event_id":"sha256:29c35602eae915020a64afec274781457eda59f6e014ae39dbf25d2f6c510983"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BAXPXXPGYAQHAT2LRJN7SC2YG/bundle.json","state_url":"https://pith.science/pith/5BAXPXXPGYAQHAT2LRJN7SC2YG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BAXPXXPGYAQHAT2LRJN7SC2YG/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":"2026-06-09T14:14:35Z","links":{"resolver":"https://pith.science/pith/5BAXPXXPGYAQHAT2LRJN7SC2YG","bundle":"https://pith.science/pith/5BAXPXXPGYAQHAT2LRJN7SC2YG/bundle.json","state":"https://pith.science/pith/5BAXPXXPGYAQHAT2LRJN7SC2YG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BAXPXXPGYAQHAT2LRJN7SC2YG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5BAXPXXPGYAQHAT2LRJN7SC2YG","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":"4e85cdaadfcf84810bc1c4924a0f1f9395bf9376ea6cb04b2ab87bc89d22e662","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-04T23:22:51Z","title_canon_sha256":"6d8da4e94a3f2f316d4adb7416f377c31b7bcbae2f007de926fb6a4b056e2a07"},"schema_version":"1.0","source":{"id":"1905.01566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01566","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01566v1","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01566","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"5BAXPXXPGYAQ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5BAXPXXPGYAQHAT2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5BAXPXXP","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:29c35602eae915020a64afec274781457eda59f6e014ae39dbf25d2f6c510983","target":"graph","created_at":"2026-05-17T23:46:58Z","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":"Distantly-labeled data can be used to scale up training of statistical models, but it is typically noisy and that noise can vary with the distant labeling technique. In this work, we propose a two-stage procedure for handling this type of data: denoise it with a learned model, then train our final model on clean and denoised distant data with standard supervised training. Our denoising approach consists of two parts. First, a filtering function discards examples from the distantly labeled data that are wholly unusable. Second, a relabeling function repairs noisy labels for the retained example","authors_text":"Greg Durrett, Yasumasa Onoe","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-04T23:22:51Z","title":"Learning to Denoise Distantly-Labeled Data for Entity Typing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01566","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":"sha256:2a8e6be05b09deb5bbc80fa8e2587df973b9c08aa665ce433b47650da7c5deb8","target":"record","created_at":"2026-05-17T23:46:58Z","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":"4e85cdaadfcf84810bc1c4924a0f1f9395bf9376ea6cb04b2ab87bc89d22e662","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-04T23:22:51Z","title_canon_sha256":"6d8da4e94a3f2f316d4adb7416f377c31b7bcbae2f007de926fb6a4b056e2a07"},"schema_version":"1.0","source":{"id":"1905.01566","kind":"arxiv","version":1}},"canonical_sha256":"e84177deef360103827a5c52dfc85ac1a9ddcbf968ea864765eb88f2fde131c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e84177deef360103827a5c52dfc85ac1a9ddcbf968ea864765eb88f2fde131c8","first_computed_at":"2026-05-17T23:46:58.163513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:58.163513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1zmd4c8jXtXC8YipjfJp+niRQVrkuszTO2cFB0yHU9NxicMD621e3FMmCHD0Wwijq1JfQN5niRu5piA7qK5TDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:58.164120Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.01566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a8e6be05b09deb5bbc80fa8e2587df973b9c08aa665ce433b47650da7c5deb8","sha256:29c35602eae915020a64afec274781457eda59f6e014ae39dbf25d2f6c510983"],"state_sha256":"7d78d99aa48419d23131cc881364739e8d671c4204924c71f7b6d18a2a075dc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BP5fEkKuck+AIf+qpjOo3vwRrXprgyonlRKhqEsCp0m8AEr2stBavAANclaqlFqdFTMzOETKoUKiGFbHUDSmDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T14:14:35.330608Z","bundle_sha256":"1a7e66130679a3f5dedcc6d4b4fd28915e62c5b44852d2fa45aa87cb129e7517"}}