{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YUBFNSHMFX4QZVO7QPGAGENF6U","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":"2055072155e3bd524b5c6540dba5162274e31234515e61b15470356e8bb2e1fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T04:01:02Z","title_canon_sha256":"a28b4820dc53edbc0972f08c18323df1771ec284e82d1a11c5fcb3992fed260c"},"schema_version":"1.0","source":{"id":"2106.09233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09233","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09233v1","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09233","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"pith_short_12","alias_value":"YUBFNSHMFX4Q","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"pith_short_16","alias_value":"YUBFNSHMFX4QZVO7","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"pith_short_8","alias_value":"YUBFNSHM","created_at":"2026-07-05T02:50:13Z"}],"graph_snapshots":[{"event_id":"sha256:8893a6d297be74e649785f53bb56a4e8e4aecaaa5024995fb28484daf542ec10","target":"graph","created_at":"2026-07-05T02:50:13Z","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/2106.09233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore undermines the effectiveness and the robustness of the learned models. In this paper, we fundamentally explain the dictionary bias via a Structural Causal Model (SCM), categorize the bias into intra-dictionary and inter-dictionary biases, and identify their causes. Based on the SCM, we learn de-biased DS-NER via causal interventions. For intra-dic","authors_text":"Hongyu Lin, Le Sun, Wenkai Zhang, Xianpei Han","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T04:01:02Z","title":"De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09233","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":"sha256:6ccbee9360b0eac6833a059b3f2d36e3694205d8d98bc37c01052bc9e9780e38","target":"record","created_at":"2026-07-05T02:50:13Z","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":"2055072155e3bd524b5c6540dba5162274e31234515e61b15470356e8bb2e1fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T04:01:02Z","title_canon_sha256":"a28b4820dc53edbc0972f08c18323df1771ec284e82d1a11c5fcb3992fed260c"},"schema_version":"1.0","source":{"id":"2106.09233","kind":"arxiv","version":1}},"canonical_sha256":"c50256c8ec2df90cd5df83cc0311a5f521b7c0dfd0cb79bafa29ea6b2f4b2e97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c50256c8ec2df90cd5df83cc0311a5f521b7c0dfd0cb79bafa29ea6b2f4b2e97","first_computed_at":"2026-07-05T02:50:13.899061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:13.899061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ktW2OzCYlYCH3F7KZVo7DnJ11WZ3f37zV6Zg5hItfunvBgCLaRLzFG482MMvIamVBAK8tP22dcAdWS/XfVMCAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:13.899420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ccbee9360b0eac6833a059b3f2d36e3694205d8d98bc37c01052bc9e9780e38","sha256:8893a6d297be74e649785f53bb56a4e8e4aecaaa5024995fb28484daf542ec10"],"state_sha256":"837a8987ce34f103e060c342cc6639861131234341ba7ace20d11997104d5d29"}