{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WEVZBZQWUN5TIWWAIK2JSFNYTO","short_pith_number":"pith:WEVZBZQW","canonical_record":{"source":{"id":"2104.09765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-20T05:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"ee396d7d6165cff85a85d704814fc405e53ee8338be3273741a246cb75878caa","abstract_canon_sha256":"9603c8c48aa49ef20b7f26602bc4d1264470fcb51cae1e8c7c736ea75a74a328"},"schema_version":"1.0"},"canonical_sha256":"b12b90e616a37b345ac042b49915b89b83747bd57bf29aa0584fcd416335e23f","source":{"kind":"arxiv","id":"2104.09765","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09765","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09765v1","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09765","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"pith_short_12","alias_value":"WEVZBZQWUN5T","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"pith_short_16","alias_value":"WEVZBZQWUN5TIWWA","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"pith_short_8","alias_value":"WEVZBZQW","created_at":"2026-07-05T02:33:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WEVZBZQWUN5TIWWAIK2JSFNYTO","target":"record","payload":{"canonical_record":{"source":{"id":"2104.09765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-20T05:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"ee396d7d6165cff85a85d704814fc405e53ee8338be3273741a246cb75878caa","abstract_canon_sha256":"9603c8c48aa49ef20b7f26602bc4d1264470fcb51cae1e8c7c736ea75a74a328"},"schema_version":"1.0"},"canonical_sha256":"b12b90e616a37b345ac042b49915b89b83747bd57bf29aa0584fcd416335e23f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:36.772670Z","signature_b64":"vJlxEcBTzEk8YRIyx1p7zAie4DImbZ95K/Oj3D3mticBxLjg0C+vqpL/y1UoRSpqdviEw02sf3fXGARQTnIQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b12b90e616a37b345ac042b49915b89b83747bd57bf29aa0584fcd416335e23f","last_reissued_at":"2026-07-05T02:33:36.772273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:36.772273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.09765","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":"2026-07-05T02:33:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"heMjiq8VQHx2Kdn3KM/V5yX1QtJLeVsp2FTa+IrpzONzTPBWQgF70Tte/9+MmdG3/58sgzTQcsyEwgIfJPf5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:53:13.671292Z"},"content_sha256":"78d616e197d053530e423e5b3323f0bd50ff3ea25ff5988c9d3d8966a65ba77b","schema_version":"1.0","event_id":"sha256:78d616e197d053530e423e5b3323f0bd50ff3ea25ff5988c9d3d8966a65ba77b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WEVZBZQWUN5TIWWAIK2JSFNYTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seed Word Selection for Weakly-Supervised Text Classification with Unsupervised Error Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshay Bhatia, Dittaya Wanvarie, Yiping Jin","submitted_at":"2021-04-20T05:10:40Z","abstract_excerpt":"Weakly-supervised text classification aims to induce text classifiers from only a few user-provided seed words. The vast majority of previous work assumes high-quality seed words are given. However, the expert-annotated seed words are sometimes non-trivial to come up with. Furthermore, in the weakly-supervised learning setting, we do not have any labeled document to measure the seed words' efficacy, making the seed word selection process \"a walk in the dark\". In this work, we remove the need for expert-curated seed words by first mining (noisy) candidate seed words associated with the category"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09765","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/2104.09765/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":"2026-07-05T02:33:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IMg7yqMmXLt4ku9UbO55OjoQYLsKE++N9mSxp0qWaW4f6neQS9gLfMZtzo+5vHEFhjBlxNrqnWM9cckHYz3KCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:53:13.671804Z"},"content_sha256":"bb323592aeb1385eca4ee865da03f68d2f8adbc915b77cde9085d5aa982b477a","schema_version":"1.0","event_id":"sha256:bb323592aeb1385eca4ee865da03f68d2f8adbc915b77cde9085d5aa982b477a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEVZBZQWUN5TIWWAIK2JSFNYTO/bundle.json","state_url":"https://pith.science/pith/WEVZBZQWUN5TIWWAIK2JSFNYTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEVZBZQWUN5TIWWAIK2JSFNYTO/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":"2026-08-23T17:53:13Z","links":{"resolver":"https://pith.science/pith/WEVZBZQWUN5TIWWAIK2JSFNYTO","bundle":"https://pith.science/pith/WEVZBZQWUN5TIWWAIK2JSFNYTO/bundle.json","state":"https://pith.science/pith/WEVZBZQWUN5TIWWAIK2JSFNYTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEVZBZQWUN5TIWWAIK2JSFNYTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WEVZBZQWUN5TIWWAIK2JSFNYTO","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":"9603c8c48aa49ef20b7f26602bc4d1264470fcb51cae1e8c7c736ea75a74a328","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-20T05:10:40Z","title_canon_sha256":"ee396d7d6165cff85a85d704814fc405e53ee8338be3273741a246cb75878caa"},"schema_version":"1.0","source":{"id":"2104.09765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09765","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09765v1","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09765","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"pith_short_12","alias_value":"WEVZBZQWUN5T","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"pith_short_16","alias_value":"WEVZBZQWUN5TIWWA","created_at":"2026-07-05T02:33:36Z"},{"alias_kind":"pith_short_8","alias_value":"WEVZBZQW","created_at":"2026-07-05T02:33:36Z"}],"graph_snapshots":[{"event_id":"sha256:bb323592aeb1385eca4ee865da03f68d2f8adbc915b77cde9085d5aa982b477a","target":"graph","created_at":"2026-07-05T02:33:36Z","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/2104.09765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Weakly-supervised text classification aims to induce text classifiers from only a few user-provided seed words. The vast majority of previous work assumes high-quality seed words are given. However, the expert-annotated seed words are sometimes non-trivial to come up with. Furthermore, in the weakly-supervised learning setting, we do not have any labeled document to measure the seed words' efficacy, making the seed word selection process \"a walk in the dark\". In this work, we remove the need for expert-curated seed words by first mining (noisy) candidate seed words associated with the category","authors_text":"Akshay Bhatia, Dittaya Wanvarie, Yiping Jin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-20T05:10:40Z","title":"Seed Word Selection for Weakly-Supervised Text Classification with Unsupervised Error Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09765","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":"sha256:78d616e197d053530e423e5b3323f0bd50ff3ea25ff5988c9d3d8966a65ba77b","target":"record","created_at":"2026-07-05T02:33:36Z","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":"9603c8c48aa49ef20b7f26602bc4d1264470fcb51cae1e8c7c736ea75a74a328","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-20T05:10:40Z","title_canon_sha256":"ee396d7d6165cff85a85d704814fc405e53ee8338be3273741a246cb75878caa"},"schema_version":"1.0","source":{"id":"2104.09765","kind":"arxiv","version":1}},"canonical_sha256":"b12b90e616a37b345ac042b49915b89b83747bd57bf29aa0584fcd416335e23f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b12b90e616a37b345ac042b49915b89b83747bd57bf29aa0584fcd416335e23f","first_computed_at":"2026-07-05T02:33:36.772273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:36.772273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vJlxEcBTzEk8YRIyx1p7zAie4DImbZ95K/Oj3D3mticBxLjg0C+vqpL/y1UoRSpqdviEw02sf3fXGARQTnIQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:36.772670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78d616e197d053530e423e5b3323f0bd50ff3ea25ff5988c9d3d8966a65ba77b","sha256:bb323592aeb1385eca4ee865da03f68d2f8adbc915b77cde9085d5aa982b477a"],"state_sha256":"e1795e9205cb922628d07bef188d729988e79934e539e58cbae12a4078b561ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"volmJhV+w2HM+jL/PY/SbXu7T38v0BlcQ25KdcqIPc4BpJS4h/8tSTAskbfZwsQ1xTuZ10LoEXCwl0gPWu23AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:53:13.676992Z","bundle_sha256":"689368b1fa3f7756b73458b11a598801c1e39d15d427dd14fb6c28675a9890b6"}}