{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:S3VQRDTK76LXPH3G5S6EJTJX4N","short_pith_number":"pith:S3VQRDTK","canonical_record":{"source":{"id":"2012.04194","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-08T03:37:50Z","cross_cats_sorted":[],"title_canon_sha256":"e014c55c7e33d27093b59bf4389c6821d8003e25df73036a185f3c0d42c83648","abstract_canon_sha256":"c535af0593a8aa63cdde5f2993c4961d31051f563fda909a1cdb4f03644793eb"},"schema_version":"1.0"},"canonical_sha256":"96eb088e6aff97779f66ecbc44cd37e3781e5993c8a59a966df061d3eb0f605f","source":{"kind":"arxiv","id":"2012.04194","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04194","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04194v1","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04194","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_12","alias_value":"S3VQRDTK76LX","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_16","alias_value":"S3VQRDTK76LXPH3G","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_8","alias_value":"S3VQRDTK","created_at":"2026-07-05T01:58:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:S3VQRDTK76LXPH3G5S6EJTJX4N","target":"record","payload":{"canonical_record":{"source":{"id":"2012.04194","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-08T03:37:50Z","cross_cats_sorted":[],"title_canon_sha256":"e014c55c7e33d27093b59bf4389c6821d8003e25df73036a185f3c0d42c83648","abstract_canon_sha256":"c535af0593a8aa63cdde5f2993c4961d31051f563fda909a1cdb4f03644793eb"},"schema_version":"1.0"},"canonical_sha256":"96eb088e6aff97779f66ecbc44cd37e3781e5993c8a59a966df061d3eb0f605f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:01.754393Z","signature_b64":"AExnW8Dyfyx/mGuyfml3q6oGP6saKKEXX5M/56t8cGy6swe1ldDqa05ZgSAbgNV6e8JO0chf2n6MHyTRfHQcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96eb088e6aff97779f66ecbc44cd37e3781e5993c8a59a966df061d3eb0f605f","last_reissued_at":"2026-07-05T01:58:01.753998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:01.753998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.04194","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":"2026-07-05T01:58:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pF82YMyMRqWnUj09j7WKMAYcx/5Hy06bLdqCFWargnOSUGHgDG80FaUunRnGPJD8vssjsXopmWxIMmVdKVlxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:33:15.434621Z"},"content_sha256":"dd3e93f5c6e7cf897ff21d5cfa82b9d78433a01dce416f8df1ec20004d20d0a0","schema_version":"1.0","event_id":"sha256:dd3e93f5c6e7cf897ff21d5cfa82b9d78433a01dce416f8df1ec20004d20d0a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:S3VQRDTK76LXPH3G5S6EJTJX4N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Label Refinement Improves Dataless Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Karl Stratos, Kevin Gimpel, Zewei Chu","submitted_at":"2020-12-08T03:37:50Z","abstract_excerpt":"Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description. While promising, it crucially relies on accurate descriptions of the label set for each downstream task. This reliance causes dataless classifiers to be highly sensitive to the choice of label descriptions and hinders the broader application of dataless classification in practice. In this paper, we ask the following question: how can we improve dataless text classification using the inputs of the downstream task dataset? Our primar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04194","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/2012.04194/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":"2026-07-05T01:58:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"abI8bivUJvWI3tU7u8CLJe+L3rNd7scdF24yxvBSYkGDlhwZT3qTZTq9m0LToinSbE+qLXza2995lzuCTpcLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:33:15.435634Z"},"content_sha256":"f6df737a94a2f3eca95e766c6c35cdac95f53828ec2fa8fbaa3c10152828bb99","schema_version":"1.0","event_id":"sha256:f6df737a94a2f3eca95e766c6c35cdac95f53828ec2fa8fbaa3c10152828bb99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S3VQRDTK76LXPH3G5S6EJTJX4N/bundle.json","state_url":"https://pith.science/pith/S3VQRDTK76LXPH3G5S6EJTJX4N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S3VQRDTK76LXPH3G5S6EJTJX4N/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":"2026-08-19T04:33:15Z","links":{"resolver":"https://pith.science/pith/S3VQRDTK76LXPH3G5S6EJTJX4N","bundle":"https://pith.science/pith/S3VQRDTK76LXPH3G5S6EJTJX4N/bundle.json","state":"https://pith.science/pith/S3VQRDTK76LXPH3G5S6EJTJX4N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S3VQRDTK76LXPH3G5S6EJTJX4N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:S3VQRDTK76LXPH3G5S6EJTJX4N","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":"c535af0593a8aa63cdde5f2993c4961d31051f563fda909a1cdb4f03644793eb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-08T03:37:50Z","title_canon_sha256":"e014c55c7e33d27093b59bf4389c6821d8003e25df73036a185f3c0d42c83648"},"schema_version":"1.0","source":{"id":"2012.04194","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04194","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04194v1","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04194","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_12","alias_value":"S3VQRDTK76LX","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_16","alias_value":"S3VQRDTK76LXPH3G","created_at":"2026-07-05T01:58:01Z"},{"alias_kind":"pith_short_8","alias_value":"S3VQRDTK","created_at":"2026-07-05T01:58:01Z"}],"graph_snapshots":[{"event_id":"sha256:f6df737a94a2f3eca95e766c6c35cdac95f53828ec2fa8fbaa3c10152828bb99","target":"graph","created_at":"2026-07-05T01:58:01Z","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/2012.04194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description. While promising, it crucially relies on accurate descriptions of the label set for each downstream task. This reliance causes dataless classifiers to be highly sensitive to the choice of label descriptions and hinders the broader application of dataless classification in practice. In this paper, we ask the following question: how can we improve dataless text classification using the inputs of the downstream task dataset? Our primar","authors_text":"Karl Stratos, Kevin Gimpel, Zewei Chu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-08T03:37:50Z","title":"Unsupervised Label Refinement Improves Dataless Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04194","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:dd3e93f5c6e7cf897ff21d5cfa82b9d78433a01dce416f8df1ec20004d20d0a0","target":"record","created_at":"2026-07-05T01:58:01Z","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":"c535af0593a8aa63cdde5f2993c4961d31051f563fda909a1cdb4f03644793eb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-08T03:37:50Z","title_canon_sha256":"e014c55c7e33d27093b59bf4389c6821d8003e25df73036a185f3c0d42c83648"},"schema_version":"1.0","source":{"id":"2012.04194","kind":"arxiv","version":1}},"canonical_sha256":"96eb088e6aff97779f66ecbc44cd37e3781e5993c8a59a966df061d3eb0f605f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96eb088e6aff97779f66ecbc44cd37e3781e5993c8a59a966df061d3eb0f605f","first_computed_at":"2026-07-05T01:58:01.753998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:01.753998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AExnW8Dyfyx/mGuyfml3q6oGP6saKKEXX5M/56t8cGy6swe1ldDqa05ZgSAbgNV6e8JO0chf2n6MHyTRfHQcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:01.754393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.04194","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd3e93f5c6e7cf897ff21d5cfa82b9d78433a01dce416f8df1ec20004d20d0a0","sha256:f6df737a94a2f3eca95e766c6c35cdac95f53828ec2fa8fbaa3c10152828bb99"],"state_sha256":"788f4655b5679b9a6391bdcf766a62d13ef17262c0ed343b303cac96155708b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhoV/CCXWuZVmJg3mWiAIEquVenuupn62Qtus5Fr+2ZhzM9QmSZc6YkYrvOY6CORc/lhRYVxs2D1lurMZJfTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:33:15.460387Z","bundle_sha256":"92bf2e6cc1d8b6f28776cf229c2447c0f76f8d6d0e229828d89c46b8da3dc87f"}}