{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Z4OKGH66EECZFQLTXTSS7J7WAN","short_pith_number":"pith:Z4OKGH66","canonical_record":{"source":{"id":"2010.02458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T03:49:22Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"3449418a02b208ee007e898562bd56235793a83daa8aa95591d65e8f78bb69a5","abstract_canon_sha256":"013cbe1a00eaa01b01e81d3632c9e05102857f6325e6d7640446b09b01c55159"},"schema_version":"1.0"},"canonical_sha256":"cf1ca31fde210592c173bce52fa7f60375542033a6218c88cb288a3915c80a61","source":{"kind":"arxiv","id":"2010.02458","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02458","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02458v1","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02458","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"Z4OKGH66EECZ","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"Z4OKGH66EECZFQLT","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"Z4OKGH66","created_at":"2026-07-05T01:40:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Z4OKGH66EECZFQLTXTSS7J7WAN","target":"record","payload":{"canonical_record":{"source":{"id":"2010.02458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T03:49:22Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"3449418a02b208ee007e898562bd56235793a83daa8aa95591d65e8f78bb69a5","abstract_canon_sha256":"013cbe1a00eaa01b01e81d3632c9e05102857f6325e6d7640446b09b01c55159"},"schema_version":"1.0"},"canonical_sha256":"cf1ca31fde210592c173bce52fa7f60375542033a6218c88cb288a3915c80a61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:50.109122Z","signature_b64":"Ar8D6cctAR4K9Cewgxos83jceb78Gj4kOxDAX5d5pAv6w6P7nSSKaEXKEi7V9tHMUjZq3fggnZ5nCED9ilIRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf1ca31fde210592c173bce52fa7f60375542033a6218c88cb288a3915c80a61","last_reissued_at":"2026-07-05T01:40:50.108665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:50.108665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.02458","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":"2026-07-05T01:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dHPemTPinpFWu+hfK3XGuOeuD87J6IqaboSL5kBoF33zoIXvUJdVDT3w34NkwQNHOhwcAiQCnOKzGtij0Y0jBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:40:46.155195Z"},"content_sha256":"bc289a4a32fd28f9292af9ac4881534535710840f8e924eeeceaede51c971d64","schema_version":"1.0","event_id":"sha256:bc289a4a32fd28f9292af9ac4881534535710840f8e924eeeceaede51c971d64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Z4OKGH66EECZFQLTXTSS7J7WAN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifying Spurious Correlations for Robust Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Aron Culotta, Zhao Wang","submitted_at":"2020-10-06T03:49:22Z","abstract_excerpt":"The predictions of text classifiers are often driven by spurious correlations -- e.g., the term `Spielberg' correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment. In this paper, we propose a method to distinguish spurious and genuine correlations in text classification. We treat this as a supervised classification problem, using features derived from treatment effect estimators to distinguish spurious correlations from \"genuine\" ones. Due to the generic nature of these features and their small dimensionality, we find that the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02458","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/2010.02458/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":"2026-07-05T01:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P96zbjV4A1jz1A1WW+bgXNVWEy/KnL9dC+dKCw0GHEHpSbnZKLkEgzCPbmTLloRLxEZtJe1LFIVr95HXpaG5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:40:46.156211Z"},"content_sha256":"62cde4d81dc2f7c91700ba763a471af8b6ed79f480cc5d8c6a3f330c98e8babd","schema_version":"1.0","event_id":"sha256:62cde4d81dc2f7c91700ba763a471af8b6ed79f480cc5d8c6a3f330c98e8babd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4OKGH66EECZFQLTXTSS7J7WAN/bundle.json","state_url":"https://pith.science/pith/Z4OKGH66EECZFQLTXTSS7J7WAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4OKGH66EECZFQLTXTSS7J7WAN/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":"2026-08-12T14:40:46Z","links":{"resolver":"https://pith.science/pith/Z4OKGH66EECZFQLTXTSS7J7WAN","bundle":"https://pith.science/pith/Z4OKGH66EECZFQLTXTSS7J7WAN/bundle.json","state":"https://pith.science/pith/Z4OKGH66EECZFQLTXTSS7J7WAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4OKGH66EECZFQLTXTSS7J7WAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z4OKGH66EECZFQLTXTSS7J7WAN","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":"013cbe1a00eaa01b01e81d3632c9e05102857f6325e6d7640446b09b01c55159","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T03:49:22Z","title_canon_sha256":"3449418a02b208ee007e898562bd56235793a83daa8aa95591d65e8f78bb69a5"},"schema_version":"1.0","source":{"id":"2010.02458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02458","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02458v1","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02458","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"Z4OKGH66EECZ","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"Z4OKGH66EECZFQLT","created_at":"2026-07-05T01:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"Z4OKGH66","created_at":"2026-07-05T01:40:50Z"}],"graph_snapshots":[{"event_id":"sha256:62cde4d81dc2f7c91700ba763a471af8b6ed79f480cc5d8c6a3f330c98e8babd","target":"graph","created_at":"2026-07-05T01:40:50Z","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/2010.02458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The predictions of text classifiers are often driven by spurious correlations -- e.g., the term `Spielberg' correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment. In this paper, we propose a method to distinguish spurious and genuine correlations in text classification. We treat this as a supervised classification problem, using features derived from treatment effect estimators to distinguish spurious correlations from \"genuine\" ones. Due to the generic nature of these features and their small dimensionality, we find that the ","authors_text":"Aron Culotta, Zhao Wang","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T03:49:22Z","title":"Identifying Spurious Correlations for Robust Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02458","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:bc289a4a32fd28f9292af9ac4881534535710840f8e924eeeceaede51c971d64","target":"record","created_at":"2026-07-05T01:40:50Z","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":"013cbe1a00eaa01b01e81d3632c9e05102857f6325e6d7640446b09b01c55159","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T03:49:22Z","title_canon_sha256":"3449418a02b208ee007e898562bd56235793a83daa8aa95591d65e8f78bb69a5"},"schema_version":"1.0","source":{"id":"2010.02458","kind":"arxiv","version":1}},"canonical_sha256":"cf1ca31fde210592c173bce52fa7f60375542033a6218c88cb288a3915c80a61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf1ca31fde210592c173bce52fa7f60375542033a6218c88cb288a3915c80a61","first_computed_at":"2026-07-05T01:40:50.108665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:50.108665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ar8D6cctAR4K9Cewgxos83jceb78Gj4kOxDAX5d5pAv6w6P7nSSKaEXKEi7V9tHMUjZq3fggnZ5nCED9ilIRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:50.109122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.02458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc289a4a32fd28f9292af9ac4881534535710840f8e924eeeceaede51c971d64","sha256:62cde4d81dc2f7c91700ba763a471af8b6ed79f480cc5d8c6a3f330c98e8babd"],"state_sha256":"38a5fa105f608159bce4a3799ed550e1e03a6d57ddbfd2efc26f5b24cd3175d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VgDaZJVx2SN8KiDO8vFgqRAgmgwU5tSJ/HKUWXq3avoXTeEM0c3G+fHqUA/+xOFeNTbAO/GX14HE9DGwS9e8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:40:46.161333Z","bundle_sha256":"16099fdbea95abce8709086f06baed81c40db523123d6c73276326f9134b1e2a"}}