{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AERT3XDBLLPJT3PMPMBACZEL3W","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":"c3c143277763522c76face242c9daf4c94a1cbe718a554de43d1ea3a5b38b9cd","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-07T22:20:03Z","title_canon_sha256":"d631830d701ee57d112c494b13a2d0d16869971316dc596bcd20798c3c04f902"},"schema_version":"1.0","source":{"id":"2011.03856","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03856","created_at":"2026-07-05T01:49:59Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03856v1","created_at":"2026-07-05T01:49:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03856","created_at":"2026-07-05T01:49:59Z"},{"alias_kind":"pith_short_12","alias_value":"AERT3XDBLLPJ","created_at":"2026-07-05T01:49:59Z"},{"alias_kind":"pith_short_16","alias_value":"AERT3XDBLLPJT3PM","created_at":"2026-07-05T01:49:59Z"},{"alias_kind":"pith_short_8","alias_value":"AERT3XDB","created_at":"2026-07-05T01:49:59Z"}],"graph_snapshots":[{"event_id":"sha256:bd1f620e8964ca7cd3191b2347eb89b3bf211c9cf30a6bc402e879c115f0449d","target":"graph","created_at":"2026-07-05T01:49:59Z","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/2011.03856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many datasets have been shown to contain incidental correlations created by idiosyncrasies in the data collection process. For example, sentence entailment datasets can have spurious word-class correlations if nearly all contradiction sentences contain the word \"not\", and image recognition datasets can have tell-tale object-background correlations if dogs are always indoors. In this paper, we propose a method that can automatically detect and ignore these kinds of dataset-specific patterns, which we call dataset biases. Our method trains a lower capacity model in an ensemble with a higher capa","authors_text":"Christopher Clark, Luke Zettlemoyer, Mark Yatskar","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-07T22:20:03Z","title":"Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03856","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":"sha256:09dcc4dcec295d7908043a021a01a411fb446536b1bfea48dceadfcdf8019928","target":"record","created_at":"2026-07-05T01:49:59Z","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":"c3c143277763522c76face242c9daf4c94a1cbe718a554de43d1ea3a5b38b9cd","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-07T22:20:03Z","title_canon_sha256":"d631830d701ee57d112c494b13a2d0d16869971316dc596bcd20798c3c04f902"},"schema_version":"1.0","source":{"id":"2011.03856","kind":"arxiv","version":1}},"canonical_sha256":"01233ddc615ade99edec7b0201648bddb4574f38bb5d5672ec9adf465f784f8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01233ddc615ade99edec7b0201648bddb4574f38bb5d5672ec9adf465f784f8e","first_computed_at":"2026-07-05T01:49:59.926159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:59.926159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+bkrR9uwoiYcK+qFvdEM9C569BY2YbLtIzpX3MCXOumLbnd7tdyCxDvz/RBVz/IcXncEeDCDFZw+v64E3YPyAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:59.926590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.03856","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09dcc4dcec295d7908043a021a01a411fb446536b1bfea48dceadfcdf8019928","sha256:bd1f620e8964ca7cd3191b2347eb89b3bf211c9cf30a6bc402e879c115f0449d"],"state_sha256":"6d39ec83b26f93f005eb5c8f1c1577f08ae724c501d7975542d10b58986f004c"}