{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MPEV3S5Z45NLCGNVA5KYI5WFEV","short_pith_number":"pith:MPEV3S5Z","canonical_record":{"source":{"id":"2012.01300","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-02T16:10:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48623abd9bd29a3e4d2e3ee88053a52f65578b24cc8b4aef92fc41d5e40963ac","abstract_canon_sha256":"cd94ccf78960e210b77148f64d753ef5a9e418a686659e19153616c15fc89cb1"},"schema_version":"1.0"},"canonical_sha256":"63c95dcbb9e75ab119b507558476c5255ba7c09acc87d93ec210efe2262514e3","source":{"kind":"arxiv","id":"2012.01300","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.01300","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"arxiv_version","alias_value":"2012.01300v1","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01300","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"pith_short_12","alias_value":"MPEV3S5Z45NL","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"pith_short_16","alias_value":"MPEV3S5Z45NLCGNV","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"pith_short_8","alias_value":"MPEV3S5Z","created_at":"2026-07-05T01:56:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MPEV3S5Z45NLCGNVA5KYI5WFEV","target":"record","payload":{"canonical_record":{"source":{"id":"2012.01300","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-02T16:10:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48623abd9bd29a3e4d2e3ee88053a52f65578b24cc8b4aef92fc41d5e40963ac","abstract_canon_sha256":"cd94ccf78960e210b77148f64d753ef5a9e418a686659e19153616c15fc89cb1"},"schema_version":"1.0"},"canonical_sha256":"63c95dcbb9e75ab119b507558476c5255ba7c09acc87d93ec210efe2262514e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:37.693083Z","signature_b64":"RB3kgWz486D2lACbgvTxgiJyNBmjEqstUcouWL8Y2XYUtHmJn1lq5jL4chyqcw67tgubzSueG7R+JAWk8BMhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63c95dcbb9e75ab119b507558476c5255ba7c09acc87d93ec210efe2262514e3","last_reissued_at":"2026-07-05T01:56:37.692697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:37.692697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.01300","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":"2026-07-05T01:56:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"phb1+4Q24BycNlXQ2Oyb8hivxEPh2sdEiV3X0+nfdxJPafJk9dWmqQWNevHZDDrTojgErJa0wBr+Z0h6WhjBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:23:37.103556Z"},"content_sha256":"0e8904968826b436f37ca7098c231f1199e8b0914679728f2b8adc1145d5c2d6","schema_version":"1.0","event_id":"sha256:0e8904968826b436f37ca7098c231f1199e8b0914679728f2b8adc1145d5c2d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MPEV3S5Z45NLCGNVA5KYI5WFEV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Thomas Wolf, Victor Sanh, Yonatan Belinkov","submitted_at":"2020-12-02T16:10:54Z","abstract_excerpt":"State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended underlying task. Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available. We consider cases where the bias issues may not be explicitly identified, and show a method for training models that learn to ignore these problematic correlations. Our approach relies on the observation that models with limited capacity primarily learn to exploit biases in the dataset. We can le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01300","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/2012.01300/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":"2026-07-05T01:56:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28UbUcGpyy89drEd9THS70Zsx3GkJov9a/Aa5itAa1OcPfPwxMbHOjZD5NDMxNnyjrL4ixl6ymlY12OlRd6kAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:23:37.104046Z"},"content_sha256":"1cd86b6c0b2c8f20fcfb2177fc93fb134c59fece5bfda6aa94438fef6086f2d8","schema_version":"1.0","event_id":"sha256:1cd86b6c0b2c8f20fcfb2177fc93fb134c59fece5bfda6aa94438fef6086f2d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPEV3S5Z45NLCGNVA5KYI5WFEV/bundle.json","state_url":"https://pith.science/pith/MPEV3S5Z45NLCGNVA5KYI5WFEV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPEV3S5Z45NLCGNVA5KYI5WFEV/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":"2026-08-08T18:23:37Z","links":{"resolver":"https://pith.science/pith/MPEV3S5Z45NLCGNVA5KYI5WFEV","bundle":"https://pith.science/pith/MPEV3S5Z45NLCGNVA5KYI5WFEV/bundle.json","state":"https://pith.science/pith/MPEV3S5Z45NLCGNVA5KYI5WFEV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPEV3S5Z45NLCGNVA5KYI5WFEV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MPEV3S5Z45NLCGNVA5KYI5WFEV","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":"cd94ccf78960e210b77148f64d753ef5a9e418a686659e19153616c15fc89cb1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-02T16:10:54Z","title_canon_sha256":"48623abd9bd29a3e4d2e3ee88053a52f65578b24cc8b4aef92fc41d5e40963ac"},"schema_version":"1.0","source":{"id":"2012.01300","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.01300","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"arxiv_version","alias_value":"2012.01300v1","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01300","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"pith_short_12","alias_value":"MPEV3S5Z45NL","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"pith_short_16","alias_value":"MPEV3S5Z45NLCGNV","created_at":"2026-07-05T01:56:37Z"},{"alias_kind":"pith_short_8","alias_value":"MPEV3S5Z","created_at":"2026-07-05T01:56:37Z"}],"graph_snapshots":[{"event_id":"sha256:1cd86b6c0b2c8f20fcfb2177fc93fb134c59fece5bfda6aa94438fef6086f2d8","target":"graph","created_at":"2026-07-05T01:56:37Z","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/2012.01300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended underlying task. Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available. We consider cases where the bias issues may not be explicitly identified, and show a method for training models that learn to ignore these problematic correlations. Our approach relies on the observation that models with limited capacity primarily learn to exploit biases in the dataset. We can le","authors_text":"Alexander M. Rush, Thomas Wolf, Victor Sanh, Yonatan Belinkov","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-02T16:10:54Z","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01300","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":"sha256:0e8904968826b436f37ca7098c231f1199e8b0914679728f2b8adc1145d5c2d6","target":"record","created_at":"2026-07-05T01:56:37Z","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":"cd94ccf78960e210b77148f64d753ef5a9e418a686659e19153616c15fc89cb1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-02T16:10:54Z","title_canon_sha256":"48623abd9bd29a3e4d2e3ee88053a52f65578b24cc8b4aef92fc41d5e40963ac"},"schema_version":"1.0","source":{"id":"2012.01300","kind":"arxiv","version":1}},"canonical_sha256":"63c95dcbb9e75ab119b507558476c5255ba7c09acc87d93ec210efe2262514e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63c95dcbb9e75ab119b507558476c5255ba7c09acc87d93ec210efe2262514e3","first_computed_at":"2026-07-05T01:56:37.692697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:37.692697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RB3kgWz486D2lACbgvTxgiJyNBmjEqstUcouWL8Y2XYUtHmJn1lq5jL4chyqcw67tgubzSueG7R+JAWk8BMhCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:37.693083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.01300","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e8904968826b436f37ca7098c231f1199e8b0914679728f2b8adc1145d5c2d6","sha256:1cd86b6c0b2c8f20fcfb2177fc93fb134c59fece5bfda6aa94438fef6086f2d8"],"state_sha256":"3c5e5efa84f2b2fb7d62d6e1050b2f97412ef518c380fbc0154b665817009a8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8baljbbaQxAc56eTn44/NRSeUzXQgpdliXfJFa4kH0JNT2am/RJRFl4eSB0f7ssCc1TXnK14R2dkDUlmw2J1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:23:37.108195Z","bundle_sha256":"0e171179dae3e27848c24504eb48798220ee7b1ea47fc9c3c821c8a111822763"}}