{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KVASLDJKAPU2BILZNFS57U7NGE","short_pith_number":"pith:KVASLDJK","canonical_record":{"source":{"id":"2002.04108","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T21:59:21Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"58f93d21061ae85963283a0692b5ae6bad9b144c4d5ae3545603acb7f6304197","abstract_canon_sha256":"3570249ebd30d9d4b8886a2883941f7dd18ad130035e562132a557a932509479"},"schema_version":"1.0"},"canonical_sha256":"5541258d2a03e9a0a1796965dfd3ed31058b57328c2aba0c118ed6a27d243c32","source":{"kind":"arxiv","id":"2002.04108","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.04108","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2002.04108v3","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04108","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"KVASLDJKAPU2","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"KVASLDJKAPU2BILZ","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"KVASLDJK","created_at":"2026-07-05T01:18:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KVASLDJKAPU2BILZNFS57U7NGE","target":"record","payload":{"canonical_record":{"source":{"id":"2002.04108","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T21:59:21Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"58f93d21061ae85963283a0692b5ae6bad9b144c4d5ae3545603acb7f6304197","abstract_canon_sha256":"3570249ebd30d9d4b8886a2883941f7dd18ad130035e562132a557a932509479"},"schema_version":"1.0"},"canonical_sha256":"5541258d2a03e9a0a1796965dfd3ed31058b57328c2aba0c118ed6a27d243c32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:00.178245Z","signature_b64":"qJOJuH+irz5Vbo2TjF83OEwghrFu5I+zsVKf6eiWJ5gd6heBbGy7OKl6dVOQEIeZUs3XDOqHRB26Clsk4jhZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5541258d2a03e9a0a1796965dfd3ed31058b57328c2aba0c118ed6a27d243c32","last_reissued_at":"2026-07-05T01:18:00.177823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:00.177823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.04108","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:18:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4sK7pGUQ2NDUhUc/Iptjhn5F1W6aUm96WZa6Z1rE42euRSuHtpaoKSo+pGvfANbRxHJA3uPaaDmvIQLetmNBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T10:14:10.582125Z"},"content_sha256":"26222ad3bacd33050dc0d01e100194640226fe58ac86e6505f115e05c8f413fb","schema_version":"1.0","event_id":"sha256:26222ad3bacd33050dc0d01e100194640226fe58ac86e6505f115e05c8f413fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KVASLDJKAPU2BILZNFS57U7NGE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Filters of Dataset Biases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashish Sabharwal, Chandra Bhagavatula, Matthew E. Peters, Ronan Le Bras, Rowan Zellers, Swabha Swayamdipta, Yejin Choi","submitted_at":"2020-02-10T21:59:21Z","abstract_excerpt":"Large neural models have demonstrated human-level performance on language and vision benchmarks, while their performance degrades considerably on adversarial or out-of-distribution samples. This raises the question of whether these models have learned to solve a dataset rather than the underlying task by overfitting to spurious dataset biases. We investigate one recently proposed approach, AFLite, which adversarially filters such dataset biases, as a means to mitigate the prevalent overestimation of machine performance. We provide a theoretical understanding for AFLite, by situating it in the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04108","kind":"arxiv","version":3},"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/2002.04108/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":"2026-07-05T01:18:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ck1D9quMbk1FIBT90lM7y2U+CUevwzdL/SoXkY3rQtJnvUuzFz+v5mKAyR5WIUs6J/jkrr2/HgIG8vfU8lrIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T10:14:10.583466Z"},"content_sha256":"596bbd8ef1d3bac7514671ce7e56218d6aff1dd540d155535c993ee65d0e786e","schema_version":"1.0","event_id":"sha256:596bbd8ef1d3bac7514671ce7e56218d6aff1dd540d155535c993ee65d0e786e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KVASLDJKAPU2BILZNFS57U7NGE/bundle.json","state_url":"https://pith.science/pith/KVASLDJKAPU2BILZNFS57U7NGE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KVASLDJKAPU2BILZNFS57U7NGE/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":"2026-07-16T10:14:10Z","links":{"resolver":"https://pith.science/pith/KVASLDJKAPU2BILZNFS57U7NGE","bundle":"https://pith.science/pith/KVASLDJKAPU2BILZNFS57U7NGE/bundle.json","state":"https://pith.science/pith/KVASLDJKAPU2BILZNFS57U7NGE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KVASLDJKAPU2BILZNFS57U7NGE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KVASLDJKAPU2BILZNFS57U7NGE","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":"3570249ebd30d9d4b8886a2883941f7dd18ad130035e562132a557a932509479","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T21:59:21Z","title_canon_sha256":"58f93d21061ae85963283a0692b5ae6bad9b144c4d5ae3545603acb7f6304197"},"schema_version":"1.0","source":{"id":"2002.04108","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.04108","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2002.04108v3","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04108","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"KVASLDJKAPU2","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"KVASLDJKAPU2BILZ","created_at":"2026-07-05T01:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"KVASLDJK","created_at":"2026-07-05T01:18:00Z"}],"graph_snapshots":[{"event_id":"sha256:596bbd8ef1d3bac7514671ce7e56218d6aff1dd540d155535c993ee65d0e786e","target":"graph","created_at":"2026-07-05T01:18:00Z","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/2002.04108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large neural models have demonstrated human-level performance on language and vision benchmarks, while their performance degrades considerably on adversarial or out-of-distribution samples. This raises the question of whether these models have learned to solve a dataset rather than the underlying task by overfitting to spurious dataset biases. We investigate one recently proposed approach, AFLite, which adversarially filters such dataset biases, as a means to mitigate the prevalent overestimation of machine performance. We provide a theoretical understanding for AFLite, by situating it in the ","authors_text":"Ashish Sabharwal, Chandra Bhagavatula, Matthew E. Peters, Ronan Le Bras, Rowan Zellers, Swabha Swayamdipta, Yejin Choi","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T21:59:21Z","title":"Adversarial Filters of Dataset Biases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04108","kind":"arxiv","version":3},"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":"sha256:26222ad3bacd33050dc0d01e100194640226fe58ac86e6505f115e05c8f413fb","target":"record","created_at":"2026-07-05T01:18:00Z","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":"3570249ebd30d9d4b8886a2883941f7dd18ad130035e562132a557a932509479","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T21:59:21Z","title_canon_sha256":"58f93d21061ae85963283a0692b5ae6bad9b144c4d5ae3545603acb7f6304197"},"schema_version":"1.0","source":{"id":"2002.04108","kind":"arxiv","version":3}},"canonical_sha256":"5541258d2a03e9a0a1796965dfd3ed31058b57328c2aba0c118ed6a27d243c32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5541258d2a03e9a0a1796965dfd3ed31058b57328c2aba0c118ed6a27d243c32","first_computed_at":"2026-07-05T01:18:00.177823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:00.177823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qJOJuH+irz5Vbo2TjF83OEwghrFu5I+zsVKf6eiWJ5gd6heBbGy7OKl6dVOQEIeZUs3XDOqHRB26Clsk4jhZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:00.178245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.04108","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26222ad3bacd33050dc0d01e100194640226fe58ac86e6505f115e05c8f413fb","sha256:596bbd8ef1d3bac7514671ce7e56218d6aff1dd540d155535c993ee65d0e786e"],"state_sha256":"eb020bdb1620b7e27ac4423c0123dd909fdd16b410de675d4e1256db7808dcc4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KpS84CtsczsXDtJMFmUvSji5XLt/bWBxjP0NdqCEbbd8ZPPZ4uw8txYkB7wNsMXwOEzk5e6axZdQvGwiqH4PDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T10:14:10.586072Z","bundle_sha256":"41c943fe023995ef26613d281f79aba51cc8ad3110a860dbc51d9414285d730b"}}