{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:YOCCY3EI26OIALEOKNFUOQCSZP","short_pith_number":"pith:YOCCY3EI","canonical_record":{"source":{"id":"2005.00816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T12:34:17Z","cross_cats_sorted":[],"title_canon_sha256":"a646905398bf64378c4d0358348b23924b160524cab6bd78361cc502bb124b0a","abstract_canon_sha256":"4e911f60aafa1c13dc78a4d89bf61a42fef1734e74c8fbad5753ba5d385465e3"},"schema_version":"1.0"},"canonical_sha256":"c3842c6c88d79c802c8e534b474052cbc2966abe997b45e267c1658b85b1c1b7","source":{"kind":"arxiv","id":"2005.00816","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00816","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00816v1","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00816","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"YOCCY3EI26OI","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"YOCCY3EI26OIALEO","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"YOCCY3EI","created_at":"2026-07-05T01:00:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:YOCCY3EI26OIALEOKNFUOQCSZP","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T12:34:17Z","cross_cats_sorted":[],"title_canon_sha256":"a646905398bf64378c4d0358348b23924b160524cab6bd78361cc502bb124b0a","abstract_canon_sha256":"4e911f60aafa1c13dc78a4d89bf61a42fef1734e74c8fbad5753ba5d385465e3"},"schema_version":"1.0"},"canonical_sha256":"c3842c6c88d79c802c8e534b474052cbc2966abe997b45e267c1658b85b1c1b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:01.061222Z","signature_b64":"RK8MajuGLPUOrvtrarrRbPnTXClCSLWUqwQOq83wz525JvyYvlDoPghxMbtIgIKtxjhPR+E9RStehtIkD3xwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3842c6c88d79c802c8e534b474052cbc2966abe997b45e267c1658b85b1c1b7","last_reissued_at":"2026-07-05T01:00:01.060803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:01.060803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00816","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":"2026-07-05T01:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b4VGfQAgx7fk07HOG0b2NIXUsouGmuy8bRfnJdIIORbwuP1kZOGwHKnxmhWKdreE5vedmu7sfs1j53tr4KXBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:35:46.394824Z"},"content_sha256":"cafc0af36718654eb90b3b375ce50729f49f7ec0a13a298498312962274409bd","schema_version":"1.0","event_id":"sha256:cafc0af36718654eb90b3b375ce50729f49f7ec0a13a298498312962274409bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:YOCCY3EI26OIALEOKNFUOQCSZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DQI: Measuring Data Quality in NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anjana Arunkumar, Bhavdeep Sachdeva, Chitta Baral, Chris Bryan, Swaroop Mishra","submitted_at":"2020-05-02T12:34:17Z","abstract_excerpt":"Neural language models have achieved human level performance across several NLP datasets. However, recent studies have shown that these models are not truly learning the desired task; rather, their high performance is attributed to overfitting using spurious biases, which suggests that the capabilities of AI systems have been over-estimated. We introduce a generic formula for Data Quality Index (DQI) to help dataset creators create datasets free of such unwanted biases. We evaluate this formula using a recently proposed approach for adversarial filtering, AFLite. We propose a new data creation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00816","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/2005.00816/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":"2026-07-05T01:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FnVWoDEqPvsWiZca0rI8N2K9Q+xRLuux2GPW40Eho9OmcvolnyYd3KE6PoTHRLG35t4Pv5r7ane+4L4oio5/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:35:46.395231Z"},"content_sha256":"31bacfe2d66b1cf5efcd031239994733fce99e97da106708b89cad021dec07f7","schema_version":"1.0","event_id":"sha256:31bacfe2d66b1cf5efcd031239994733fce99e97da106708b89cad021dec07f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/bundle.json","state_url":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOCCY3EI26OIALEOKNFUOQCSZP/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":"2026-07-31T13:35:46Z","links":{"resolver":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP","bundle":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/bundle.json","state":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOCCY3EI26OIALEOKNFUOQCSZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YOCCY3EI26OIALEOKNFUOQCSZP","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":"4e911f60aafa1c13dc78a4d89bf61a42fef1734e74c8fbad5753ba5d385465e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T12:34:17Z","title_canon_sha256":"a646905398bf64378c4d0358348b23924b160524cab6bd78361cc502bb124b0a"},"schema_version":"1.0","source":{"id":"2005.00816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00816","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00816v1","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00816","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"YOCCY3EI26OI","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"YOCCY3EI26OIALEO","created_at":"2026-07-05T01:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"YOCCY3EI","created_at":"2026-07-05T01:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:31bacfe2d66b1cf5efcd031239994733fce99e97da106708b89cad021dec07f7","target":"graph","created_at":"2026-07-05T01:00:01Z","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/2005.00816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural language models have achieved human level performance across several NLP datasets. However, recent studies have shown that these models are not truly learning the desired task; rather, their high performance is attributed to overfitting using spurious biases, which suggests that the capabilities of AI systems have been over-estimated. We introduce a generic formula for Data Quality Index (DQI) to help dataset creators create datasets free of such unwanted biases. We evaluate this formula using a recently proposed approach for adversarial filtering, AFLite. We propose a new data creation","authors_text":"Anjana Arunkumar, Bhavdeep Sachdeva, Chitta Baral, Chris Bryan, Swaroop Mishra","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T12:34:17Z","title":"DQI: Measuring Data Quality in NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00816","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:cafc0af36718654eb90b3b375ce50729f49f7ec0a13a298498312962274409bd","target":"record","created_at":"2026-07-05T01:00:01Z","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":"4e911f60aafa1c13dc78a4d89bf61a42fef1734e74c8fbad5753ba5d385465e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T12:34:17Z","title_canon_sha256":"a646905398bf64378c4d0358348b23924b160524cab6bd78361cc502bb124b0a"},"schema_version":"1.0","source":{"id":"2005.00816","kind":"arxiv","version":1}},"canonical_sha256":"c3842c6c88d79c802c8e534b474052cbc2966abe997b45e267c1658b85b1c1b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3842c6c88d79c802c8e534b474052cbc2966abe997b45e267c1658b85b1c1b7","first_computed_at":"2026-07-05T01:00:01.060803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:01.060803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RK8MajuGLPUOrvtrarrRbPnTXClCSLWUqwQOq83wz525JvyYvlDoPghxMbtIgIKtxjhPR+E9RStehtIkD3xwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:01.061222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cafc0af36718654eb90b3b375ce50729f49f7ec0a13a298498312962274409bd","sha256:31bacfe2d66b1cf5efcd031239994733fce99e97da106708b89cad021dec07f7"],"state_sha256":"42454eb96b3ab6ad2389d441badbec5690019a5303e1cb3d8ed28f437abcb071"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zdbv2GucKQ7r9+qqgSXVgIga8wY3hxxg6FuyNCwBaQdQbxy9NhwrFvbqn6SZ0+HWxQ1/899tmwZ/t1Nhf/QkCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T13:35:46.398556Z","bundle_sha256":"8db595a1c1075a169986748e54aa5ad9384dba32f9dc99c1f666da0da74cac93"}}