{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KFELEO3LQUUWS4OEUG7UAQC4MO","short_pith_number":"pith:KFELEO3L","canonical_record":{"source":{"id":"2410.20245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T18:21:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b0aa3b8ef463d9cd1d2e294f1c686c7ecbb86b389e02135ae34d6f1c23719841","abstract_canon_sha256":"65a46ac953a289da7a67e399c87a5dcdef413213590a3a1cfe83453ee38496fb"},"schema_version":"1.0"},"canonical_sha256":"5148b23b6b85296971c4a1bf40405c63a7759d9d66493ee22c37296c3b279e3d","source":{"kind":"arxiv","id":"2410.20245","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20245","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20245v2","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20245","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"KFELEO3LQUUW","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"KFELEO3LQUUWS4OE","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"KFELEO3L","created_at":"2026-07-05T10:12:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KFELEO3LQUUWS4OEUG7UAQC4MO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.20245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T18:21:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b0aa3b8ef463d9cd1d2e294f1c686c7ecbb86b389e02135ae34d6f1c23719841","abstract_canon_sha256":"65a46ac953a289da7a67e399c87a5dcdef413213590a3a1cfe83453ee38496fb"},"schema_version":"1.0"},"canonical_sha256":"5148b23b6b85296971c4a1bf40405c63a7759d9d66493ee22c37296c3b279e3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:22.622194Z","signature_b64":"m0aTYV8IngzLC5xhoI0K1oTrqIC1R+THHb4rgvb1yVjEe1+7H++XQAtXa8gnskxTMoN1I28MwhoRhZcK6fkPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5148b23b6b85296971c4a1bf40405c63a7759d9d66493ee22c37296c3b279e3d","last_reissued_at":"2026-07-05T10:12:22.621708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:22.621708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.20245","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UGjCb86mqh270Oiy2rTKr6qwfeA/QaIV55hyCHsUSOpm31IXz9S/gsXS/RkyN1g9Q6BjfVdx9rHsBlbYBslZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:21:54.590496Z"},"content_sha256":"1c66f2b1cdc31119cd1242e266b2c9a7e9075d0d90a843629085e883001ca07e","schema_version":"1.0","event_id":"sha256:1c66f2b1cdc31119cd1242e266b2c9a7e9075d0d90a843629085e883001ca07e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KFELEO3LQUUWS4OEUG7UAQC4MO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adina Williams, Candace Ross, David Pantoja, Megan Ung, Rebecca J. Passonneau, Vipul Gupta","submitted_at":"2024-10-26T18:21:44Z","abstract_excerpt":"One of the most challenging problems facing NLP today is evaluation. Some of the most pressing issues pertain to benchmark saturation, data contamination, and diversity in the quality of test examples. To address these concerns, we propose Selection Methodology for Accurate, Reduced, and Targeted (SMART) filtering, a novel approach to select a high-quality subset of examples from existing benchmark datasets by systematically removing less informative and less challenging examples. Our approach applies three filtering criteria, removing (i) easy examples, (ii) data-contaminated examples, and (i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20245","kind":"arxiv","version":2},"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/2410.20245/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":"2026-07-05T10:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ozDORTfTHJaTLsH3+R/bq1jMnKUQIx+YdEk7/3NTvLJRJFB4Ed/J6Nj0prx+zMuUH2+iPICZUxqeRlgQV8IxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:21:54.591366Z"},"content_sha256":"87b95087bf1a2a65943e31d21ccb6edac51b152383a006d5aa91d691688b3e54","schema_version":"1.0","event_id":"sha256:87b95087bf1a2a65943e31d21ccb6edac51b152383a006d5aa91d691688b3e54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KFELEO3LQUUWS4OEUG7UAQC4MO/bundle.json","state_url":"https://pith.science/pith/KFELEO3LQUUWS4OEUG7UAQC4MO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KFELEO3LQUUWS4OEUG7UAQC4MO/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":"2026-08-05T11:21:54Z","links":{"resolver":"https://pith.science/pith/KFELEO3LQUUWS4OEUG7UAQC4MO","bundle":"https://pith.science/pith/KFELEO3LQUUWS4OEUG7UAQC4MO/bundle.json","state":"https://pith.science/pith/KFELEO3LQUUWS4OEUG7UAQC4MO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KFELEO3LQUUWS4OEUG7UAQC4MO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KFELEO3LQUUWS4OEUG7UAQC4MO","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":"65a46ac953a289da7a67e399c87a5dcdef413213590a3a1cfe83453ee38496fb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T18:21:44Z","title_canon_sha256":"b0aa3b8ef463d9cd1d2e294f1c686c7ecbb86b389e02135ae34d6f1c23719841"},"schema_version":"1.0","source":{"id":"2410.20245","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20245","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20245v2","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20245","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"KFELEO3LQUUW","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"KFELEO3LQUUWS4OE","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"KFELEO3L","created_at":"2026-07-05T10:12:22Z"}],"graph_snapshots":[{"event_id":"sha256:87b95087bf1a2a65943e31d21ccb6edac51b152383a006d5aa91d691688b3e54","target":"graph","created_at":"2026-07-05T10:12:22Z","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/2410.20245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the most challenging problems facing NLP today is evaluation. Some of the most pressing issues pertain to benchmark saturation, data contamination, and diversity in the quality of test examples. To address these concerns, we propose Selection Methodology for Accurate, Reduced, and Targeted (SMART) filtering, a novel approach to select a high-quality subset of examples from existing benchmark datasets by systematically removing less informative and less challenging examples. Our approach applies three filtering criteria, removing (i) easy examples, (ii) data-contaminated examples, and (i","authors_text":"Adina Williams, Candace Ross, David Pantoja, Megan Ung, Rebecca J. Passonneau, Vipul Gupta","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T18:21:44Z","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20245","kind":"arxiv","version":2},"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":"sha256:1c66f2b1cdc31119cd1242e266b2c9a7e9075d0d90a843629085e883001ca07e","target":"record","created_at":"2026-07-05T10:12:22Z","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":"65a46ac953a289da7a67e399c87a5dcdef413213590a3a1cfe83453ee38496fb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T18:21:44Z","title_canon_sha256":"b0aa3b8ef463d9cd1d2e294f1c686c7ecbb86b389e02135ae34d6f1c23719841"},"schema_version":"1.0","source":{"id":"2410.20245","kind":"arxiv","version":2}},"canonical_sha256":"5148b23b6b85296971c4a1bf40405c63a7759d9d66493ee22c37296c3b279e3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5148b23b6b85296971c4a1bf40405c63a7759d9d66493ee22c37296c3b279e3d","first_computed_at":"2026-07-05T10:12:22.621708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:22.621708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m0aTYV8IngzLC5xhoI0K1oTrqIC1R+THHb4rgvb1yVjEe1+7H++XQAtXa8gnskxTMoN1I28MwhoRhZcK6fkPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:22.622194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20245","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c66f2b1cdc31119cd1242e266b2c9a7e9075d0d90a843629085e883001ca07e","sha256:87b95087bf1a2a65943e31d21ccb6edac51b152383a006d5aa91d691688b3e54"],"state_sha256":"2644ea27047fd669731ea5bf20b065b9e293d60d0a52b138e9fc836c6695fd57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCLbXBWqtb8KL0yK+OCDnK6uYI7Owm3DI5IRkxL98uN5Y2hQzZgHv8j/ntHoy5QZtSzQS9P82waXSvNxLgHaDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:21:54.599269Z","bundle_sha256":"6af7d3037b2d763537535001ae1386b22c73e9aae8a2f0893189a2efe43e69b0"}}