{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CERHYIOY7J7MPH23QVZO6XR5TN","short_pith_number":"pith:CERHYIOY","canonical_record":{"source":{"id":"2410.18889","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T16:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"57d2eff12d06f7be84020069276b67f8c6845ec13123c81609d325d1a0e97bfa","abstract_canon_sha256":"180fdcbc94791dd31b44a1bd596dc8a7623040f6ce1a6b435539f1cb3e211a69"},"schema_version":"1.0"},"canonical_sha256":"11227c21d8fa7ec79f5b8572ef5e3d9b5e52429c141d5db67c596d9d9891baa5","source":{"kind":"arxiv","id":"2410.18889","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18889","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18889v2","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18889","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"CERHYIOY7J7M","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"pith_short_16","alias_value":"CERHYIOY7J7MPH23","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"pith_short_8","alias_value":"CERHYIOY","created_at":"2026-07-05T12:10:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CERHYIOY7J7MPH23QVZO6XR5TN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18889","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T16:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"57d2eff12d06f7be84020069276b67f8c6845ec13123c81609d325d1a0e97bfa","abstract_canon_sha256":"180fdcbc94791dd31b44a1bd596dc8a7623040f6ce1a6b435539f1cb3e211a69"},"schema_version":"1.0"},"canonical_sha256":"11227c21d8fa7ec79f5b8572ef5e3d9b5e52429c141d5db67c596d9d9891baa5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:10:53.762810Z","signature_b64":"ss4AONlt6iPthLjI/zWscXV93H81aePjgxxTkMT31TXf1e1sFLjZ7xxvMx525wM7Jgi1WfPDr7/wSh+ym2tFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11227c21d8fa7ec79f5b8572ef5e3d9b5e52429c141d5db67c596d9d9891baa5","last_reissued_at":"2026-07-05T12:10:53.762299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:10:53.762299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18889","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":"2026-07-05T12:10:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5U+oh37VBMc6AFD6+am3HoF9TMea2U1ap587sNM4hZbSQIrYEy0qnMqct+yN4jFBqJQaUpeutj2gzJTlSdfDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:32:04.625143Z"},"content_sha256":"3e2c97ea515ae9ba82c6c0e83a749f2ca22b190c0d4871be92d955ceedc89a6e","schema_version":"1.0","event_id":"sha256:3e2c97ea515ae9ba82c6c0e83a749f2ca22b190c0d4871be92d955ceedc89a6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CERHYIOY7J7MPH23QVZO6XR5TN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Idan Szpektor, Nitay Calderon, Omer Nahum, Orgad Keller, Roi Reichart","submitted_at":"2024-10-24T16:27:03Z","abstract_excerpt":"NLP benchmarks rely on standardized datasets for training and evaluating models and are crucial for advancing the field. Traditionally, expert annotations ensure high-quality labels; however, the cost of expert annotation does not scale well with the growing demand for larger datasets required by modern models. While crowd-sourcing provides a more scalable solution, it often comes at the expense of annotation precision and consistency. Recent advancements in large language models (LLMs) offer new opportunities to enhance the annotation process, particularly for detecting label errors in existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18889","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/2410.18889/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":"2026-07-05T12:10:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3Tr1ujb56nb3QGaPinPVpF8gngfuSb6t6AWdm3XXOd+Ax/azH74AsY0wmOxZVBz+hTnkRHYRLbsin4XM8DpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:32:04.626884Z"},"content_sha256":"dc849dbd1498596564147a4d348d2277c177275e5b45f8c24cd9d6dc6fee5a52","schema_version":"1.0","event_id":"sha256:dc849dbd1498596564147a4d348d2277c177275e5b45f8c24cd9d6dc6fee5a52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CERHYIOY7J7MPH23QVZO6XR5TN/bundle.json","state_url":"https://pith.science/pith/CERHYIOY7J7MPH23QVZO6XR5TN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CERHYIOY7J7MPH23QVZO6XR5TN/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":"2026-08-06T13:32:04Z","links":{"resolver":"https://pith.science/pith/CERHYIOY7J7MPH23QVZO6XR5TN","bundle":"https://pith.science/pith/CERHYIOY7J7MPH23QVZO6XR5TN/bundle.json","state":"https://pith.science/pith/CERHYIOY7J7MPH23QVZO6XR5TN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CERHYIOY7J7MPH23QVZO6XR5TN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CERHYIOY7J7MPH23QVZO6XR5TN","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":"180fdcbc94791dd31b44a1bd596dc8a7623040f6ce1a6b435539f1cb3e211a69","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T16:27:03Z","title_canon_sha256":"57d2eff12d06f7be84020069276b67f8c6845ec13123c81609d325d1a0e97bfa"},"schema_version":"1.0","source":{"id":"2410.18889","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18889","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18889v2","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18889","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"CERHYIOY7J7M","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"pith_short_16","alias_value":"CERHYIOY7J7MPH23","created_at":"2026-07-05T12:10:53Z"},{"alias_kind":"pith_short_8","alias_value":"CERHYIOY","created_at":"2026-07-05T12:10:53Z"}],"graph_snapshots":[{"event_id":"sha256:dc849dbd1498596564147a4d348d2277c177275e5b45f8c24cd9d6dc6fee5a52","target":"graph","created_at":"2026-07-05T12:10:53Z","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/2410.18889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"NLP benchmarks rely on standardized datasets for training and evaluating models and are crucial for advancing the field. Traditionally, expert annotations ensure high-quality labels; however, the cost of expert annotation does not scale well with the growing demand for larger datasets required by modern models. While crowd-sourcing provides a more scalable solution, it often comes at the expense of annotation precision and consistency. Recent advancements in large language models (LLMs) offer new opportunities to enhance the annotation process, particularly for detecting label errors in existi","authors_text":"Idan Szpektor, Nitay Calderon, Omer Nahum, Orgad Keller, Roi Reichart","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T16:27:03Z","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18889","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":"sha256:3e2c97ea515ae9ba82c6c0e83a749f2ca22b190c0d4871be92d955ceedc89a6e","target":"record","created_at":"2026-07-05T12:10:53Z","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":"180fdcbc94791dd31b44a1bd596dc8a7623040f6ce1a6b435539f1cb3e211a69","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T16:27:03Z","title_canon_sha256":"57d2eff12d06f7be84020069276b67f8c6845ec13123c81609d325d1a0e97bfa"},"schema_version":"1.0","source":{"id":"2410.18889","kind":"arxiv","version":2}},"canonical_sha256":"11227c21d8fa7ec79f5b8572ef5e3d9b5e52429c141d5db67c596d9d9891baa5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11227c21d8fa7ec79f5b8572ef5e3d9b5e52429c141d5db67c596d9d9891baa5","first_computed_at":"2026-07-05T12:10:53.762299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:10:53.762299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ss4AONlt6iPthLjI/zWscXV93H81aePjgxxTkMT31TXf1e1sFLjZ7xxvMx525wM7Jgi1WfPDr7/wSh+ym2tFDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:10:53.762810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18889","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e2c97ea515ae9ba82c6c0e83a749f2ca22b190c0d4871be92d955ceedc89a6e","sha256:dc849dbd1498596564147a4d348d2277c177275e5b45f8c24cd9d6dc6fee5a52"],"state_sha256":"5bf02e324cc9219b89dc917443228b486978f0f697bced69c4b6cb6273810ca5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKmPIP9SA8QhPbO71ZAkc5c8qLlFg9gfxMmZ1DIdswacpiuFaPRMyBJ/v9/j8bHKEBdSlzCD8kX2dREoeXxtAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:32:04.636066Z","bundle_sha256":"684be2ed8b6e795169e9c464e1c5db139564b8392136708bd2ef4342356c7f1b"}}