{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DVQTQIAN7W2HNHFVYYCKJLRUIY","short_pith_number":"pith:DVQTQIAN","canonical_record":{"source":{"id":"2312.12343","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-19T17:16:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0ced5c9d69dcd683d46e22ec3672770c1f3eaff97dac3df7769704408ae916a","abstract_canon_sha256":"bd2d625bef508123cbe4a7b0a452517f0d451a11c63391c76c03577d64185bf5"},"schema_version":"1.0"},"canonical_sha256":"1d6138200dfdb4769cb5c604a4ae34463b010f8eb0eb27ff536a5b691de14d28","source":{"kind":"arxiv","id":"2312.12343","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12343","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12343v3","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12343","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"pith_short_12","alias_value":"DVQTQIAN7W2H","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"pith_short_16","alias_value":"DVQTQIAN7W2HNHFV","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"pith_short_8","alias_value":"DVQTQIAN","created_at":"2026-07-05T07:50:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DVQTQIAN7W2HNHFVYYCKJLRUIY","target":"record","payload":{"canonical_record":{"source":{"id":"2312.12343","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-19T17:16:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0ced5c9d69dcd683d46e22ec3672770c1f3eaff97dac3df7769704408ae916a","abstract_canon_sha256":"bd2d625bef508123cbe4a7b0a452517f0d451a11c63391c76c03577d64185bf5"},"schema_version":"1.0"},"canonical_sha256":"1d6138200dfdb4769cb5c604a4ae34463b010f8eb0eb27ff536a5b691de14d28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:54.324295Z","signature_b64":"j0Blt5+9l74owHW1cs77QohGLL+5PNRI6hEgeenioDlq4iwWADVwQ/Lu0jJGUMzmXu2VpsvgD83h0E4PO2NNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d6138200dfdb4769cb5c604a4ae34463b010f8eb0eb27ff536a5b691de14d28","last_reissued_at":"2026-07-05T07:50:54.323774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:54.323774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.12343","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":"2026-07-05T07:50:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9DjyTjE6/eyHmkGzc4moTtkkGkke+avtATfWyrgNjtpknukKk+YF5Nn5Ou0TyJGmneL69cYsDH9ptkq83nJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:25:45.358874Z"},"content_sha256":"cbb2ea048ee4e0f92336a3d0d6eed06794a372bcfa87262b374c64b11495a61f","schema_version":"1.0","event_id":"sha256:cbb2ea048ee4e0f92336a3d0d6eed06794a372bcfa87262b374c64b11495a61f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DVQTQIAN7W2HNHFVYYCKJLRUIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Frank Guerin, Yucheng Li","submitted_at":"2023-12-19T17:16:43Z","abstract_excerpt":"Data contamination in evaluation is getting increasingly prevalent with the emergence of language models pre-trained on super large, automatically crawled corpora. This problem leads to significant challenges in the accurate assessment of model capabilities and generalisations. In this paper, we propose LatestEval, an automatic method that leverages the most recent texts to create uncontaminated reading comprehension evaluations. LatestEval avoids data contamination by only using texts published within a recent time window, ensuring no overlap with the training corpora of pre-trained language "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12343","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/2312.12343/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":"2026-07-05T07:50:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LsoGU3BMoCp6TOhIO/ckxp3NnXjKWGaD+GWGgv+fYVsPppz90hzo4nAvwqtx4SePdE82/qSqNizcQwYKNtgSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:25:45.359421Z"},"content_sha256":"0631534d2a2e9dde6f8058652810c4bc66e7e22819a5b361dd24688640079e97","schema_version":"1.0","event_id":"sha256:0631534d2a2e9dde6f8058652810c4bc66e7e22819a5b361dd24688640079e97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVQTQIAN7W2HNHFVYYCKJLRUIY/bundle.json","state_url":"https://pith.science/pith/DVQTQIAN7W2HNHFVYYCKJLRUIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVQTQIAN7W2HNHFVYYCKJLRUIY/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":"2026-08-12T13:25:45Z","links":{"resolver":"https://pith.science/pith/DVQTQIAN7W2HNHFVYYCKJLRUIY","bundle":"https://pith.science/pith/DVQTQIAN7W2HNHFVYYCKJLRUIY/bundle.json","state":"https://pith.science/pith/DVQTQIAN7W2HNHFVYYCKJLRUIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVQTQIAN7W2HNHFVYYCKJLRUIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DVQTQIAN7W2HNHFVYYCKJLRUIY","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":"bd2d625bef508123cbe4a7b0a452517f0d451a11c63391c76c03577d64185bf5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-19T17:16:43Z","title_canon_sha256":"b0ced5c9d69dcd683d46e22ec3672770c1f3eaff97dac3df7769704408ae916a"},"schema_version":"1.0","source":{"id":"2312.12343","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12343","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12343v3","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12343","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"pith_short_12","alias_value":"DVQTQIAN7W2H","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"pith_short_16","alias_value":"DVQTQIAN7W2HNHFV","created_at":"2026-07-05T07:50:54Z"},{"alias_kind":"pith_short_8","alias_value":"DVQTQIAN","created_at":"2026-07-05T07:50:54Z"}],"graph_snapshots":[{"event_id":"sha256:0631534d2a2e9dde6f8058652810c4bc66e7e22819a5b361dd24688640079e97","target":"graph","created_at":"2026-07-05T07:50:54Z","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/2312.12343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data contamination in evaluation is getting increasingly prevalent with the emergence of language models pre-trained on super large, automatically crawled corpora. This problem leads to significant challenges in the accurate assessment of model capabilities and generalisations. In this paper, we propose LatestEval, an automatic method that leverages the most recent texts to create uncontaminated reading comprehension evaluations. LatestEval avoids data contamination by only using texts published within a recent time window, ensuring no overlap with the training corpora of pre-trained language ","authors_text":"Chenghua Lin, Frank Guerin, Yucheng Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-19T17:16:43Z","title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12343","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:cbb2ea048ee4e0f92336a3d0d6eed06794a372bcfa87262b374c64b11495a61f","target":"record","created_at":"2026-07-05T07:50:54Z","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":"bd2d625bef508123cbe4a7b0a452517f0d451a11c63391c76c03577d64185bf5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-19T17:16:43Z","title_canon_sha256":"b0ced5c9d69dcd683d46e22ec3672770c1f3eaff97dac3df7769704408ae916a"},"schema_version":"1.0","source":{"id":"2312.12343","kind":"arxiv","version":3}},"canonical_sha256":"1d6138200dfdb4769cb5c604a4ae34463b010f8eb0eb27ff536a5b691de14d28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d6138200dfdb4769cb5c604a4ae34463b010f8eb0eb27ff536a5b691de14d28","first_computed_at":"2026-07-05T07:50:54.323774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:54.323774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j0Blt5+9l74owHW1cs77QohGLL+5PNRI6hEgeenioDlq4iwWADVwQ/Lu0jJGUMzmXu2VpsvgD83h0E4PO2NNAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:54.324295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12343","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbb2ea048ee4e0f92336a3d0d6eed06794a372bcfa87262b374c64b11495a61f","sha256:0631534d2a2e9dde6f8058652810c4bc66e7e22819a5b361dd24688640079e97"],"state_sha256":"7e50a9c92b90ba0774baaa9d2f565139e3648874a63a2f326e2e758d82b3af0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6Bap4NPLCGmixozkv65Y4JM4nNW4msKhhJ2YrLwTMksNBjpHr9zdUoM5/Nj9ulbEZ+VYiN6sUSK0RaJ4ofFDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:25:45.364648Z","bundle_sha256":"6c438e2a1b6c650655fdea24298bba9ffaffe975b4b08f83036142950d18fd18"}}