{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UAROUVVS2G6BH34ME7VXHZNH4O","short_pith_number":"pith:UAROUVVS","canonical_record":{"source":{"id":"2505.08389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T09:35:40Z","cross_cats_sorted":[],"title_canon_sha256":"8cf4213844ee97b78ad2627b3e5003335c46f2b2d6d2a3fd2c2f75333798e331","abstract_canon_sha256":"24a013b90e9381f0ba8d16955787015f9115cbe4040f00df0556296022c45fd6"},"schema_version":"1.0"},"canonical_sha256":"a022ea56b2d1bc13ef8c27eb73e5a7e39f9d1886ae7f1f28f0a6f2fa2ac87981","source":{"kind":"arxiv","id":"2505.08389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08389","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08389v1","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08389","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"UAROUVVS2G6B","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"UAROUVVS2G6BH34M","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"UAROUVVS","created_at":"2026-07-05T11:02:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UAROUVVS2G6BH34ME7VXHZNH4O","target":"record","payload":{"canonical_record":{"source":{"id":"2505.08389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T09:35:40Z","cross_cats_sorted":[],"title_canon_sha256":"8cf4213844ee97b78ad2627b3e5003335c46f2b2d6d2a3fd2c2f75333798e331","abstract_canon_sha256":"24a013b90e9381f0ba8d16955787015f9115cbe4040f00df0556296022c45fd6"},"schema_version":"1.0"},"canonical_sha256":"a022ea56b2d1bc13ef8c27eb73e5a7e39f9d1886ae7f1f28f0a6f2fa2ac87981","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:29.968583Z","signature_b64":"9qEohER1GyCCRpy7Yga3JqonpmOeFZnhPTuayDk7Q9P/tyhMuBJ9nsncZa7qTonuMp4cQfTwBA7soSH/0CS/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a022ea56b2d1bc13ef8c27eb73e5a7e39f9d1886ae7f1f28f0a6f2fa2ac87981","last_reissued_at":"2026-07-05T11:02:29.968085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:29.968085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.08389","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":"2026-07-05T11:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"51a00+y8AKc+8w6NuIgz/c06KUfVJb0lDGKDTxVnijb20dUalv+NpOZsnvoKJbNVY3168zO94iIdv4L1RVaTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:46:49.807415Z"},"content_sha256":"e8e1be61a912dddf602f063c5b36c2d9f58a9e7d187d830b97edcedbb1424395","schema_version":"1.0","event_id":"sha256:e8e1be61a912dddf602f063c5b36c2d9f58a9e7d187d830b97edcedbb1424395"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UAROUVVS2G6BH34ME7VXHZNH4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Contamination Resistant Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rahmatullah Musawi, Sheng Lu","submitted_at":"2025-05-13T09:35:40Z","abstract_excerpt":"The rapid development of large language models (LLMs) has transformed the landscape of natural language processing. Evaluating LLMs properly is crucial for understanding their potential and addressing concerns such as safety. However, LLM evaluation is confronted by various factors, among which contamination stands out as a key issue that undermines the reliability of evaluations. In this work, we introduce the concept of contamination resistance to address this challenge. We propose a benchmark based on Caesar ciphers (e.g., \"ab\" to \"bc\" when the shift is 1), which, despite its simplicity, is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08389","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/2505.08389/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":"2026-07-05T11:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"erd7VoYs8Q/++B/xFvbD9mGMywNgt7xwn0oCN7zJrEOw5oWx+GieneQnNkRyrZFtWq0VzyYBSPeXW5WR7jphDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:46:49.808015Z"},"content_sha256":"12a357609a2f9e773ed05c6fd75b46c1ed46d456e7c84a37b790daf9da46dfee","schema_version":"1.0","event_id":"sha256:12a357609a2f9e773ed05c6fd75b46c1ed46d456e7c84a37b790daf9da46dfee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UAROUVVS2G6BH34ME7VXHZNH4O/bundle.json","state_url":"https://pith.science/pith/UAROUVVS2G6BH34ME7VXHZNH4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UAROUVVS2G6BH34ME7VXHZNH4O/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":"2026-08-17T18:46:49Z","links":{"resolver":"https://pith.science/pith/UAROUVVS2G6BH34ME7VXHZNH4O","bundle":"https://pith.science/pith/UAROUVVS2G6BH34ME7VXHZNH4O/bundle.json","state":"https://pith.science/pith/UAROUVVS2G6BH34ME7VXHZNH4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UAROUVVS2G6BH34ME7VXHZNH4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UAROUVVS2G6BH34ME7VXHZNH4O","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":"24a013b90e9381f0ba8d16955787015f9115cbe4040f00df0556296022c45fd6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T09:35:40Z","title_canon_sha256":"8cf4213844ee97b78ad2627b3e5003335c46f2b2d6d2a3fd2c2f75333798e331"},"schema_version":"1.0","source":{"id":"2505.08389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08389","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08389v1","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08389","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"UAROUVVS2G6B","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"UAROUVVS2G6BH34M","created_at":"2026-07-05T11:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"UAROUVVS","created_at":"2026-07-05T11:02:29Z"}],"graph_snapshots":[{"event_id":"sha256:12a357609a2f9e773ed05c6fd75b46c1ed46d456e7c84a37b790daf9da46dfee","target":"graph","created_at":"2026-07-05T11:02:29Z","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/2505.08389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of large language models (LLMs) has transformed the landscape of natural language processing. Evaluating LLMs properly is crucial for understanding their potential and addressing concerns such as safety. However, LLM evaluation is confronted by various factors, among which contamination stands out as a key issue that undermines the reliability of evaluations. In this work, we introduce the concept of contamination resistance to address this challenge. We propose a benchmark based on Caesar ciphers (e.g., \"ab\" to \"bc\" when the shift is 1), which, despite its simplicity, is","authors_text":"Rahmatullah Musawi, Sheng Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T09:35:40Z","title":"Towards Contamination Resistant Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08389","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:e8e1be61a912dddf602f063c5b36c2d9f58a9e7d187d830b97edcedbb1424395","target":"record","created_at":"2026-07-05T11:02:29Z","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":"24a013b90e9381f0ba8d16955787015f9115cbe4040f00df0556296022c45fd6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T09:35:40Z","title_canon_sha256":"8cf4213844ee97b78ad2627b3e5003335c46f2b2d6d2a3fd2c2f75333798e331"},"schema_version":"1.0","source":{"id":"2505.08389","kind":"arxiv","version":1}},"canonical_sha256":"a022ea56b2d1bc13ef8c27eb73e5a7e39f9d1886ae7f1f28f0a6f2fa2ac87981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a022ea56b2d1bc13ef8c27eb73e5a7e39f9d1886ae7f1f28f0a6f2fa2ac87981","first_computed_at":"2026-07-05T11:02:29.968085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:29.968085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9qEohER1GyCCRpy7Yga3JqonpmOeFZnhPTuayDk7Q9P/tyhMuBJ9nsncZa7qTonuMp4cQfTwBA7soSH/0CS/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:29.968583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8e1be61a912dddf602f063c5b36c2d9f58a9e7d187d830b97edcedbb1424395","sha256:12a357609a2f9e773ed05c6fd75b46c1ed46d456e7c84a37b790daf9da46dfee"],"state_sha256":"d950d6a40f6f68df7a5e5434726c0b3decb01c0b1e9a7e3426ddbc2ae50edd8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlAkpyOi35BThZPucFBa0r5cRDcOVxNE2nTyQlW35488UPZyjPpB1WWcSO/4HIktyqvxUsJ9AtykEnkAVAb8DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:46:49.813094Z","bundle_sha256":"b2a2804d5b467d6ddd61e6542cc5d967a8e15aebb14cd1e81e1dbdf4a51b0693"}}