{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SX7PTBO5XB6PTT3ZLABYKAAWG2","short_pith_number":"pith:SX7PTBO5","canonical_record":{"source":{"id":"2507.19219","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T12:39:03Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"25c1af58e34bcf4231b11a4d3b490779913a28a884c4280b6df659625becadde","abstract_canon_sha256":"9ae78d4bf022fd503a679482cbc7b5a316176b41bcdc3211bb8eb76afdb5d54e"},"schema_version":"1.0"},"canonical_sha256":"95fef985ddb87cf9cf79580385001636843dfcab2e746e90e8865cce2ea4fd30","source":{"kind":"arxiv","id":"2507.19219","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19219","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19219v2","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19219","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"SX7PTBO5XB6P","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"SX7PTBO5XB6PTT3Z","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"SX7PTBO5","created_at":"2026-05-26T01:03:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SX7PTBO5XB6PTT3ZLABYKAAWG2","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19219","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T12:39:03Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"25c1af58e34bcf4231b11a4d3b490779913a28a884c4280b6df659625becadde","abstract_canon_sha256":"9ae78d4bf022fd503a679482cbc7b5a316176b41bcdc3211bb8eb76afdb5d54e"},"schema_version":"1.0"},"canonical_sha256":"95fef985ddb87cf9cf79580385001636843dfcab2e746e90e8865cce2ea4fd30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:13.766279Z","signature_b64":"269JhZN17wc+NpyQrBIn+xAK8g+cEi3J982Evp9vqZMNdKIAB8Sax4f8PHjfVoRwLfRzGt+jjyxkpEffdfFyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95fef985ddb87cf9cf79580385001636843dfcab2e746e90e8865cce2ea4fd30","last_reissued_at":"2026-05-26T01:03:13.765708Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:13.765708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19219","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":"2026-05-26T01:03:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0w/E6AUvGxPriNLnA3Ws4KdV7gqCeFgtXpAi4Mxitd9n1I2cndI4CQcwEVdDttvJeZYcgYUOeELuz8FjypACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:07:16.359918Z"},"content_sha256":"928d026aeb1d065a0ee22d07bb52950a6ddc0801ea2f4bef252b38439ba23fcd","schema_version":"1.0","event_id":"sha256:928d026aeb1d065a0ee22d07bb52950a6ddc0801ea2f4bef252b38439ba23fcd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SX7PTBO5XB6PTT3ZLABYKAAWG2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Haibo Hu, Liantong Yu, Qingqing Ye, Shiyu Zhang, Zi Liang","submitted_at":"2025-07-25T12:39:03Z","abstract_excerpt":"Overestimation in evaluating large language models (LLMs) has become an increasing concern. Due to the contamination of public benchmarks or imbalanced model training, LLMs may achieve unreal evaluation results on public benchmarks, either intentionally or unintentionally, which leads to unfair comparisons among LLMs and undermines their realistic capability assessments. Existing benchmarks attempt to address these issues by keeping test cases permanently secret, mitigating contamination through human evaluation, or repeatedly collecting and constructing new samples. However, these approaches "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19219","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/2507.19219/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":"2026-05-26T01:03:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pVl9XrwHaWuimGyRw1rbuqsSJd5uMlWTWAOuo6HvboSKISmIuNHnIUzkgJdHgjCLBt82FZXOSTku9XPulUKGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:07:16.360743Z"},"content_sha256":"e76cb6e90810f66907af7c686e29e3861ec4e8485c6afea8eae1531c3459d425","schema_version":"1.0","event_id":"sha256:e76cb6e90810f66907af7c686e29e3861ec4e8485c6afea8eae1531c3459d425"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SX7PTBO5XB6PTT3ZLABYKAAWG2/bundle.json","state_url":"https://pith.science/pith/SX7PTBO5XB6PTT3ZLABYKAAWG2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SX7PTBO5XB6PTT3ZLABYKAAWG2/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":"2026-06-10T08:07:16Z","links":{"resolver":"https://pith.science/pith/SX7PTBO5XB6PTT3ZLABYKAAWG2","bundle":"https://pith.science/pith/SX7PTBO5XB6PTT3ZLABYKAAWG2/bundle.json","state":"https://pith.science/pith/SX7PTBO5XB6PTT3ZLABYKAAWG2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SX7PTBO5XB6PTT3ZLABYKAAWG2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SX7PTBO5XB6PTT3ZLABYKAAWG2","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":"9ae78d4bf022fd503a679482cbc7b5a316176b41bcdc3211bb8eb76afdb5d54e","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T12:39:03Z","title_canon_sha256":"25c1af58e34bcf4231b11a4d3b490779913a28a884c4280b6df659625becadde"},"schema_version":"1.0","source":{"id":"2507.19219","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19219","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19219v2","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19219","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"SX7PTBO5XB6P","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"SX7PTBO5XB6PTT3Z","created_at":"2026-05-26T01:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"SX7PTBO5","created_at":"2026-05-26T01:03:13Z"}],"graph_snapshots":[{"event_id":"sha256:e76cb6e90810f66907af7c686e29e3861ec4e8485c6afea8eae1531c3459d425","target":"graph","created_at":"2026-05-26T01:03:13Z","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/2507.19219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Overestimation in evaluating large language models (LLMs) has become an increasing concern. Due to the contamination of public benchmarks or imbalanced model training, LLMs may achieve unreal evaluation results on public benchmarks, either intentionally or unintentionally, which leads to unfair comparisons among LLMs and undermines their realistic capability assessments. Existing benchmarks attempt to address these issues by keeping test cases permanently secret, mitigating contamination through human evaluation, or repeatedly collecting and constructing new samples. However, these approaches ","authors_text":"Haibo Hu, Liantong Yu, Qingqing Ye, Shiyu Zhang, Zi Liang","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T12:39:03Z","title":"How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19219","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":"sha256:928d026aeb1d065a0ee22d07bb52950a6ddc0801ea2f4bef252b38439ba23fcd","target":"record","created_at":"2026-05-26T01:03:13Z","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":"9ae78d4bf022fd503a679482cbc7b5a316176b41bcdc3211bb8eb76afdb5d54e","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T12:39:03Z","title_canon_sha256":"25c1af58e34bcf4231b11a4d3b490779913a28a884c4280b6df659625becadde"},"schema_version":"1.0","source":{"id":"2507.19219","kind":"arxiv","version":2}},"canonical_sha256":"95fef985ddb87cf9cf79580385001636843dfcab2e746e90e8865cce2ea4fd30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95fef985ddb87cf9cf79580385001636843dfcab2e746e90e8865cce2ea4fd30","first_computed_at":"2026-05-26T01:03:13.765708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:13.765708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"269JhZN17wc+NpyQrBIn+xAK8g+cEi3J982Evp9vqZMNdKIAB8Sax4f8PHjfVoRwLfRzGt+jjyxkpEffdfFyAg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:13.766279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19219","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:928d026aeb1d065a0ee22d07bb52950a6ddc0801ea2f4bef252b38439ba23fcd","sha256:e76cb6e90810f66907af7c686e29e3861ec4e8485c6afea8eae1531c3459d425"],"state_sha256":"9d9b7c91d2d2d19649c871aca0f5ddef2426fe36e84b00134e77d9a3a2b06af3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wltYxme6oKGSnKlc7epi1L8HB5+tXFRkURuh89No+Rg352gdim4L4134PgSypl8sU1kitWRg8MITvinEch5yDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T08:07:16.364962Z","bundle_sha256":"2a5b5abd726aa728410b65920e964fe4476c9af0a637e59d0adbc004811ff6b6"}}