{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:B2W5U7HKGSIKHBWLX2HTEXX65R","short_pith_number":"pith:B2W5U7HK","canonical_record":{"source":{"id":"2310.10628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T17:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"27c50443c5d0cb5fefed547287ffdf2a957a027cce2ec94d907803f0d026886c","abstract_canon_sha256":"4fa197e15fd4d56a06a0548d5a93778ac1f324ab3022ee02a8ab87257a9cc43e"},"schema_version":"1.0"},"canonical_sha256":"0eadda7cea3490a386cbbe8f325efeec4b5baef41cc93b7a280833fcd8253f23","source":{"kind":"arxiv","id":"2310.10628","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10628","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10628v1","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10628","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"B2W5U7HKGSIK","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_16","alias_value":"B2W5U7HKGSIKHBWL","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_8","alias_value":"B2W5U7HK","created_at":"2026-07-05T07:01:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:B2W5U7HKGSIKHBWLX2HTEXX65R","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T17:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"27c50443c5d0cb5fefed547287ffdf2a957a027cce2ec94d907803f0d026886c","abstract_canon_sha256":"4fa197e15fd4d56a06a0548d5a93778ac1f324ab3022ee02a8ab87257a9cc43e"},"schema_version":"1.0"},"canonical_sha256":"0eadda7cea3490a386cbbe8f325efeec4b5baef41cc93b7a280833fcd8253f23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:22.584998Z","signature_b64":"F20f5AqgyIDGpCJecS9KQWzrTJwgz0Mix0CYFQnSEJA3QHe/cx1y4wqjJA4pA2+Qfi6rIOpQ4zgNdqiVyq2rDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eadda7cea3490a386cbbe8f325efeec4b5baef41cc93b7a280833fcd8253f23","last_reissued_at":"2026-07-05T07:01:22.584509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:22.584509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10628","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":"2026-07-05T07:01:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ap2gSx7ZabkhlnakkVz5lnCJLRWsluQQ+jLVmuCE6diSi9q3b3+lgSY++Yu1mAofvP2XjVLyRcsZmOJn1LvXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:04:59.474681Z"},"content_sha256":"26e0e87039e0eaa18dc68dc6cd43b7317ba8e873f760e7627cccf7873cb81f71","schema_version":"1.0","event_id":"sha256:26e0e87039e0eaa18dc68dc6cd43b7317ba8e873f760e7627cccf7873cb81f71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:B2W5U7HKGSIKHBWLX2HTEXX65R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Contamination Through the Lens of Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christine Herlihy, Colin White, Himanshu Thakur, Manley Roberts, Samuel Dooley","submitted_at":"2023-10-16T17:51:29Z","abstract_excerpt":"Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks. Since LLMs train on wide swaths of the internet, this practice raises concerns of data contamination, i.e., evaluating on examples that are explicitly or implicitly included in the training data. Data contamination remains notoriously challenging to measure and mitigate, even with partial attempts like controlled experimentation of training data, canary strings, or embedding similarities. In this work, we conduct the first thorough longitudinal analysis "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10628","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/2310.10628/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":"2026-07-05T07:01:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mp0UogDdhFIfSPRbYMcYC0NrJq+ChMssMT6LaoIycPGVkkXCQHU+SLoik77p5KyWqWvchqs3G5q2lFzPOkwlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:04:59.475058Z"},"content_sha256":"46257746d80ee77c512dfec6f0cd031f9514c5091e9b798da96509c5879cfaa2","schema_version":"1.0","event_id":"sha256:46257746d80ee77c512dfec6f0cd031f9514c5091e9b798da96509c5879cfaa2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2W5U7HKGSIKHBWLX2HTEXX65R/bundle.json","state_url":"https://pith.science/pith/B2W5U7HKGSIKHBWLX2HTEXX65R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2W5U7HKGSIKHBWLX2HTEXX65R/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":"2026-07-05T15:04:59Z","links":{"resolver":"https://pith.science/pith/B2W5U7HKGSIKHBWLX2HTEXX65R","bundle":"https://pith.science/pith/B2W5U7HKGSIKHBWLX2HTEXX65R/bundle.json","state":"https://pith.science/pith/B2W5U7HKGSIKHBWLX2HTEXX65R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2W5U7HKGSIKHBWLX2HTEXX65R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B2W5U7HKGSIKHBWLX2HTEXX65R","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":"4fa197e15fd4d56a06a0548d5a93778ac1f324ab3022ee02a8ab87257a9cc43e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T17:51:29Z","title_canon_sha256":"27c50443c5d0cb5fefed547287ffdf2a957a027cce2ec94d907803f0d026886c"},"schema_version":"1.0","source":{"id":"2310.10628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10628","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10628v1","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10628","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"B2W5U7HKGSIK","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_16","alias_value":"B2W5U7HKGSIKHBWL","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_8","alias_value":"B2W5U7HK","created_at":"2026-07-05T07:01:22Z"}],"graph_snapshots":[{"event_id":"sha256:46257746d80ee77c512dfec6f0cd031f9514c5091e9b798da96509c5879cfaa2","target":"graph","created_at":"2026-07-05T07:01:22Z","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/2310.10628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks. Since LLMs train on wide swaths of the internet, this practice raises concerns of data contamination, i.e., evaluating on examples that are explicitly or implicitly included in the training data. Data contamination remains notoriously challenging to measure and mitigate, even with partial attempts like controlled experimentation of training data, canary strings, or embedding similarities. In this work, we conduct the first thorough longitudinal analysis ","authors_text":"Christine Herlihy, Colin White, Himanshu Thakur, Manley Roberts, Samuel Dooley","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T17:51:29Z","title":"Data Contamination Through the Lens of Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10628","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":"sha256:26e0e87039e0eaa18dc68dc6cd43b7317ba8e873f760e7627cccf7873cb81f71","target":"record","created_at":"2026-07-05T07:01:22Z","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":"4fa197e15fd4d56a06a0548d5a93778ac1f324ab3022ee02a8ab87257a9cc43e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T17:51:29Z","title_canon_sha256":"27c50443c5d0cb5fefed547287ffdf2a957a027cce2ec94d907803f0d026886c"},"schema_version":"1.0","source":{"id":"2310.10628","kind":"arxiv","version":1}},"canonical_sha256":"0eadda7cea3490a386cbbe8f325efeec4b5baef41cc93b7a280833fcd8253f23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0eadda7cea3490a386cbbe8f325efeec4b5baef41cc93b7a280833fcd8253f23","first_computed_at":"2026-07-05T07:01:22.584509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:22.584509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F20f5AqgyIDGpCJecS9KQWzrTJwgz0Mix0CYFQnSEJA3QHe/cx1y4wqjJA4pA2+Qfi6rIOpQ4zgNdqiVyq2rDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:22.584998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26e0e87039e0eaa18dc68dc6cd43b7317ba8e873f760e7627cccf7873cb81f71","sha256:46257746d80ee77c512dfec6f0cd031f9514c5091e9b798da96509c5879cfaa2"],"state_sha256":"e4c37714385e5ee0031cf34a891a99b16c282f302603fda0d2689e4f0c43f08b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z5C3+oCAjivIzm1Q5B+HXb8FUEmNiYRaU+Scy+QXGcQhbSBOqiKtjHnsAJ0P+5sh8Mt4g4jDonOA4if7y7UcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:04:59.477132Z","bundle_sha256":"ae32778cb15132d4dacaf21a3d92c74a3472c01a3d80b9c17e82fa09353ed55e"}}