{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QKMP4LJQ2SFUUL35EMK35K43YR","short_pith_number":"pith:QKMP4LJQ","canonical_record":{"source":{"id":"2608.02985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T00:45:54Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"f98e207eb16879a55b2d65b9c380cab127e2d33f5fe207ba33c936f1e6218b47","abstract_canon_sha256":"0e86fe09edf6a30441804b7a546cca0e38158e8c99af0eb65444f7488af33a1e"},"schema_version":"1.0"},"canonical_sha256":"8298fe2d30d48b4a2f7d2315beab9bc45b4fa71bb8916aca27a14ee8afa383e8","source":{"kind":"arxiv","id":"2608.02985","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02985","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02985v1","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02985","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"QKMP4LJQ2SFU","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"QKMP4LJQ2SFUUL35","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"QKMP4LJQ","created_at":"2026-08-05T00:44:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QKMP4LJQ2SFUUL35EMK35K43YR","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T00:45:54Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"f98e207eb16879a55b2d65b9c380cab127e2d33f5fe207ba33c936f1e6218b47","abstract_canon_sha256":"0e86fe09edf6a30441804b7a546cca0e38158e8c99af0eb65444f7488af33a1e"},"schema_version":"1.0"},"canonical_sha256":"8298fe2d30d48b4a2f7d2315beab9bc45b4fa71bb8916aca27a14ee8afa383e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:44:19.735005Z","signature_b64":"aYfd3CbopwN3t1PXV8ypWyJxF8aERcV74bHox/1Gs2zX+AU44Z8t6uS8DC19DtqhKaeDLS/bTvMEjedpGBKLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8298fe2d30d48b4a2f7d2315beab9bc45b4fa71bb8916aca27a14ee8afa383e8","last_reissued_at":"2026-08-05T00:44:19.732597Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:44:19.732597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02985","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":"2026-08-05T00:44:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bgi5UkEkI2+vAJxc6P/eZwJFgp+04k7t+P0lffHR8gwoIT0I9SUztlMOyL3bQA6hBA0NesI5wsF1z3eHSSSsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:43:32.557403Z"},"content_sha256":"c02378cae0243d7e3ebed09420e7c76cd34eeb7b07c15c18c1c0701de2bf5213","schema_version":"1.0","event_id":"sha256:c02378cae0243d7e3ebed09420e7c76cd34eeb7b07c15c18c1c0701de2bf5213"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QKMP4LJQ2SFUUL35EMK35K43YR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bradly C. Stadie, Zeyu Zhang","submitted_at":"2026-08-04T00:45:54Z","abstract_excerpt":"The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff. We show this check is uninformative. Four flagship models fail it on questions they cannot have memorized: every scored question resolved after their cutoffs. The reason is structural. Models legitimately know more about times near their cutoff, so recency mimics leakage, and we prove no passive backtest can separate the two from genuine skill. Measurement, not just detection, requires information from outside the backtest. We supply it in two forms. A known cutoff identifies l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02985","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/2608.02985/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":"2026-08-05T00:44:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W1a/j1TsYfWfG1q4MDLbjm71eKaZSkfgubmIALamY3pEGBDJgrwzAa6N6irxXL8J5nM0oBaI0DIIXZhxDRlTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:43:32.558063Z"},"content_sha256":"9e7b4f7b2bc9b41172b5fca57d4c4db0e973606e646adc3a2795273628221dab","schema_version":"1.0","event_id":"sha256:9e7b4f7b2bc9b41172b5fca57d4c4db0e973606e646adc3a2795273628221dab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QKMP4LJQ2SFUUL35EMK35K43YR/bundle.json","state_url":"https://pith.science/pith/QKMP4LJQ2SFUUL35EMK35K43YR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QKMP4LJQ2SFUUL35EMK35K43YR/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":"2026-08-08T19:43:32Z","links":{"resolver":"https://pith.science/pith/QKMP4LJQ2SFUUL35EMK35K43YR","bundle":"https://pith.science/pith/QKMP4LJQ2SFUUL35EMK35K43YR/bundle.json","state":"https://pith.science/pith/QKMP4LJQ2SFUUL35EMK35K43YR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QKMP4LJQ2SFUUL35EMK35K43YR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QKMP4LJQ2SFUUL35EMK35K43YR","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":"0e86fe09edf6a30441804b7a546cca0e38158e8c99af0eb65444f7488af33a1e","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T00:45:54Z","title_canon_sha256":"f98e207eb16879a55b2d65b9c380cab127e2d33f5fe207ba33c936f1e6218b47"},"schema_version":"1.0","source":{"id":"2608.02985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02985","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02985v1","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02985","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"QKMP4LJQ2SFU","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"QKMP4LJQ2SFUUL35","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"QKMP4LJQ","created_at":"2026-08-05T00:44:19Z"}],"graph_snapshots":[{"event_id":"sha256:9e7b4f7b2bc9b41172b5fca57d4c4db0e973606e646adc3a2795273628221dab","target":"graph","created_at":"2026-08-05T00:44:19Z","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/2608.02985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff. We show this check is uninformative. Four flagship models fail it on questions they cannot have memorized: every scored question resolved after their cutoffs. The reason is structural. Models legitimately know more about times near their cutoff, so recency mimics leakage, and we prove no passive backtest can separate the two from genuine skill. Measurement, not just detection, requires information from outside the backtest. We supply it in two forms. A known cutoff identifies l","authors_text":"Bradly C. Stadie, Zeyu Zhang","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T00:45:54Z","title":"Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02985","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:c02378cae0243d7e3ebed09420e7c76cd34eeb7b07c15c18c1c0701de2bf5213","target":"record","created_at":"2026-08-05T00:44:19Z","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":"0e86fe09edf6a30441804b7a546cca0e38158e8c99af0eb65444f7488af33a1e","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T00:45:54Z","title_canon_sha256":"f98e207eb16879a55b2d65b9c380cab127e2d33f5fe207ba33c936f1e6218b47"},"schema_version":"1.0","source":{"id":"2608.02985","kind":"arxiv","version":1}},"canonical_sha256":"8298fe2d30d48b4a2f7d2315beab9bc45b4fa71bb8916aca27a14ee8afa383e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8298fe2d30d48b4a2f7d2315beab9bc45b4fa71bb8916aca27a14ee8afa383e8","first_computed_at":"2026-08-05T00:44:19.732597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:44:19.732597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aYfd3CbopwN3t1PXV8ypWyJxF8aERcV74bHox/1Gs2zX+AU44Z8t6uS8DC19DtqhKaeDLS/bTvMEjedpGBKLAA==","signature_status":"signed_v1","signed_at":"2026-08-05T00:44:19.735005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c02378cae0243d7e3ebed09420e7c76cd34eeb7b07c15c18c1c0701de2bf5213","sha256:9e7b4f7b2bc9b41172b5fca57d4c4db0e973606e646adc3a2795273628221dab"],"state_sha256":"85d8f433da6bc49f25d3091d9a91bafab22bb6b393838d1dba121e2531a8647d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0tN517Yv2X5SJjH27I9gWhCdWgyvL19R4y1K9BhNhzKc3q3uS0TmXDTchHx/i2LFAW76JBjkOIvXJtwrWEADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:43:32.564399Z","bundle_sha256":"9d85a53754f7d9dfa742fa9e7d024dfbd580864303b7b0eef8ab3f6a5448dbcf"}}