{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JZJNA3FFSLVQKE4BL743NOAIU6","short_pith_number":"pith:JZJNA3FF","schema_version":"1.0","canonical_sha256":"4e52d06ca592eb0513815ff9b6b808a795b40cee34e65d509493820c0dcce56b","source":{"kind":"arxiv","id":"2605.18843","version":1},"attestation_state":"computed","paper":{"title":"TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bradly C. Stadie, Zeyu Zhang","submitted_at":"2026-05-13T05:01:37Z","abstract_excerpt":"Backtesting large language models on historical events requires reasoning exclusively from information available before a specified cutoff date. Yet models routinely leak post-cutoff knowledge from pre-training into their reasoning, inflating apparent accuracy and undermining evaluation validity. Prompt-based constraints fail when suppressed content is causally related to the prediction, and knowledge unlearning cannot address this problem because temporal compliance is instance-specific: the same fact may be legitimate evidence for one cutoff date and a violation for another. Rather than eras"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.18843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T05:01:37Z","cross_cats_sorted":[],"title_canon_sha256":"223ad33603e1edb23706609fa153f38269879f54d781a559ac9b79847454e77a","abstract_canon_sha256":"6a8d19f6d822d2add9b76368bf5c4a14a8db6b08b62046c68a9c1b960ddde061"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:25.323942Z","signature_b64":"pLrJx5gLRiLxFiyrmNZ8GfI9tEWKpm8BaKSkmse980xt9i/88DTMJXUQSI/iFTPID3teQBYBVX9m+7/HuH1+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e52d06ca592eb0513815ff9b6b808a795b40cee34e65d509493820c0dcce56b","last_reissued_at":"2026-05-20T00:06:25.323125Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:25.323125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bradly C. Stadie, Zeyu Zhang","submitted_at":"2026-05-13T05:01:37Z","abstract_excerpt":"Backtesting large language models on historical events requires reasoning exclusively from information available before a specified cutoff date. Yet models routinely leak post-cutoff knowledge from pre-training into their reasoning, inflating apparent accuracy and undermining evaluation validity. Prompt-based constraints fail when suppressed content is causally related to the prediction, and knowledge unlearning cannot address this problem because temporal compliance is instance-specific: the same fact may be legitimate evidence for one cutoff date and a violation for another. Rather than eras"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18843","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/2605.18843/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.18843","created_at":"2026-05-20T00:06:25.323259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18843v1","created_at":"2026-05-20T00:06:25.323259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18843","created_at":"2026-05-20T00:06:25.323259+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZJNA3FFSLVQ","created_at":"2026-05-20T00:06:25.323259+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZJNA3FFSLVQKE4B","created_at":"2026-05-20T00:06:25.323259+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZJNA3FF","created_at":"2026-05-20T00:06:25.323259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6","json":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6.json","graph_json":"https://pith.science/api/pith-number/JZJNA3FFSLVQKE4BL743NOAIU6/graph.json","events_json":"https://pith.science/api/pith-number/JZJNA3FFSLVQKE4BL743NOAIU6/events.json","paper":"https://pith.science/paper/JZJNA3FF"},"agent_actions":{"view_html":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6","download_json":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6.json","view_paper":"https://pith.science/paper/JZJNA3FF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18843&json=true","fetch_graph":"https://pith.science/api/pith-number/JZJNA3FFSLVQKE4BL743NOAIU6/graph.json","fetch_events":"https://pith.science/api/pith-number/JZJNA3FFSLVQKE4BL743NOAIU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6/action/storage_attestation","attest_author":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6/action/author_attestation","sign_citation":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6/action/citation_signature","submit_replication":"https://pith.science/pith/JZJNA3FFSLVQKE4BL743NOAIU6/action/replication_record"}},"created_at":"2026-05-20T00:06:25.323259+00:00","updated_at":"2026-05-20T00:06:25.323259+00:00"}