{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3HQIEGXZ46W377BBLRVM4ZC5EX","short_pith_number":"pith:3HQIEGXZ","canonical_record":{"source":{"id":"2402.16797","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:10:56Z","cross_cats_sorted":[],"title_canon_sha256":"dfa4a68c501d731f5975aa82d3864ac7852713a81b64f0a72411285709843508","abstract_canon_sha256":"a91022c69469431ae13cc7062b3ff329172cd8f8714302c00408c442b38b2b9e"},"schema_version":"1.0"},"canonical_sha256":"d9e0821af9e7adbffc215c6ace645d25c5d34c711b9f72ae504647c5c451339e","source":{"kind":"arxiv","id":"2402.16797","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16797","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16797v2","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16797","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"3HQIEGXZ46W3","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"3HQIEGXZ46W377BB","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"3HQIEGXZ","created_at":"2026-07-05T08:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3HQIEGXZ46W377BBLRVM4ZC5EX","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16797","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:10:56Z","cross_cats_sorted":[],"title_canon_sha256":"dfa4a68c501d731f5975aa82d3864ac7852713a81b64f0a72411285709843508","abstract_canon_sha256":"a91022c69469431ae13cc7062b3ff329172cd8f8714302c00408c442b38b2b9e"},"schema_version":"1.0"},"canonical_sha256":"d9e0821af9e7adbffc215c6ace645d25c5d34c711b9f72ae504647c5c451339e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:22.996630Z","signature_b64":"8/ordN2vdjasQXJD2rcb8yd5ip6HyCA06aqaxHHPUiRuprzI1d4w1vQ8QiEXeh/EUaFvBgU737CVo00kBlxTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9e0821af9e7adbffc215c6ace645d25c5d34c711b9f72ae504647c5c451339e","last_reissued_at":"2026-07-05T08:29:22.996081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:22.996081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16797","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":"2026-07-05T08:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RVofDS6WUZBaAKizLFibmRCUP1oUZkptA0iNTd3yMVlOs3WaCAPt4Nka4MyvoqDOyjSsQHYPYWoEvXRPFYInCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:56:59.142248Z"},"content_sha256":"86e1bb3e3874cd71474c08ff97195745f4eba7946010470db2843b2cc230f3e3","schema_version":"1.0","event_id":"sha256:86e1bb3e3874cd71474c08ff97195745f4eba7946010470db2843b2cc230f3e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3HQIEGXZ46W377BBLRVM4ZC5EX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Set the Clock: Temporal Alignment of Pretrained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Zhao, Hannaneh Hajishirzi, Noah A. Smith, Yizhong Wang, Zander Brumbaugh","submitted_at":"2024-02-26T18:10:56Z","abstract_excerpt":"Language models (LMs) are trained on web text originating from many points in time and, in general, without any explicit temporal grounding. This work investigates the temporal chaos of pretrained LMs and explores various methods to align their internal knowledge to a target time, which we call \"temporal alignment.\" To do this, we first automatically construct a dataset containing 20K time-sensitive questions and their answers for each year from 2000 to 2023. Based on this dataset, we empirically show that pretrained LMs (e.g., LLaMa2), despite having a recent pretraining cutoff (e.g., 2022), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16797","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/2402.16797/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":"2026-07-05T08:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IM7Qi+shzszTDd+re3ue33raOkS+8qdI/Lzb67ratXMoxgh1HbB0vQ4zQIxi2iqYMJkFnd4EX9H7Z9p4BaxcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:56:59.143175Z"},"content_sha256":"bede308bf433e0b4cb52c097ab7cc079555ea1874e6557db2378676a5c4c4c3c","schema_version":"1.0","event_id":"sha256:bede308bf433e0b4cb52c097ab7cc079555ea1874e6557db2378676a5c4c4c3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HQIEGXZ46W377BBLRVM4ZC5EX/bundle.json","state_url":"https://pith.science/pith/3HQIEGXZ46W377BBLRVM4ZC5EX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HQIEGXZ46W377BBLRVM4ZC5EX/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":"2026-08-08T13:56:59Z","links":{"resolver":"https://pith.science/pith/3HQIEGXZ46W377BBLRVM4ZC5EX","bundle":"https://pith.science/pith/3HQIEGXZ46W377BBLRVM4ZC5EX/bundle.json","state":"https://pith.science/pith/3HQIEGXZ46W377BBLRVM4ZC5EX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HQIEGXZ46W377BBLRVM4ZC5EX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3HQIEGXZ46W377BBLRVM4ZC5EX","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":"a91022c69469431ae13cc7062b3ff329172cd8f8714302c00408c442b38b2b9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:10:56Z","title_canon_sha256":"dfa4a68c501d731f5975aa82d3864ac7852713a81b64f0a72411285709843508"},"schema_version":"1.0","source":{"id":"2402.16797","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16797","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16797v2","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16797","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"3HQIEGXZ46W3","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"3HQIEGXZ46W377BB","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"3HQIEGXZ","created_at":"2026-07-05T08:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:bede308bf433e0b4cb52c097ab7cc079555ea1874e6557db2378676a5c4c4c3c","target":"graph","created_at":"2026-07-05T08:29:22Z","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/2402.16797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) are trained on web text originating from many points in time and, in general, without any explicit temporal grounding. This work investigates the temporal chaos of pretrained LMs and explores various methods to align their internal knowledge to a target time, which we call \"temporal alignment.\" To do this, we first automatically construct a dataset containing 20K time-sensitive questions and their answers for each year from 2000 to 2023. Based on this dataset, we empirically show that pretrained LMs (e.g., LLaMa2), despite having a recent pretraining cutoff (e.g., 2022), ","authors_text":"Bowen Zhao, Hannaneh Hajishirzi, Noah A. Smith, Yizhong Wang, Zander Brumbaugh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:10:56Z","title":"Set the Clock: Temporal Alignment of Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16797","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":"sha256:86e1bb3e3874cd71474c08ff97195745f4eba7946010470db2843b2cc230f3e3","target":"record","created_at":"2026-07-05T08:29:22Z","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":"a91022c69469431ae13cc7062b3ff329172cd8f8714302c00408c442b38b2b9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:10:56Z","title_canon_sha256":"dfa4a68c501d731f5975aa82d3864ac7852713a81b64f0a72411285709843508"},"schema_version":"1.0","source":{"id":"2402.16797","kind":"arxiv","version":2}},"canonical_sha256":"d9e0821af9e7adbffc215c6ace645d25c5d34c711b9f72ae504647c5c451339e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9e0821af9e7adbffc215c6ace645d25c5d34c711b9f72ae504647c5c451339e","first_computed_at":"2026-07-05T08:29:22.996081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:22.996081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8/ordN2vdjasQXJD2rcb8yd5ip6HyCA06aqaxHHPUiRuprzI1d4w1vQ8QiEXeh/EUaFvBgU737CVo00kBlxTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:22.996630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16797","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86e1bb3e3874cd71474c08ff97195745f4eba7946010470db2843b2cc230f3e3","sha256:bede308bf433e0b4cb52c097ab7cc079555ea1874e6557db2378676a5c4c4c3c"],"state_sha256":"00279b8e7bce6569ffa8acfc88d17f36eb200186a6975211ebde2017252dbf9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n8AtNhlrBroetWS8/s/P/irC5JuGAr8SgMYyuqP+hSEEmrQSRZ8InZnSwIhTpah6NQYhLcOGxYIUY7GPfChsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:56:59.148757Z","bundle_sha256":"8afc93618597cfdf7b4432f67ee5148bc7c52280f6220647f72fc8c42f1151e6"}}