{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:63R2ENRN4C3WKFV2ATDZJSJ3VS","short_pith_number":"pith:63R2ENRN","schema_version":"1.0","canonical_sha256":"f6e3a2362de0b76516ba04c794c93bac9f558539b55a8aa6eb11656d9a953fe0","source":{"kind":"arxiv","id":"2106.15110","version":2},"attestation_state":"computed","paper":{"title":"Time-Aware Language Models as Temporal Knowledge Bases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Daniel Gillick, Jacob Eisenstein, Jeremy R. Cole, Julian Martin Eisenschlos, William W. Cohen","submitted_at":"2021-06-29T06:18:57Z","abstract_excerpt":"Many facts come with an expiration date, from the name of the President to the basketball team Lebron James plays for. But language models (LMs) are trained on snapshots of data collected at a specific moment in time, and this can limit their utility, especially in the closed-book setting where the pretraining corpus must contain the facts the model should memorize. We introduce a diagnostic dataset aimed at probing LMs for factual knowledge that changes over time and highlight problems with LMs at either end of the spectrum -- those trained on specific slices of temporal data, as well as thos"},"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":"2106.15110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-29T06:18:57Z","cross_cats_sorted":[],"title_canon_sha256":"e48d6d8f2fb6f2de4fd94f915cb6a90b637e699b3a1ce662137bbe9049ab3b19","abstract_canon_sha256":"5ef68bd4a5785a5e8c722baeb1d9a78e4c08c2379bb3f52f96bd5d1e21c5b104"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:02.949695Z","signature_b64":"kTQ1RjkiTPWhgtlM2GTqYI6sFRMt7sR2ZGZJgICsyXWx3uUJy7BTyZgaX8b4zl7ncTcPr3mlZYIUOL0YjNDzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6e3a2362de0b76516ba04c794c93bac9f558539b55a8aa6eb11656d9a953fe0","last_reissued_at":"2026-07-05T04:17:02.949334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:02.949334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-Aware Language Models as Temporal Knowledge Bases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Daniel Gillick, Jacob Eisenstein, Jeremy R. Cole, Julian Martin Eisenschlos, William W. Cohen","submitted_at":"2021-06-29T06:18:57Z","abstract_excerpt":"Many facts come with an expiration date, from the name of the President to the basketball team Lebron James plays for. But language models (LMs) are trained on snapshots of data collected at a specific moment in time, and this can limit their utility, especially in the closed-book setting where the pretraining corpus must contain the facts the model should memorize. We introduce a diagnostic dataset aimed at probing LMs for factual knowledge that changes over time and highlight problems with LMs at either end of the spectrum -- those trained on specific slices of temporal data, as well as thos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15110","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/2106.15110/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":"2106.15110","created_at":"2026-07-05T04:17:02.949390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15110v2","created_at":"2026-07-05T04:17:02.949390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15110","created_at":"2026-07-05T04:17:02.949390+00:00"},{"alias_kind":"pith_short_12","alias_value":"63R2ENRN4C3W","created_at":"2026-07-05T04:17:02.949390+00:00"},{"alias_kind":"pith_short_16","alias_value":"63R2ENRN4C3WKFV2","created_at":"2026-07-05T04:17:02.949390+00:00"},{"alias_kind":"pith_short_8","alias_value":"63R2ENRN","created_at":"2026-07-05T04:17:02.949390+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/63R2ENRN4C3WKFV2ATDZJSJ3VS","json":"https://pith.science/pith/63R2ENRN4C3WKFV2ATDZJSJ3VS.json","graph_json":"https://pith.science/api/pith-number/63R2ENRN4C3WKFV2ATDZJSJ3VS/graph.json","events_json":"https://pith.science/api/pith-number/63R2ENRN4C3WKFV2ATDZJSJ3VS/events.json","paper":"https://pith.science/paper/63R2ENRN"},"agent_actions":{"view_html":"https://pith.science/pith/63R2ENRN4C3WKFV2ATDZJSJ3VS","download_json":"https://pith.science/pith/63R2ENRN4C3WKFV2ATDZJSJ3VS.json","view_paper":"https://pith.science/paper/63R2ENRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15110&json=true","fetch_graph":"https://pith.science/api/pith-number/63R2ENRN4C3WKFV2ATDZJSJ3VS/graph.json","fetch_events":"https://pith.science/api/pith-number/63R2ENRN4C3WKFV2ATDZJSJ3VS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63R2ENRN4C3WKFV2ATDZJSJ3VS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63R2ENRN4C3WKFV2ATDZJSJ3VS/action/storage_attestation","attest_author":"https://pith.science/pith/63R2ENRN4C3WKFV2ATDZJSJ3VS/action/author_attestation","sign_citation":"https://pith.science/pith/63R2ENRN4C3WKFV2ATDZJSJ3VS/action/citation_signature","submit_replication":"https://pith.science/pith/63R2ENRN4C3WKFV2ATDZJSJ3VS/action/replication_record"}},"created_at":"2026-07-05T04:17:02.949390+00:00","updated_at":"2026-07-05T04:17:02.949390+00:00"}