{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A25RKRCKPTPEZKWDTX2BNR4LUH","short_pith_number":"pith:A25RKRCK","schema_version":"1.0","canonical_sha256":"06bb15444a7cde4caac39df416c78ba1f3b71ffaa04698483ff9c46bba93f1ec","source":{"kind":"arxiv","id":"2607.24750","version":1},"attestation_state":"computed","paper":{"title":"TimeCapsule: Generative Hallucination as a Method for Historical Sensemaking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Hamed Yaghoobian, Hayk Grigorian","submitted_at":"2026-05-22T18:25:04Z","abstract_excerpt":"Large Language Models (LLMs) are temporally overexposed: trained on vast contemporary corpora, they encode present-day concepts that make them unreliable narrators of the past. We present TimeCapsule, a 1.2B-parameter LLaMA-style causal model trained exclusively on Victorian texts (1800-1875) as an epistemologically isolated generative archive. Quantitative evaluation shows a 45.4% perplexity reduction over a GPT-2 baseline on held-out Victorian prose, while larger contemporary causal models achieve lower raw perplexity through broader pretraining but lack temporal isolation. TimeCapsule exhib"},"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":"2607.24750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T18:25:04Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"8d513658363a5a28dd0dcb69636b3f007ae4ac72c7b75d672a60dc9b2fa90ffe","abstract_canon_sha256":"fa53bde1ee3ec3eaa4ff45205116f41310ee1b0e99d5277e180dd99c8b4ab5b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:41.968308Z","signature_b64":"qyN5DyqgeqDzizpPDxmozMf+cey2zbVu7L3SayRo74U5V2oAm4Ik+qu1hhMQhG3CjpF/lq7oJMbvsqLhCRkUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06bb15444a7cde4caac39df416c78ba1f3b71ffaa04698483ff9c46bba93f1ec","last_reissued_at":"2026-07-29T00:24:41.967363Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:41.967363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeCapsule: Generative Hallucination as a Method for Historical Sensemaking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Hamed Yaghoobian, Hayk Grigorian","submitted_at":"2026-05-22T18:25:04Z","abstract_excerpt":"Large Language Models (LLMs) are temporally overexposed: trained on vast contemporary corpora, they encode present-day concepts that make them unreliable narrators of the past. We present TimeCapsule, a 1.2B-parameter LLaMA-style causal model trained exclusively on Victorian texts (1800-1875) as an epistemologically isolated generative archive. Quantitative evaluation shows a 45.4% perplexity reduction over a GPT-2 baseline on held-out Victorian prose, while larger contemporary causal models achieve lower raw perplexity through broader pretraining but lack temporal isolation. TimeCapsule exhib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24750","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/2607.24750/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":"2607.24750","created_at":"2026-07-29T00:24:41.967816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24750v1","created_at":"2026-07-29T00:24:41.967816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24750","created_at":"2026-07-29T00:24:41.967816+00:00"},{"alias_kind":"pith_short_12","alias_value":"A25RKRCKPTPE","created_at":"2026-07-29T00:24:41.967816+00:00"},{"alias_kind":"pith_short_16","alias_value":"A25RKRCKPTPEZKWD","created_at":"2026-07-29T00:24:41.967816+00:00"},{"alias_kind":"pith_short_8","alias_value":"A25RKRCK","created_at":"2026-07-29T00:24:41.967816+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/A25RKRCKPTPEZKWDTX2BNR4LUH","json":"https://pith.science/pith/A25RKRCKPTPEZKWDTX2BNR4LUH.json","graph_json":"https://pith.science/api/pith-number/A25RKRCKPTPEZKWDTX2BNR4LUH/graph.json","events_json":"https://pith.science/api/pith-number/A25RKRCKPTPEZKWDTX2BNR4LUH/events.json","paper":"https://pith.science/paper/A25RKRCK"},"agent_actions":{"view_html":"https://pith.science/pith/A25RKRCKPTPEZKWDTX2BNR4LUH","download_json":"https://pith.science/pith/A25RKRCKPTPEZKWDTX2BNR4LUH.json","view_paper":"https://pith.science/paper/A25RKRCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24750&json=true","fetch_graph":"https://pith.science/api/pith-number/A25RKRCKPTPEZKWDTX2BNR4LUH/graph.json","fetch_events":"https://pith.science/api/pith-number/A25RKRCKPTPEZKWDTX2BNR4LUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A25RKRCKPTPEZKWDTX2BNR4LUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A25RKRCKPTPEZKWDTX2BNR4LUH/action/storage_attestation","attest_author":"https://pith.science/pith/A25RKRCKPTPEZKWDTX2BNR4LUH/action/author_attestation","sign_citation":"https://pith.science/pith/A25RKRCKPTPEZKWDTX2BNR4LUH/action/citation_signature","submit_replication":"https://pith.science/pith/A25RKRCKPTPEZKWDTX2BNR4LUH/action/replication_record"}},"created_at":"2026-07-29T00:24:41.967816+00:00","updated_at":"2026-07-29T00:24:41.967816+00:00"}