{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ET75EIP3GNUMCAOH3UHD6TYXVD","short_pith_number":"pith:ET75EIP3","canonical_record":{"source":{"id":"2606.02991","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T00:59:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"abb6d070159cf9695a6468e7abb84cb68b0b330d07224963fcfae08a6980fb2b","abstract_canon_sha256":"6e70dbb297999322c837c45399be4e67b79a617c4b426e6910e558a65b34be95"},"schema_version":"1.0"},"canonical_sha256":"24ffd221fb3368c101c7dd0e3f4f17a8c9fa884a22378344e73018acd646609b","source":{"kind":"arxiv","id":"2606.02991","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02991","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02991v1","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02991","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"pith_short_12","alias_value":"ET75EIP3GNUM","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"pith_short_16","alias_value":"ET75EIP3GNUMCAOH","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"pith_short_8","alias_value":"ET75EIP3","created_at":"2026-06-03T01:05:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ET75EIP3GNUMCAOH3UHD6TYXVD","target":"record","payload":{"canonical_record":{"source":{"id":"2606.02991","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T00:59:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"abb6d070159cf9695a6468e7abb84cb68b0b330d07224963fcfae08a6980fb2b","abstract_canon_sha256":"6e70dbb297999322c837c45399be4e67b79a617c4b426e6910e558a65b34be95"},"schema_version":"1.0"},"canonical_sha256":"24ffd221fb3368c101c7dd0e3f4f17a8c9fa884a22378344e73018acd646609b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:28.694991Z","signature_b64":"gUk1KLRdTtJbkQDMT3ofH4cOWzBm5QVcnwj1KDSJrtxgRfCemkHZUNffxNl5UzKfQc5cCLp2d6SDOAhRuk0DDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24ffd221fb3368c101c7dd0e3f4f17a8c9fa884a22378344e73018acd646609b","last_reissued_at":"2026-06-03T01:05:28.694576Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:28.694576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.02991","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":"2026-06-03T01:05:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nB64p6qqoBJzmGsW/B3uY/sXLgVe3Ijk38CDJ/At0ieCldd6OdcnKCPIB8NzGLRXNdL7qFi6M/8bxF1YViMHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T20:17:34.474943Z"},"content_sha256":"c4a312b346ba142a36b724c0ac36a081a41ad94252528beb1ec9e140e77bbd95","schema_version":"1.0","event_id":"sha256:c4a312b346ba142a36b724c0ac36a081a41ad94252528beb1ec9e140e77bbd95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ET75EIP3GNUMCAOH3UHD6TYXVD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pretraining Language Models on Historical Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Freda Shi, Junchi Yu, Niclas Griesshaber, Philip Torr, Xiaoxi Luo, Yao Lu, Yixuan Wang, Zachary Shinnick","submitted_at":"2026-06-02T00:59:06Z","abstract_excerpt":"We introduce TypewriterLM, a 7.24B History language model (LM) trained exclusively on English text predating 1913. Developing History LMs requires addressing challenges in data quality and availability, preventing temporal leakage, designing temporally consistent post-training pipelines, and constructing reliable evaluations. To address these issues, we construct TypewriterCorpus, a 54B-token historical corpus collected from diverse archival and linguistically annotated sources with extensive data cleaning and leakage mitigation procedures. Furthermore, we introduce lexically grounded instruct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02991","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/2606.02991/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":"2026-06-03T01:05:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMIaPSuv7pJ4tYbup3sRZBOeIh0Ij+LldPxv4BI5l1pRfk/eJ65uWTlvU3j5wFKqEAnjMmDexJSKQFUb4cNiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T20:17:34.475329Z"},"content_sha256":"2e6a957b468ef7ecd525065290b51d9a6d726ae05c8543b99b308c6518f99751","schema_version":"1.0","event_id":"sha256:2e6a957b468ef7ecd525065290b51d9a6d726ae05c8543b99b308c6518f99751"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ET75EIP3GNUMCAOH3UHD6TYXVD/bundle.json","state_url":"https://pith.science/pith/ET75EIP3GNUMCAOH3UHD6TYXVD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ET75EIP3GNUMCAOH3UHD6TYXVD/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":"2026-07-02T20:17:34Z","links":{"resolver":"https://pith.science/pith/ET75EIP3GNUMCAOH3UHD6TYXVD","bundle":"https://pith.science/pith/ET75EIP3GNUMCAOH3UHD6TYXVD/bundle.json","state":"https://pith.science/pith/ET75EIP3GNUMCAOH3UHD6TYXVD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ET75EIP3GNUMCAOH3UHD6TYXVD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ET75EIP3GNUMCAOH3UHD6TYXVD","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":"6e70dbb297999322c837c45399be4e67b79a617c4b426e6910e558a65b34be95","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T00:59:06Z","title_canon_sha256":"abb6d070159cf9695a6468e7abb84cb68b0b330d07224963fcfae08a6980fb2b"},"schema_version":"1.0","source":{"id":"2606.02991","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02991","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02991v1","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02991","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"pith_short_12","alias_value":"ET75EIP3GNUM","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"pith_short_16","alias_value":"ET75EIP3GNUMCAOH","created_at":"2026-06-03T01:05:28Z"},{"alias_kind":"pith_short_8","alias_value":"ET75EIP3","created_at":"2026-06-03T01:05:28Z"}],"graph_snapshots":[{"event_id":"sha256:2e6a957b468ef7ecd525065290b51d9a6d726ae05c8543b99b308c6518f99751","target":"graph","created_at":"2026-06-03T01:05:28Z","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/2606.02991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce TypewriterLM, a 7.24B History language model (LM) trained exclusively on English text predating 1913. Developing History LMs requires addressing challenges in data quality and availability, preventing temporal leakage, designing temporally consistent post-training pipelines, and constructing reliable evaluations. To address these issues, we construct TypewriterCorpus, a 54B-token historical corpus collected from diverse archival and linguistically annotated sources with extensive data cleaning and leakage mitigation procedures. Furthermore, we introduce lexically grounded instruct","authors_text":"Freda Shi, Junchi Yu, Niclas Griesshaber, Philip Torr, Xiaoxi Luo, Yao Lu, Yixuan Wang, Zachary Shinnick","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T00:59:06Z","title":"Pretraining Language Models on Historical Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02991","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:c4a312b346ba142a36b724c0ac36a081a41ad94252528beb1ec9e140e77bbd95","target":"record","created_at":"2026-06-03T01:05:28Z","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":"6e70dbb297999322c837c45399be4e67b79a617c4b426e6910e558a65b34be95","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T00:59:06Z","title_canon_sha256":"abb6d070159cf9695a6468e7abb84cb68b0b330d07224963fcfae08a6980fb2b"},"schema_version":"1.0","source":{"id":"2606.02991","kind":"arxiv","version":1}},"canonical_sha256":"24ffd221fb3368c101c7dd0e3f4f17a8c9fa884a22378344e73018acd646609b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24ffd221fb3368c101c7dd0e3f4f17a8c9fa884a22378344e73018acd646609b","first_computed_at":"2026-06-03T01:05:28.694576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:28.694576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gUk1KLRdTtJbkQDMT3ofH4cOWzBm5QVcnwj1KDSJrtxgRfCemkHZUNffxNl5UzKfQc5cCLp2d6SDOAhRuk0DDg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:28.694991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02991","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4a312b346ba142a36b724c0ac36a081a41ad94252528beb1ec9e140e77bbd95","sha256:2e6a957b468ef7ecd525065290b51d9a6d726ae05c8543b99b308c6518f99751"],"state_sha256":"58a6f8c13bb3d42bca871eaf3670fb203a47e5a09907198c87a94eb72bc24380"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X7fstpCFlVQRZqdw4wxhaVkDoXz8fQLx4mtLOMlD1qOikgMVChFIz/QrHLDagE0EloZxF0/NJG0riGTrnipeAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T20:17:34.477715Z","bundle_sha256":"d0a1b5d36a7c20cc34e373772ad4960ab7f8b5803460941766df2e3f717b1fdb"}}