{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4HI7PQU2J5V2CBJW633B5FY5F2","short_pith_number":"pith:4HI7PQU2","canonical_record":{"source":{"id":"2608.08800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-09T16:26:29Z","cross_cats_sorted":[],"title_canon_sha256":"72f2f6738bc3c93e6c790ad4f870d90aa5ecec6b6eaac8af9983d6599d40dd3d","abstract_canon_sha256":"de067c656e11754352b1058a2c64ac35713fde7aa5329bb0a0f0fbe653c6cdca"},"schema_version":"1.0"},"canonical_sha256":"e1d1f7c29a4f6ba10536f6f61e971d2ea1505cf215f5d8317b4bf6511cb11db7","source":{"kind":"arxiv","id":"2608.08800","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08800","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08800v1","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08800","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"pith_short_12","alias_value":"4HI7PQU2J5V2","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"pith_short_16","alias_value":"4HI7PQU2J5V2CBJW","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"pith_short_8","alias_value":"4HI7PQU2","created_at":"2026-08-11T01:25:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4HI7PQU2J5V2CBJW633B5FY5F2","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-09T16:26:29Z","cross_cats_sorted":[],"title_canon_sha256":"72f2f6738bc3c93e6c790ad4f870d90aa5ecec6b6eaac8af9983d6599d40dd3d","abstract_canon_sha256":"de067c656e11754352b1058a2c64ac35713fde7aa5329bb0a0f0fbe653c6cdca"},"schema_version":"1.0"},"canonical_sha256":"e1d1f7c29a4f6ba10536f6f61e971d2ea1505cf215f5d8317b4bf6511cb11db7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:25:22.585468Z","signature_b64":"53PcfZTQS8Ly753or3r4WZGUhSetBPdmwjwtBS+gdqop78PqOxscIuslOdinqHJ3DqSFyxa3rdv1U562vquMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d1f7c29a4f6ba10536f6f61e971d2ea1505cf215f5d8317b4bf6511cb11db7","last_reissued_at":"2026-08-11T01:25:22.582802Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:25:22.582802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08800","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":"2026-08-11T01:25:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2j6xs+OgXp2bN0YyQv9+AQng9rn5rCdCFib+/vlZrABGa5jLA81m0UW2QTgb0OMpONbixsn5d9SG1JqE01M3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:16:43.615253Z"},"content_sha256":"5c48bd8c516933758ec99d5ca82f80a36064ce4a28194b509fe1226f63503d48","schema_version":"1.0","event_id":"sha256:5c48bd8c516933758ec99d5ca82f80a36064ce4a28194b509fe1226f63503d48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4HI7PQU2J5V2CBJW633B5FY5F2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instability of LLM Pre-Pretraining: It Doesn't Always Help. An Investigation on Multiple Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nam Luu, Ond\\v{r}ej Bojar, Sofiia Riazhskykh","submitted_at":"2026-08-09T16:26:29Z","abstract_excerpt":"Pretraining LLMs on artificial languages (\"pre-pretraining\") is a technique that could reportedly increase token efficiency by 33%, i.e., save up to 33% of training tokens needed to reach a certain performance. We validate this prior result for English on a larger set of natural languages across four language families, using two different tokenizers and varying model sizes. We also relate the observed gains (or losses) in token efficiency to quantified linguistic properties of the languages, such as sentence length, morphological richness, and features of dependency syntactic trees (tree depth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08800","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/2608.08800/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":"2026-08-11T01:25:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3kFrTJBKgNmAJp1Yv+Er272DRxtZbgp3yh7xCufG3CGgsPmoLts+PjXvgLr8DEQwp2+aqQtBzVvrAz+siYPSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:16:43.615769Z"},"content_sha256":"19e24e996e249377d67fa3b67aa64c3a923854e01974f5db1179caf8d5f3f80b","schema_version":"1.0","event_id":"sha256:19e24e996e249377d67fa3b67aa64c3a923854e01974f5db1179caf8d5f3f80b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HI7PQU2J5V2CBJW633B5FY5F2/bundle.json","state_url":"https://pith.science/pith/4HI7PQU2J5V2CBJW633B5FY5F2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HI7PQU2J5V2CBJW633B5FY5F2/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":"2026-08-19T07:16:43Z","links":{"resolver":"https://pith.science/pith/4HI7PQU2J5V2CBJW633B5FY5F2","bundle":"https://pith.science/pith/4HI7PQU2J5V2CBJW633B5FY5F2/bundle.json","state":"https://pith.science/pith/4HI7PQU2J5V2CBJW633B5FY5F2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HI7PQU2J5V2CBJW633B5FY5F2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4HI7PQU2J5V2CBJW633B5FY5F2","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":"de067c656e11754352b1058a2c64ac35713fde7aa5329bb0a0f0fbe653c6cdca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-09T16:26:29Z","title_canon_sha256":"72f2f6738bc3c93e6c790ad4f870d90aa5ecec6b6eaac8af9983d6599d40dd3d"},"schema_version":"1.0","source":{"id":"2608.08800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08800","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08800v1","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08800","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"pith_short_12","alias_value":"4HI7PQU2J5V2","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"pith_short_16","alias_value":"4HI7PQU2J5V2CBJW","created_at":"2026-08-11T01:25:22Z"},{"alias_kind":"pith_short_8","alias_value":"4HI7PQU2","created_at":"2026-08-11T01:25:22Z"}],"graph_snapshots":[{"event_id":"sha256:19e24e996e249377d67fa3b67aa64c3a923854e01974f5db1179caf8d5f3f80b","target":"graph","created_at":"2026-08-11T01:25:22Z","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/2608.08800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining LLMs on artificial languages (\"pre-pretraining\") is a technique that could reportedly increase token efficiency by 33%, i.e., save up to 33% of training tokens needed to reach a certain performance. We validate this prior result for English on a larger set of natural languages across four language families, using two different tokenizers and varying model sizes. We also relate the observed gains (or losses) in token efficiency to quantified linguistic properties of the languages, such as sentence length, morphological richness, and features of dependency syntactic trees (tree depth","authors_text":"Nam Luu, Ond\\v{r}ej Bojar, Sofiia Riazhskykh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-09T16:26:29Z","title":"Instability of LLM Pre-Pretraining: It Doesn't Always Help. An Investigation on Multiple Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08800","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":"sha256:5c48bd8c516933758ec99d5ca82f80a36064ce4a28194b509fe1226f63503d48","target":"record","created_at":"2026-08-11T01:25:22Z","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":"de067c656e11754352b1058a2c64ac35713fde7aa5329bb0a0f0fbe653c6cdca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-09T16:26:29Z","title_canon_sha256":"72f2f6738bc3c93e6c790ad4f870d90aa5ecec6b6eaac8af9983d6599d40dd3d"},"schema_version":"1.0","source":{"id":"2608.08800","kind":"arxiv","version":1}},"canonical_sha256":"e1d1f7c29a4f6ba10536f6f61e971d2ea1505cf215f5d8317b4bf6511cb11db7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1d1f7c29a4f6ba10536f6f61e971d2ea1505cf215f5d8317b4bf6511cb11db7","first_computed_at":"2026-08-11T01:25:22.582802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:25:22.582802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"53PcfZTQS8Ly753or3r4WZGUhSetBPdmwjwtBS+gdqop78PqOxscIuslOdinqHJ3DqSFyxa3rdv1U562vquMCQ==","signature_status":"signed_v1","signed_at":"2026-08-11T01:25:22.585468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c48bd8c516933758ec99d5ca82f80a36064ce4a28194b509fe1226f63503d48","sha256:19e24e996e249377d67fa3b67aa64c3a923854e01974f5db1179caf8d5f3f80b"],"state_sha256":"42cfa57653786f66e3d1a4e0daa2875001e6144ce95a2a9a27af67e4a9961d2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBgN5qyFx05e+xrnXYWzwXy+kXnR7V7c4Y05DnZ+he64HNKDcIDJi5MPiHHrr65tYOVrbFkZdDlYl76gDrMACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:16:43.621099Z","bundle_sha256":"b7ac5e6a33a7e4341628fcc1e41b634f0c48588094a9a3b32227508024ef81e0"}}