{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RRSTML4DVVYVJZKYGQ5DOUHFZT","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":"ddde7bbd7eeb9ea9aabaee42b15b57b9453fad3e844941daf0d7a8c9303ebdfe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T12:03:44Z","title_canon_sha256":"de4e36a94395f16b65a7a4af48102170db92d4a8e5dcb323d13c415af313d478"},"schema_version":"1.0","source":{"id":"2508.05305","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05305","created_at":"2026-05-27T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05305v2","created_at":"2026-05-27T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05305","created_at":"2026-05-27T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"RRSTML4DVVYV","created_at":"2026-05-27T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"RRSTML4DVVYVJZKY","created_at":"2026-05-27T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"RRSTML4D","created_at":"2026-05-27T01:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:8397915cc77f8f6851371e4bff4379ad9085da87f4b50d2eb7c5bf23d50db5e4","target":"graph","created_at":"2026-05-27T01:04:49Z","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/2508.05305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-squared error or diffusion objectives. We present SONAR-LLM, a decoder-only transformer that \"thinks\" in the same continuous SONAR embedding space, yet is supervised through token-level cross-entropy propagated via the frozen SONAR decoder. This hybrid objective retains the semantic abstraction of LCM while eliminating its diffusion sampler and restoring a likelihood-based training signal. Across model sizes from 39M to 1.3B parameters, SONAR-LLM at","authors_text":"Andrey Kuznetsov, Anna Borisiuk, Anton Razzhigaev, Aysel Mirzoeva, Elizaveta Goncharova, Nikita Dragunov, Nikita Kurdiukov, Temurbek Rahmatullaev","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T12:03:44Z","title":"SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05305","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":"sha256:1708dedef6b88fb0bd1d3566012dfc141d46d8e35fee7af1307c16088f8ea882","target":"record","created_at":"2026-05-27T01:04:49Z","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":"ddde7bbd7eeb9ea9aabaee42b15b57b9453fad3e844941daf0d7a8c9303ebdfe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T12:03:44Z","title_canon_sha256":"de4e36a94395f16b65a7a4af48102170db92d4a8e5dcb323d13c415af313d478"},"schema_version":"1.0","source":{"id":"2508.05305","kind":"arxiv","version":2}},"canonical_sha256":"8c65362f83ad7154e558343a3750e5ccdb728b63dfb0e76c80cfbb8b432b741c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c65362f83ad7154e558343a3750e5ccdb728b63dfb0e76c80cfbb8b432b741c","first_computed_at":"2026-05-27T01:04:49.806590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:49.806590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XtgYBPCASD2nYjr1+ephS/cDcJBMeq1Gwq9ZAhuM/MU0rmuQZdGtmkQB34M+fdo/2SyAIdJf8XIv5lLx182iCA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:49.807306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05305","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1708dedef6b88fb0bd1d3566012dfc141d46d8e35fee7af1307c16088f8ea882","sha256:8397915cc77f8f6851371e4bff4379ad9085da87f4b50d2eb7c5bf23d50db5e4"],"state_sha256":"f52735292438b1640cf46a934ef16f181e835622c141d65f6b1d9ee695e93503"}