{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6RVGS7X3IGN3XDE3UJGYRG2ZAL","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":"3562199cf2d084986032a59499ce2052812db2c926891a30795a8bb3b1b4af6c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-21T08:09:25Z","title_canon_sha256":"d2a1a068867cb4809bb487fafe4e71da0aae14a881c6c13518fe7f758dc673b2"},"schema_version":"1.0","source":{"id":"2601.14750","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.14750","created_at":"2026-06-02T01:04:15Z"},{"alias_kind":"arxiv_version","alias_value":"2601.14750v4","created_at":"2026-06-02T01:04:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14750","created_at":"2026-06-02T01:04:15Z"},{"alias_kind":"pith_short_12","alias_value":"6RVGS7X3IGN3","created_at":"2026-06-02T01:04:15Z"},{"alias_kind":"pith_short_16","alias_value":"6RVGS7X3IGN3XDE3","created_at":"2026-06-02T01:04:15Z"},{"alias_kind":"pith_short_8","alias_value":"6RVGS7X3","created_at":"2026-06-02T01:04:15Z"}],"graph_snapshots":[{"event_id":"sha256:13785e04c1f6c3c93efa0955d8361f87700507fbe229995ad1a50be1a93c514c","target":"graph","created_at":"2026-06-02T01:04:15Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we introduce Render-of-Thought (RoT), the first framework to reify the reasoning chain by rendering textual steps into images, making the latent rationale explicit and traceable... achieves 3-4x token compression and substantial inference acceleration compared to explicit CoT... maintains competitive performance"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"leverage the vision encoders of existing Vision Language Models (VLMs) as semantic anchors to align the vision embeddings with the textual space without incurring additional pre-training overhead"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RoT renders CoT reasoning text as images and aligns them via VLM vision encoders to achieve 3-4x token compression and faster inference with competitive accuracy."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Rendering chain-of-thought steps as images compresses reasoning tokens by 3-4x in language models."}],"snapshot_sha256":"f8c4c691ad6e276c3ca94c0e6aee1cf8c48ea65cd984ae900617a22971d24d2e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"576df87d959918d735756e0d26432afcd892c9ef93de8a32a4ae5cbd19f01330"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.14750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead. Recent works often focus exclusively on outcome alignment and lack supervision on the intermediate reasoning process. These deficiencies obscure the analyzability of the latent reasoning chain. To address these challenges, we introduce Render-of-Thought (RoT), the first framework to reify the reasoning chain by rendering textual steps into images, making the ","authors_text":"Peiming Li, Shiyu Li, Xiaochen Yang, Yang Tang, Yifan Wang, Zheng Wei","cross_cats":["cs.CV"],"headline":"Rendering chain-of-thought steps as images compresses reasoning tokens by 3-4x in language models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-21T08:09:25Z","title":"Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14750","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-16T12:48:19.486929Z","id":"00e34123-b44d-42e0-9364-db5dc84462d1","model_set":{"reader":"grok-4.3"},"one_line_summary":"RoT renders CoT reasoning text as images and aligns them via VLM vision encoders to achieve 3-4x token compression and faster inference with competitive accuracy.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Rendering chain-of-thought steps as images compresses reasoning tokens by 3-4x in language models.","strongest_claim":"we introduce Render-of-Thought (RoT), the first framework to reify the reasoning chain by rendering textual steps into images, making the latent rationale explicit and traceable... achieves 3-4x token compression and substantial inference acceleration compared to explicit CoT... maintains competitive performance","weakest_assumption":"leverage the vision encoders of existing Vision Language Models (VLMs) as semantic anchors to align the vision embeddings with the textual space without incurring additional pre-training overhead"}},"verdict_id":"00e34123-b44d-42e0-9364-db5dc84462d1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9955f45d996764c2610d9e088cd2861f646667064c00f88cd3b3df3744937c55","target":"record","created_at":"2026-06-02T01:04:15Z","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":"3562199cf2d084986032a59499ce2052812db2c926891a30795a8bb3b1b4af6c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-21T08:09:25Z","title_canon_sha256":"d2a1a068867cb4809bb487fafe4e71da0aae14a881c6c13518fe7f758dc673b2"},"schema_version":"1.0","source":{"id":"2601.14750","kind":"arxiv","version":4}},"canonical_sha256":"f46a697efb419bbb8c9ba24d889b5902c337566ac46983c39be9b829b5a2ff63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f46a697efb419bbb8c9ba24d889b5902c337566ac46983c39be9b829b5a2ff63","first_computed_at":"2026-06-02T01:04:15.471492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:15.471492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RyetACfQIdaPgQBnhjIeKmyfjJjw3nZ8Dyx6irrVblOCbzlyj2xwiZlapspft3+4uwq8rk3yFFo/YlhmLDrjDw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:15.471947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.14750","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9955f45d996764c2610d9e088cd2861f646667064c00f88cd3b3df3744937c55","sha256:13785e04c1f6c3c93efa0955d8361f87700507fbe229995ad1a50be1a93c514c"],"state_sha256":"fc4b9f70ace26d5ca06770b97c3a45fb1c6518f2dc51ba7c0cd8f0f712c642e1"}