{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5Z7TBQEA5GNECEJTCJQBZXATLY","short_pith_number":"pith:5Z7TBQEA","schema_version":"1.0","canonical_sha256":"ee7f30c080e99a41113312601cdc135e212dd73c206b1726875d271b25261107","source":{"kind":"arxiv","id":"2606.09585","version":1},"attestation_state":"computed","paper":{"title":"Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongjie Cheng, Heming Xia, Wenjie Li, Yongqi Li, Yutong Bian","submitted_at":"2026-06-08T14:58:59Z","abstract_excerpt":"Chain-of-Thought (CoT) improves the performance of Large Language Models (LLMs) and has been extended to Multimodal Large Language Models (MLLMs). More recent work further moves from text-based multimodal reasoning toward interleaved-modal reasoning, where intermediate steps can incorporate both textual rationales and visual evidence. In this work, we propose a bolder and more ambitious idea: could images alone serve as the reasoning medium for both language and multimodal tasks? To explore this, we propose optical reasoning, which treats images as a standalone reasoning medium. We instantiate"},"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":"2606.09585","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T14:58:59Z","cross_cats_sorted":[],"title_canon_sha256":"8ae5ee526cfff093976d26be999fc52faf00c98ea6a05defd92ee64ad6647888","abstract_canon_sha256":"d6459ba24050937ab360a364869f40f3a91aa50c9dd45a3ef65e6b0cfee732c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:57.460687Z","signature_b64":"heQfW/m7JuP/v6rTk7WNZp+ViAlizuAmrCausc/6pieKCCEvf9tRLsFCNP/CH2XpN/93QMBoVkRLLLe1qbvyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee7f30c080e99a41113312601cdc135e212dd73c206b1726875d271b25261107","last_reissued_at":"2026-06-09T02:08:57.459780Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:57.459780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongjie Cheng, Heming Xia, Wenjie Li, Yongqi Li, Yutong Bian","submitted_at":"2026-06-08T14:58:59Z","abstract_excerpt":"Chain-of-Thought (CoT) improves the performance of Large Language Models (LLMs) and has been extended to Multimodal Large Language Models (MLLMs). More recent work further moves from text-based multimodal reasoning toward interleaved-modal reasoning, where intermediate steps can incorporate both textual rationales and visual evidence. In this work, we propose a bolder and more ambitious idea: could images alone serve as the reasoning medium for both language and multimodal tasks? To explore this, we propose optical reasoning, which treats images as a standalone reasoning medium. We instantiate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09585","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/2606.09585/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":"2606.09585","created_at":"2026-06-09T02:08:57.459930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09585v1","created_at":"2026-06-09T02:08:57.459930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09585","created_at":"2026-06-09T02:08:57.459930+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Z7TBQEA5GNE","created_at":"2026-06-09T02:08:57.459930+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Z7TBQEA5GNECEJT","created_at":"2026-06-09T02:08:57.459930+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Z7TBQEA","created_at":"2026-06-09T02:08:57.459930+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/5Z7TBQEA5GNECEJTCJQBZXATLY","json":"https://pith.science/pith/5Z7TBQEA5GNECEJTCJQBZXATLY.json","graph_json":"https://pith.science/api/pith-number/5Z7TBQEA5GNECEJTCJQBZXATLY/graph.json","events_json":"https://pith.science/api/pith-number/5Z7TBQEA5GNECEJTCJQBZXATLY/events.json","paper":"https://pith.science/paper/5Z7TBQEA"},"agent_actions":{"view_html":"https://pith.science/pith/5Z7TBQEA5GNECEJTCJQBZXATLY","download_json":"https://pith.science/pith/5Z7TBQEA5GNECEJTCJQBZXATLY.json","view_paper":"https://pith.science/paper/5Z7TBQEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09585&json=true","fetch_graph":"https://pith.science/api/pith-number/5Z7TBQEA5GNECEJTCJQBZXATLY/graph.json","fetch_events":"https://pith.science/api/pith-number/5Z7TBQEA5GNECEJTCJQBZXATLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Z7TBQEA5GNECEJTCJQBZXATLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Z7TBQEA5GNECEJTCJQBZXATLY/action/storage_attestation","attest_author":"https://pith.science/pith/5Z7TBQEA5GNECEJTCJQBZXATLY/action/author_attestation","sign_citation":"https://pith.science/pith/5Z7TBQEA5GNECEJTCJQBZXATLY/action/citation_signature","submit_replication":"https://pith.science/pith/5Z7TBQEA5GNECEJTCJQBZXATLY/action/replication_record"}},"created_at":"2026-06-09T02:08:57.459930+00:00","updated_at":"2026-06-09T02:08:57.459930+00:00"}