{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2TAODQFPZIPHRYZ7RYHVYQ5ZDX","short_pith_number":"pith:2TAODQFP","schema_version":"1.0","canonical_sha256":"d4c0e1c0afca1e78e33f8e0f5c43b91dc7766248bbcc51229ea7c910eadf5713","source":{"kind":"arxiv","id":"2402.07754","version":3},"attestation_state":"computed","paper":{"title":"Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chuan Wu, Han Shi, Jiacheng Ye, Jiahui Gao, Liheng Chen, Lingpeng Kong, Lin Zheng, Shansan Gong, Wei Bi, Xin Jiang, Zhenguo Li","submitted_at":"2024-02-12T16:23:28Z","abstract_excerpt":"Recently, diffusion models have garnered significant interest in the field of text processing due to their many potential advantages compared to conventional autoregressive models. In this work, we propose Diffusion-of-Thought (DoT), a novel approach that integrates diffusion models with Chain-of-Thought, a well-established technique for improving the reasoning ability of autoregressive language models. In contrast to autoregressive language models that make decisions in a left-to-right, token-by-token manner, DoT allows reasoning steps to diffuse over time through a diffusion language model a"},"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":"2402.07754","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T16:23:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1c82e5eb9b494f6349f1b18279af245508185bf6cd2a9335adbc2498e2089b10","abstract_canon_sha256":"304b86bf8760035e19e2382b109d02fce46625df04c5e0bba01fe141192f2b3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:49.579642Z","signature_b64":"nMPjfqxmfoYUCbFMhMtBh54V/ucudbegUTEjwImQ+gj2cXVgBIBLxgFd5xopX4kloTrnlmhF6BU/ahKV8LupAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4c0e1c0afca1e78e33f8e0f5c43b91dc7766248bbcc51229ea7c910eadf5713","last_reissued_at":"2026-07-05T09:44:49.579149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:49.579149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chuan Wu, Han Shi, Jiacheng Ye, Jiahui Gao, Liheng Chen, Lingpeng Kong, Lin Zheng, Shansan Gong, Wei Bi, Xin Jiang, Zhenguo Li","submitted_at":"2024-02-12T16:23:28Z","abstract_excerpt":"Recently, diffusion models have garnered significant interest in the field of text processing due to their many potential advantages compared to conventional autoregressive models. In this work, we propose Diffusion-of-Thought (DoT), a novel approach that integrates diffusion models with Chain-of-Thought, a well-established technique for improving the reasoning ability of autoregressive language models. In contrast to autoregressive language models that make decisions in a left-to-right, token-by-token manner, DoT allows reasoning steps to diffuse over time through a diffusion language model a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07754","kind":"arxiv","version":3},"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/2402.07754/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":"2402.07754","created_at":"2026-07-05T09:44:49.579206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07754v3","created_at":"2026-07-05T09:44:49.579206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07754","created_at":"2026-07-05T09:44:49.579206+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TAODQFPZIPH","created_at":"2026-07-05T09:44:49.579206+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TAODQFPZIPHRYZ7","created_at":"2026-07-05T09:44:49.579206+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TAODQFP","created_at":"2026-07-05T09:44:49.579206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.17891","citing_title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17497","citing_title":"Self-Supervised On-Policy Distillation for Reasoning Language Models","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX","json":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX.json","graph_json":"https://pith.science/api/pith-number/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/graph.json","events_json":"https://pith.science/api/pith-number/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/events.json","paper":"https://pith.science/paper/2TAODQFP"},"agent_actions":{"view_html":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX","download_json":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX.json","view_paper":"https://pith.science/paper/2TAODQFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07754&json=true","fetch_graph":"https://pith.science/api/pith-number/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/graph.json","fetch_events":"https://pith.science/api/pith-number/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/action/storage_attestation","attest_author":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/action/author_attestation","sign_citation":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/action/citation_signature","submit_replication":"https://pith.science/pith/2TAODQFPZIPHRYZ7RYHVYQ5ZDX/action/replication_record"}},"created_at":"2026-07-05T09:44:49.579206+00:00","updated_at":"2026-07-05T09:44:49.579206+00:00"}