{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GTVYZKN4FIVXFIZYQTLQBIE7LO","short_pith_number":"pith:GTVYZKN4","schema_version":"1.0","canonical_sha256":"34eb8ca9bc2a2b72a33884d700a09f5bad9813a0a3a23a20eebb874244df4d8d","source":{"kind":"arxiv","id":"2606.19697","version":1},"attestation_state":"computed","paper":{"title":"Efficiently Representing Algorithms With Chain-of-Thought Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Anej Svete, Ashish Sabharwal, William Merrill, Yanhong Li","submitted_at":"2026-06-18T01:49:29Z","abstract_excerpt":"The increasing popularity of \\emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation. However, the Turing machine, while suitable for complexity-theoretic analysis, is not convenient, intuitive, or efficient for discussing algorithms. Algorithms are typically designed and analyzed at a higher level of abstraction, captured by the \\emph{Word RAM} model with random-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":"2606.19697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T01:49:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5865eae02469ed4ca076c3df1748cd2931ff6fc4933e3b528d35448235d755de","abstract_canon_sha256":"61313e4566c617c0c52afec72dd90fe801db7090b8b9edc47eca8f7f9855d9c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:32.457139Z","signature_b64":"/4jceNf9+WNr34qXXv/9rjveWs3yZbQGYQWApCqngXQ4HbX5NMtGVrMyCR6JRDhit+h9MNyX50mYuzfk+pITBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34eb8ca9bc2a2b72a33884d700a09f5bad9813a0a3a23a20eebb874244df4d8d","last_reissued_at":"2026-06-19T16:12:32.456712Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:32.456712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficiently Representing Algorithms With Chain-of-Thought Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Anej Svete, Ashish Sabharwal, William Merrill, Yanhong Li","submitted_at":"2026-06-18T01:49:29Z","abstract_excerpt":"The increasing popularity of \\emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation. However, the Turing machine, while suitable for complexity-theoretic analysis, is not convenient, intuitive, or efficient for discussing algorithms. Algorithms are typically designed and analyzed at a higher level of abstraction, captured by the \\emph{Word RAM} model with random-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19697","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/2606.19697/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":"2606.19697","created_at":"2026-06-19T16:12:32.456766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19697v1","created_at":"2026-06-19T16:12:32.456766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19697","created_at":"2026-06-19T16:12:32.456766+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTVYZKN4FIVX","created_at":"2026-06-19T16:12:32.456766+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTVYZKN4FIVXFIZY","created_at":"2026-06-19T16:12:32.456766+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTVYZKN4","created_at":"2026-06-19T16:12:32.456766+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/GTVYZKN4FIVXFIZYQTLQBIE7LO","json":"https://pith.science/pith/GTVYZKN4FIVXFIZYQTLQBIE7LO.json","graph_json":"https://pith.science/api/pith-number/GTVYZKN4FIVXFIZYQTLQBIE7LO/graph.json","events_json":"https://pith.science/api/pith-number/GTVYZKN4FIVXFIZYQTLQBIE7LO/events.json","paper":"https://pith.science/paper/GTVYZKN4"},"agent_actions":{"view_html":"https://pith.science/pith/GTVYZKN4FIVXFIZYQTLQBIE7LO","download_json":"https://pith.science/pith/GTVYZKN4FIVXFIZYQTLQBIE7LO.json","view_paper":"https://pith.science/paper/GTVYZKN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19697&json=true","fetch_graph":"https://pith.science/api/pith-number/GTVYZKN4FIVXFIZYQTLQBIE7LO/graph.json","fetch_events":"https://pith.science/api/pith-number/GTVYZKN4FIVXFIZYQTLQBIE7LO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTVYZKN4FIVXFIZYQTLQBIE7LO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTVYZKN4FIVXFIZYQTLQBIE7LO/action/storage_attestation","attest_author":"https://pith.science/pith/GTVYZKN4FIVXFIZYQTLQBIE7LO/action/author_attestation","sign_citation":"https://pith.science/pith/GTVYZKN4FIVXFIZYQTLQBIE7LO/action/citation_signature","submit_replication":"https://pith.science/pith/GTVYZKN4FIVXFIZYQTLQBIE7LO/action/replication_record"}},"created_at":"2026-06-19T16:12:32.456766+00:00","updated_at":"2026-06-19T16:12:32.456766+00:00"}