{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QBU4XORNJLMKWTOFKICKWCHQLO","short_pith_number":"pith:QBU4XORN","schema_version":"1.0","canonical_sha256":"8069cbba2d4ad8ab4dc55204ab08f05bb8f52457d954f376934c1d2eda5e92c5","source":{"kind":"arxiv","id":"2607.17710","version":1},"attestation_state":"computed","paper":{"title":"Planning with Transformers: Chain of Computation and Structured Context Windows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ehsan Futuhi, Nathan R. Sturtevant","submitted_at":"2026-07-20T09:06:15Z","abstract_excerpt":"Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning. However, recent studies have shown that they struggle to reliably solve planning problems. At the same time, theoretical results have shown that transformers, the core architecture underlying modern LLMs, are Turing-complete. In this work, we investigate this apparent gap between the theoretical computational power of LLMs and their empirical planning performance. We propose Chain of Computation (COC), a computational architecture that places a transformer-based LM inside an iterative loop, leverag"},"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":"2607.17710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T09:06:15Z","cross_cats_sorted":[],"title_canon_sha256":"c7e1c93d34197a6d7bd10b8cd6c7744a5d007a722101a53060ad389204b191e6","abstract_canon_sha256":"884eb7d3f5d2c375a5c81febac169bc9dc75f72f4d310590381300c0deff4581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:21:55.702412Z","signature_b64":"milrg38CcqILBTiix0/geQSXb2M+Mz0dtK2DhfbTPh4x/pJbNUwhwwIUmSFVwqrvdkSTtLJ3aajC1hungvv2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8069cbba2d4ad8ab4dc55204ab08f05bb8f52457d954f376934c1d2eda5e92c5","last_reissued_at":"2026-07-21T02:21:55.701528Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:21:55.701528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Planning with Transformers: Chain of Computation and Structured Context Windows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ehsan Futuhi, Nathan R. Sturtevant","submitted_at":"2026-07-20T09:06:15Z","abstract_excerpt":"Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning. However, recent studies have shown that they struggle to reliably solve planning problems. At the same time, theoretical results have shown that transformers, the core architecture underlying modern LLMs, are Turing-complete. In this work, we investigate this apparent gap between the theoretical computational power of LLMs and their empirical planning performance. We propose Chain of Computation (COC), a computational architecture that places a transformer-based LM inside an iterative loop, leverag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17710","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/2607.17710/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":"2607.17710","created_at":"2026-07-21T02:21:55.701988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17710v1","created_at":"2026-07-21T02:21:55.701988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17710","created_at":"2026-07-21T02:21:55.701988+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBU4XORNJLMK","created_at":"2026-07-21T02:21:55.701988+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBU4XORNJLMKWTOF","created_at":"2026-07-21T02:21:55.701988+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBU4XORN","created_at":"2026-07-21T02:21:55.701988+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/QBU4XORNJLMKWTOFKICKWCHQLO","json":"https://pith.science/pith/QBU4XORNJLMKWTOFKICKWCHQLO.json","graph_json":"https://pith.science/api/pith-number/QBU4XORNJLMKWTOFKICKWCHQLO/graph.json","events_json":"https://pith.science/api/pith-number/QBU4XORNJLMKWTOFKICKWCHQLO/events.json","paper":"https://pith.science/paper/QBU4XORN"},"agent_actions":{"view_html":"https://pith.science/pith/QBU4XORNJLMKWTOFKICKWCHQLO","download_json":"https://pith.science/pith/QBU4XORNJLMKWTOFKICKWCHQLO.json","view_paper":"https://pith.science/paper/QBU4XORN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17710&json=true","fetch_graph":"https://pith.science/api/pith-number/QBU4XORNJLMKWTOFKICKWCHQLO/graph.json","fetch_events":"https://pith.science/api/pith-number/QBU4XORNJLMKWTOFKICKWCHQLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBU4XORNJLMKWTOFKICKWCHQLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBU4XORNJLMKWTOFKICKWCHQLO/action/storage_attestation","attest_author":"https://pith.science/pith/QBU4XORNJLMKWTOFKICKWCHQLO/action/author_attestation","sign_citation":"https://pith.science/pith/QBU4XORNJLMKWTOFKICKWCHQLO/action/citation_signature","submit_replication":"https://pith.science/pith/QBU4XORNJLMKWTOFKICKWCHQLO/action/replication_record"}},"created_at":"2026-07-21T02:21:55.701988+00:00","updated_at":"2026-07-21T02:21:55.701988+00:00"}