{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CO3FTT33JW3KZ3P4RTITOGUZXX","short_pith_number":"pith:CO3FTT33","schema_version":"1.0","canonical_sha256":"13b659cf7b4db6acedfc8cd1371a99bdc854321b81848a96aa7fd7ba12713d9f","source":{"kind":"arxiv","id":"2607.20268","version":1},"attestation_state":"computed","paper":{"title":"PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Anmol Kankariya, Sercan \\\"O. Ar{\\i}k","submitted_at":"2026-07-22T15:20:53Z","abstract_excerpt":"While Large Language Models (LLMs) excel at many tasks, they frequently struggle with complex reasoning that requires long-horizon planning and iterative error correction. Furthermore, standard single-stream prompting proves brittle when models encounter novel abstractions or rigorous domain constraints. We introduce PoTRE (Poly-Topological Reasoning Ensembles), a heterogeneous framework that decouples inference into four agents: (1) Adversarial Refinement Agent, (2) Hierarchical strategic Planning Agent, (3) Spectrum Search Agent, and (4) Direct Chain Agent. A final Task-Adaptive Aggregation "},"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":"2607.20268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-22T15:20:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b8bda212c17aaa06a895d9fa8d9b741870940da44695647bf0d114c0bc8c680e","abstract_canon_sha256":"8c222ed8a62d51feeaf183ea07c2ecb3857419b230c49a6fef62cd5ff4d84371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:25:10.995289Z","signature_b64":"u1beSlokHJbEgIEbLTEWZJ2h4w1gwzDe3Eq6VWMxW1/Xx13jN8wNRj/Z4YpR9jySUse4nvlIfjQTDPavK0OTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13b659cf7b4db6acedfc8cd1371a99bdc854321b81848a96aa7fd7ba12713d9f","last_reissued_at":"2026-07-23T01:25:10.994469Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:25:10.994469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Anmol Kankariya, Sercan \\\"O. Ar{\\i}k","submitted_at":"2026-07-22T15:20:53Z","abstract_excerpt":"While Large Language Models (LLMs) excel at many tasks, they frequently struggle with complex reasoning that requires long-horizon planning and iterative error correction. Furthermore, standard single-stream prompting proves brittle when models encounter novel abstractions or rigorous domain constraints. We introduce PoTRE (Poly-Topological Reasoning Ensembles), a heterogeneous framework that decouples inference into four agents: (1) Adversarial Refinement Agent, (2) Hierarchical strategic Planning Agent, (3) Spectrum Search Agent, and (4) Direct Chain Agent. A final Task-Adaptive Aggregation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20268","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/2607.20268/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":"2607.20268","created_at":"2026-07-23T01:25:10.994887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20268v1","created_at":"2026-07-23T01:25:10.994887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20268","created_at":"2026-07-23T01:25:10.994887+00:00"},{"alias_kind":"pith_short_12","alias_value":"CO3FTT33JW3K","created_at":"2026-07-23T01:25:10.994887+00:00"},{"alias_kind":"pith_short_16","alias_value":"CO3FTT33JW3KZ3P4","created_at":"2026-07-23T01:25:10.994887+00:00"},{"alias_kind":"pith_short_8","alias_value":"CO3FTT33","created_at":"2026-07-23T01:25:10.994887+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/CO3FTT33JW3KZ3P4RTITOGUZXX","json":"https://pith.science/pith/CO3FTT33JW3KZ3P4RTITOGUZXX.json","graph_json":"https://pith.science/api/pith-number/CO3FTT33JW3KZ3P4RTITOGUZXX/graph.json","events_json":"https://pith.science/api/pith-number/CO3FTT33JW3KZ3P4RTITOGUZXX/events.json","paper":"https://pith.science/paper/CO3FTT33"},"agent_actions":{"view_html":"https://pith.science/pith/CO3FTT33JW3KZ3P4RTITOGUZXX","download_json":"https://pith.science/pith/CO3FTT33JW3KZ3P4RTITOGUZXX.json","view_paper":"https://pith.science/paper/CO3FTT33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20268&json=true","fetch_graph":"https://pith.science/api/pith-number/CO3FTT33JW3KZ3P4RTITOGUZXX/graph.json","fetch_events":"https://pith.science/api/pith-number/CO3FTT33JW3KZ3P4RTITOGUZXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CO3FTT33JW3KZ3P4RTITOGUZXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CO3FTT33JW3KZ3P4RTITOGUZXX/action/storage_attestation","attest_author":"https://pith.science/pith/CO3FTT33JW3KZ3P4RTITOGUZXX/action/author_attestation","sign_citation":"https://pith.science/pith/CO3FTT33JW3KZ3P4RTITOGUZXX/action/citation_signature","submit_replication":"https://pith.science/pith/CO3FTT33JW3KZ3P4RTITOGUZXX/action/replication_record"}},"created_at":"2026-07-23T01:25:10.994887+00:00","updated_at":"2026-07-23T01:25:10.994887+00:00"}