{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:552DAJ6CMXPTA4RW77MXUCUKXM","short_pith_number":"pith:552DAJ6C","schema_version":"1.0","canonical_sha256":"ef743027c265df307236ffd97a0a8abb3eee533ce09588085636e0af9fdd7bbc","source":{"kind":"arxiv","id":"2608.13221","version":1},"attestation_state":"computed","paper":{"title":"TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chaoyang Zhang, Jiale Liu, Qingpei Guo, Shunwen Bai, Yarong Wang, Zhen Qin, Ziping Ma","submitted_at":"2026-08-13T13:24:47Z","abstract_excerpt":"The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning paths and allocate reasoning resources--that is, how they organize search. Prior process-level methods focus on the coherence and redundancy of chain-of-thought (CoT), and most benchmark tasks have a single objective solvable by static capabilities such as derivation and tool use, leaving search organization unmeasured. We introduce TsuGO, a process-level reasoning benchmark for evaluating Search Efficiency in LLM reasoning throu"},"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":"2608.13221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-13T13:24:47Z","cross_cats_sorted":[],"title_canon_sha256":"ac1cc7cd600f775d5db6073183d474591104eae550f2cde157a6bd912f899aeb","abstract_canon_sha256":"38596eb4b0961f58ad7986ba7c5114776dd12e29149e4bc1e85486a49ac7a8c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:42.440452Z","signature_b64":"TLSywtcuet4QLu6Hf6XbK50HIO7hl9uo2/enFwYbvriaNaX2upZxDDC704H1azLgJzcJjXsWpEkPI1b1XUJqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef743027c265df307236ffd97a0a8abb3eee533ce09588085636e0af9fdd7bbc","last_reissued_at":"2026-08-14T01:00:42.438367Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:42.438367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chaoyang Zhang, Jiale Liu, Qingpei Guo, Shunwen Bai, Yarong Wang, Zhen Qin, Ziping Ma","submitted_at":"2026-08-13T13:24:47Z","abstract_excerpt":"The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning paths and allocate reasoning resources--that is, how they organize search. Prior process-level methods focus on the coherence and redundancy of chain-of-thought (CoT), and most benchmark tasks have a single objective solvable by static capabilities such as derivation and tool use, leaving search organization unmeasured. We introduce TsuGO, a process-level reasoning benchmark for evaluating Search Efficiency in LLM reasoning throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13221","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/2608.13221/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":"2608.13221","created_at":"2026-08-14T01:00:42.439415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13221v1","created_at":"2026-08-14T01:00:42.439415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13221","created_at":"2026-08-14T01:00:42.439415+00:00"},{"alias_kind":"pith_short_12","alias_value":"552DAJ6CMXPT","created_at":"2026-08-14T01:00:42.439415+00:00"},{"alias_kind":"pith_short_16","alias_value":"552DAJ6CMXPTA4RW","created_at":"2026-08-14T01:00:42.439415+00:00"},{"alias_kind":"pith_short_8","alias_value":"552DAJ6C","created_at":"2026-08-14T01:00:42.439415+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/552DAJ6CMXPTA4RW77MXUCUKXM","json":"https://pith.science/pith/552DAJ6CMXPTA4RW77MXUCUKXM.json","graph_json":"https://pith.science/api/pith-number/552DAJ6CMXPTA4RW77MXUCUKXM/graph.json","events_json":"https://pith.science/api/pith-number/552DAJ6CMXPTA4RW77MXUCUKXM/events.json","paper":"https://pith.science/paper/552DAJ6C"},"agent_actions":{"view_html":"https://pith.science/pith/552DAJ6CMXPTA4RW77MXUCUKXM","download_json":"https://pith.science/pith/552DAJ6CMXPTA4RW77MXUCUKXM.json","view_paper":"https://pith.science/paper/552DAJ6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13221&json=true","fetch_graph":"https://pith.science/api/pith-number/552DAJ6CMXPTA4RW77MXUCUKXM/graph.json","fetch_events":"https://pith.science/api/pith-number/552DAJ6CMXPTA4RW77MXUCUKXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/552DAJ6CMXPTA4RW77MXUCUKXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/552DAJ6CMXPTA4RW77MXUCUKXM/action/storage_attestation","attest_author":"https://pith.science/pith/552DAJ6CMXPTA4RW77MXUCUKXM/action/author_attestation","sign_citation":"https://pith.science/pith/552DAJ6CMXPTA4RW77MXUCUKXM/action/citation_signature","submit_replication":"https://pith.science/pith/552DAJ6CMXPTA4RW77MXUCUKXM/action/replication_record"}},"created_at":"2026-08-14T01:00:42.439415+00:00","updated_at":"2026-08-14T01:00:42.439415+00:00"}