{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CXQYCJ2KS5IOAO2WMK7VBGA77S","short_pith_number":"pith:CXQYCJ2K","schema_version":"1.0","canonical_sha256":"15e181274a9750e03b5662bf50981ffc8475cab2f5ef4106a8f1ce0b7ee29c3c","source":{"kind":"arxiv","id":"2607.18438","version":1},"attestation_state":"computed","paper":{"title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Liam Swayne","submitted_at":"2026-07-20T18:46:17Z","abstract_excerpt":"Introducing Relay-Bench, an unsaturated, holistic, text-only benchmark that measures LLMs' ability to complete an assortment of tasks from distinct domains in a single prompt. The leading model, GPT-5.5 (xHigh), scores 43.3%. The test set entirely consists of composite problems: groups of single-domain subproblems that are strung together into challenges that require reasoning across multiple domains in combination. Many of these problems then have layers of complexity added through prompt encoding and deliberate context bloat. Domains tested include visual reasoning, coding, math, information"},"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":"2607.18438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T18:46:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bafc1a5ddc5913a0e7ad9a12689f2bf00231cfaaf57f273e25b325b33d44eab3","abstract_canon_sha256":"428a0e678e46bef1f962db358a5fb7a7b81bc13962934b27f630c08814e8bf67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:48.581835Z","signature_b64":"lRxPzfU7qksZZOSoYvsLjyq2KqccNtELTHS86lLFXAM3PkA84CqW4uGj4DxuImDVfp0T7FOCraAjRA27VXt7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15e181274a9750e03b5662bf50981ffc8475cab2f5ef4106a8f1ce0b7ee29c3c","last_reissued_at":"2026-07-22T00:22:48.580969Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:48.580969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Liam Swayne","submitted_at":"2026-07-20T18:46:17Z","abstract_excerpt":"Introducing Relay-Bench, an unsaturated, holistic, text-only benchmark that measures LLMs' ability to complete an assortment of tasks from distinct domains in a single prompt. The leading model, GPT-5.5 (xHigh), scores 43.3%. The test set entirely consists of composite problems: groups of single-domain subproblems that are strung together into challenges that require reasoning across multiple domains in combination. Many of these problems then have layers of complexity added through prompt encoding and deliberate context bloat. Domains tested include visual reasoning, coding, math, information"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18438","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/2607.18438/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":"2607.18438","created_at":"2026-07-22T00:22:48.581394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18438v1","created_at":"2026-07-22T00:22:48.581394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18438","created_at":"2026-07-22T00:22:48.581394+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXQYCJ2KS5IO","created_at":"2026-07-22T00:22:48.581394+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXQYCJ2KS5IOAO2W","created_at":"2026-07-22T00:22:48.581394+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXQYCJ2K","created_at":"2026-07-22T00:22:48.581394+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/CXQYCJ2KS5IOAO2WMK7VBGA77S","json":"https://pith.science/pith/CXQYCJ2KS5IOAO2WMK7VBGA77S.json","graph_json":"https://pith.science/api/pith-number/CXQYCJ2KS5IOAO2WMK7VBGA77S/graph.json","events_json":"https://pith.science/api/pith-number/CXQYCJ2KS5IOAO2WMK7VBGA77S/events.json","paper":"https://pith.science/paper/CXQYCJ2K"},"agent_actions":{"view_html":"https://pith.science/pith/CXQYCJ2KS5IOAO2WMK7VBGA77S","download_json":"https://pith.science/pith/CXQYCJ2KS5IOAO2WMK7VBGA77S.json","view_paper":"https://pith.science/paper/CXQYCJ2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18438&json=true","fetch_graph":"https://pith.science/api/pith-number/CXQYCJ2KS5IOAO2WMK7VBGA77S/graph.json","fetch_events":"https://pith.science/api/pith-number/CXQYCJ2KS5IOAO2WMK7VBGA77S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXQYCJ2KS5IOAO2WMK7VBGA77S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXQYCJ2KS5IOAO2WMK7VBGA77S/action/storage_attestation","attest_author":"https://pith.science/pith/CXQYCJ2KS5IOAO2WMK7VBGA77S/action/author_attestation","sign_citation":"https://pith.science/pith/CXQYCJ2KS5IOAO2WMK7VBGA77S/action/citation_signature","submit_replication":"https://pith.science/pith/CXQYCJ2KS5IOAO2WMK7VBGA77S/action/replication_record"}},"created_at":"2026-07-22T00:22:48.581394+00:00","updated_at":"2026-07-22T00:22:48.581394+00:00"}