{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CXQYCJ2KS5IOAO2WMK7VBGA77S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"428a0e678e46bef1f962db358a5fb7a7b81bc13962934b27f630c08814e8bf67","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T18:46:17Z","title_canon_sha256":"bafc1a5ddc5913a0e7ad9a12689f2bf00231cfaaf57f273e25b325b33d44eab3"},"schema_version":"1.0","source":{"id":"2607.18438","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18438","created_at":"2026-07-22T00:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18438v1","created_at":"2026-07-22T00:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18438","created_at":"2026-07-22T00:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"CXQYCJ2KS5IO","created_at":"2026-07-22T00:22:48Z"},{"alias_kind":"pith_short_16","alias_value":"CXQYCJ2KS5IOAO2W","created_at":"2026-07-22T00:22:48Z"},{"alias_kind":"pith_short_8","alias_value":"CXQYCJ2K","created_at":"2026-07-22T00:22:48Z"}],"graph_snapshots":[{"event_id":"sha256:09a9832343dd8ef9829ea88b2c71114d54b29dddd50f75d574d15fc0c0ab9991","target":"graph","created_at":"2026-07-22T00:22:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.18438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Liam Swayne","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T18:46:17Z","title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18438","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:88c6dfecfce215331204d3594464583853d8f4cfb0bc285c65d7b4f258e04acd","target":"record","created_at":"2026-07-22T00:22:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"428a0e678e46bef1f962db358a5fb7a7b81bc13962934b27f630c08814e8bf67","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T18:46:17Z","title_canon_sha256":"bafc1a5ddc5913a0e7ad9a12689f2bf00231cfaaf57f273e25b325b33d44eab3"},"schema_version":"1.0","source":{"id":"2607.18438","kind":"arxiv","version":1}},"canonical_sha256":"15e181274a9750e03b5662bf50981ffc8475cab2f5ef4106a8f1ce0b7ee29c3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15e181274a9750e03b5662bf50981ffc8475cab2f5ef4106a8f1ce0b7ee29c3c","first_computed_at":"2026-07-22T00:22:48.580969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:48.580969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lRxPzfU7qksZZOSoYvsLjyq2KqccNtELTHS86lLFXAM3PkA84CqW4uGj4DxuImDVfp0T7FOCraAjRA27VXt7Aw==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:48.581835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18438","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88c6dfecfce215331204d3594464583853d8f4cfb0bc285c65d7b4f258e04acd","sha256:09a9832343dd8ef9829ea88b2c71114d54b29dddd50f75d574d15fc0c0ab9991"],"state_sha256":"c1550cd3b3bff0acc0259019a7732176fad6a8c8af5484f1f2a7670fb79ad588"}