{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I23T3BDAZ56GRZAKX3DNIBH5L3","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":"6173ddb2b9f99cf49f42200657462dc15f59331815f4bf7bad4ce08ffb491419","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T15:23:37Z","title_canon_sha256":"2df7f337d97436fc540018705eaf16da8215be1cecbc05ad2b4282a15bb4d99d"},"schema_version":"1.0","source":{"id":"2603.16654","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16654","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16654v2","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16654","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"I23T3BDAZ56G","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"I23T3BDAZ56GRZAK","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"I23T3BDA","created_at":"2026-05-27T02:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:70ab1ad8ba610ac968888196377ab0b6a8cb2140b27ff48e0d9942be9e3075b1","target":"graph","created_at":"2026-05-27T02:05:13Z","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/2603.16654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the reasoning abilities of large language models (LLMs) solely from final answers can obscure failures in intermediate steps, especially in multi-hop QA benchmarks without step-level annotations. To address this gap, we introduce Omanic, an open-domain 4-hop QA benchmark designed not only to measure final-answer accuracy but also to diagnose where reasoning breaks down. Omanic contains 10,296 machine-generated training examples (OmanicSynth) and 967 expert-reviewed human-annotated evaluation examples (OmanicBench), with each evaluation question decomposed into single-hop sub-questio","authors_text":"Aosong Feng, Chanjun Park, Irene Li, Jinghui Lu, Rex Ying, Sherry T. Tong, Sophia Simeng Han, Xiaojie Gu, Yingjian Chen, Yusuke Iwasawa, Yutaka Matsuo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T15:23:37Z","title":"Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16654","kind":"arxiv","version":2},"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":"sha256:3b6773895f649658d5995057c225da7ff8ae8f194dc8e5cc80117ab2dad64793","target":"record","created_at":"2026-05-27T02:05:13Z","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":"6173ddb2b9f99cf49f42200657462dc15f59331815f4bf7bad4ce08ffb491419","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T15:23:37Z","title_canon_sha256":"2df7f337d97436fc540018705eaf16da8215be1cecbc05ad2b4282a15bb4d99d"},"schema_version":"1.0","source":{"id":"2603.16654","kind":"arxiv","version":2}},"canonical_sha256":"46b73d8460cf7c68e40abec6d404fd5ef390050ec201481b82cb4803e46c3d60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46b73d8460cf7c68e40abec6d404fd5ef390050ec201481b82cb4803e46c3d60","first_computed_at":"2026-05-27T02:05:13.804648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:05:13.804648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6rurP/nzmXv3vqOpuHEEGf3TY9jeO6lPcxB2ogvksdd5ITWUHJ/TyI3N5fqNkBOlvcEy6vi7CDKggQDbVKKqCw==","signature_status":"signed_v1","signed_at":"2026-05-27T02:05:13.805305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.16654","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b6773895f649658d5995057c225da7ff8ae8f194dc8e5cc80117ab2dad64793","sha256:70ab1ad8ba610ac968888196377ab0b6a8cb2140b27ff48e0d9942be9e3075b1"],"state_sha256":"c710d67f8755716ddd3ac255eede536c3a70e62e4247ab2dda6030caeefd8480"}