{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YATQFDHA2KKLSTA6EQS2VKTLDK","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":"5bf821b1f9dac395c9b3a6c8254685dec649fd11b603156be4bc7405d2fc5565","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-24T03:16:32Z","title_canon_sha256":"a7f8be7325c122701eb20c32c30495e94c3492426b46a35bfe3ba5cf9d9ac876"},"schema_version":"1.0","source":{"id":"2603.22744","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.22744","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"arxiv_version","alias_value":"2603.22744v2","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.22744","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"pith_short_12","alias_value":"YATQFDHA2KKL","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"pith_short_16","alias_value":"YATQFDHA2KKLSTA6","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"pith_short_8","alias_value":"YATQFDHA","created_at":"2026-06-01T01:02:37Z"}],"graph_snapshots":[{"event_id":"sha256:7cdb57828198638f306ae1d046c8726c89374205b3336fd5e7a023501edaee0d","target":"graph","created_at":"2026-06-01T01:02:37Z","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/2603.22744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models excel on objectively verifiable tasks such as math and programming, where evaluation reduces to unit tests or a single correct answer. In contrast, real-world enterprise work is often subjective and context-dependent: success hinges on organizational goals, user intent, and the quality of intermediate artifacts produced across long, multi-tool workflows.\n  We introduce LH-Bench, a three-pillar evaluation design that moves beyond binary correctness to score autonomous, long-horizon execution on subjective enterprise tasks. The pillars are: (i) expert-grounded rubrics that ","authors_text":"Abhishek Chandwani, Ishan Gupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-24T03:16:32Z","title":"LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.22744","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":"sha256:2ec6640d1990894d95a0de5072893e0360d6b6f164df7a6af75853392dccd3ba","target":"record","created_at":"2026-06-01T01:02:37Z","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":"5bf821b1f9dac395c9b3a6c8254685dec649fd11b603156be4bc7405d2fc5565","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-24T03:16:32Z","title_canon_sha256":"a7f8be7325c122701eb20c32c30495e94c3492426b46a35bfe3ba5cf9d9ac876"},"schema_version":"1.0","source":{"id":"2603.22744","kind":"arxiv","version":2}},"canonical_sha256":"c027028ce0d294b94c1e2425aaaa6b1aa9a55b3aac5147323064f96bc70a8544","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c027028ce0d294b94c1e2425aaaa6b1aa9a55b3aac5147323064f96bc70a8544","first_computed_at":"2026-06-01T01:02:37.882051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:37.882051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RhvkMlKCaaz5g8LpLxTGPxdgAVC1WAiWjz++WarpluL4U3IQAeG0GgigLyu+pU74WJmYhVYZT5p/oXfpVZXFBQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:37.882988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.22744","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ec6640d1990894d95a0de5072893e0360d6b6f164df7a6af75853392dccd3ba","sha256:7cdb57828198638f306ae1d046c8726c89374205b3336fd5e7a023501edaee0d"],"state_sha256":"0570ccf7fbd5b272f7c912ed066d824c98bcc6b3c54b2cf54431cc20b37eadea"}