{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YATQFDHA2KKLSTA6EQS2VKTLDK","short_pith_number":"pith:YATQFDHA","schema_version":"1.0","canonical_sha256":"c027028ce0d294b94c1e2425aaaa6b1aa9a55b3aac5147323064f96bc70a8544","source":{"kind":"arxiv","id":"2603.22744","version":2},"attestation_state":"computed","paper":{"title":"LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Chandwani, Ishan Gupta","submitted_at":"2026-03-24T03:16:32Z","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 "},"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":"2603.22744","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-24T03:16:32Z","cross_cats_sorted":[],"title_canon_sha256":"a7f8be7325c122701eb20c32c30495e94c3492426b46a35bfe3ba5cf9d9ac876","abstract_canon_sha256":"5bf821b1f9dac395c9b3a6c8254685dec649fd11b603156be4bc7405d2fc5565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:37.882988Z","signature_b64":"RhvkMlKCaaz5g8LpLxTGPxdgAVC1WAiWjz++WarpluL4U3IQAeG0GgigLyu+pU74WJmYhVYZT5p/oXfpVZXFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c027028ce0d294b94c1e2425aaaa6b1aa9a55b3aac5147323064f96bc70a8544","last_reissued_at":"2026-06-01T01:02:37.882051Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:37.882051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Chandwani, Ishan Gupta","submitted_at":"2026-03-24T03:16:32Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.22744","kind":"arxiv","version":2},"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/2603.22744/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":"2603.22744","created_at":"2026-06-01T01:02:37.882184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.22744v2","created_at":"2026-06-01T01:02:37.882184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.22744","created_at":"2026-06-01T01:02:37.882184+00:00"},{"alias_kind":"pith_short_12","alias_value":"YATQFDHA2KKL","created_at":"2026-06-01T01:02:37.882184+00:00"},{"alias_kind":"pith_short_16","alias_value":"YATQFDHA2KKLSTA6","created_at":"2026-06-01T01:02:37.882184+00:00"},{"alias_kind":"pith_short_8","alias_value":"YATQFDHA","created_at":"2026-06-01T01:02:37.882184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15230","citing_title":"EnergyAgentBench: Benchmarking LLM Agents on Live Energy Infrastructure Data","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK","json":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK.json","graph_json":"https://pith.science/api/pith-number/YATQFDHA2KKLSTA6EQS2VKTLDK/graph.json","events_json":"https://pith.science/api/pith-number/YATQFDHA2KKLSTA6EQS2VKTLDK/events.json","paper":"https://pith.science/paper/YATQFDHA"},"agent_actions":{"view_html":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK","download_json":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK.json","view_paper":"https://pith.science/paper/YATQFDHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.22744&json=true","fetch_graph":"https://pith.science/api/pith-number/YATQFDHA2KKLSTA6EQS2VKTLDK/graph.json","fetch_events":"https://pith.science/api/pith-number/YATQFDHA2KKLSTA6EQS2VKTLDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK/action/storage_attestation","attest_author":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK/action/author_attestation","sign_citation":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK/action/citation_signature","submit_replication":"https://pith.science/pith/YATQFDHA2KKLSTA6EQS2VKTLDK/action/replication_record"}},"created_at":"2026-06-01T01:02:37.882184+00:00","updated_at":"2026-06-01T01:02:37.882184+00:00"}