{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QFCLTIUX77VTP3BDYHYKE6Q76K","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":"1e521610acc37fa404b34b509fc2d46a4e828948ce70d0316bd7e334943d2029","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:21:05Z","title_canon_sha256":"1120a839c5d26efaf20b7f9d6e40b5edb1f399fbf8873087805ccb918d8daad3"},"schema_version":"1.0","source":{"id":"2608.06301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06301","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06301v1","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06301","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_12","alias_value":"QFCLTIUX77VT","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_16","alias_value":"QFCLTIUX77VTP3BD","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_8","alias_value":"QFCLTIUX","created_at":"2026-08-07T01:41:19Z"}],"graph_snapshots":[{"event_id":"sha256:6130ee7e7a52a8e14c8875923ec8eb23f4fb5eff8b5fe158a818e7a6bae65aa3","target":"graph","created_at":"2026-08-07T01:41:19Z","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/2608.06301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them. This makes automated harness optimization -- the iterative and evaluation-guided improvement of a harness by an AI system -- both an important route to improving AI systems and a demanding capability for AI systems themselves. Yet the community lacks a common protocol for measuring how well frontier LLMs perform at this task. We introduce HarnessOpt-Bench, a benchmark for end","authors_text":"Apaar Shanker, Shehab Yasser, Varun Ursekar, Veronica Chatrath, Vijay S. Kalmath, Yash Maurya, Yuan Xue","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:21:05Z","title":"HarnessOpt-Bench: Evaluating LLMs at Harness Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06301","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:b6974b3732cd70df6fdb7ce2c6838ad33f0323e45147fbbdde240d8018ddf6c7","target":"record","created_at":"2026-08-07T01:41:19Z","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":"1e521610acc37fa404b34b509fc2d46a4e828948ce70d0316bd7e334943d2029","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:21:05Z","title_canon_sha256":"1120a839c5d26efaf20b7f9d6e40b5edb1f399fbf8873087805ccb918d8daad3"},"schema_version":"1.0","source":{"id":"2608.06301","kind":"arxiv","version":1}},"canonical_sha256":"8144b9a297ffeb37ec23c1f0a27a1ff2867f417e170018a008d3c16f4cd7abe8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8144b9a297ffeb37ec23c1f0a27a1ff2867f417e170018a008d3c16f4cd7abe8","first_computed_at":"2026-08-07T01:41:19.622012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T01:41:19.622012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4l98QFbdoy61CBz56Tw4KmGsgX4adl9fF7z2Y9uQBuYN83L/4murx4S+D2FoTrr+sH5GkLXpZEu2YB2CSqGTCg==","signature_status":"signed_v1","signed_at":"2026-08-07T01:41:19.623670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6974b3732cd70df6fdb7ce2c6838ad33f0323e45147fbbdde240d8018ddf6c7","sha256:6130ee7e7a52a8e14c8875923ec8eb23f4fb5eff8b5fe158a818e7a6bae65aa3"],"state_sha256":"db36bb9e4039a81dcf3e0a3e5bcf8df92350203ffbf1682807d4b411e62851ee"}