{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JDBNSSL7M7EKJGGT55HPZCN7HP","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":"3abf44ebf17ca669d8740e7a0533d4962b8f775b3e211a32d72a9b990347a6d9","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-08T03:00:56Z","title_canon_sha256":"84c30a74b34596d006804b8581b935d59b40e89bdc2b99711ea453c05dcaef80"},"schema_version":"1.0","source":{"id":"2606.08960","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08960","created_at":"2026-06-09T02:07:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08960v1","created_at":"2026-06-09T02:07:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08960","created_at":"2026-06-09T02:07:50Z"},{"alias_kind":"pith_short_12","alias_value":"JDBNSSL7M7EK","created_at":"2026-06-09T02:07:50Z"},{"alias_kind":"pith_short_16","alias_value":"JDBNSSL7M7EKJGGT","created_at":"2026-06-09T02:07:50Z"},{"alias_kind":"pith_short_8","alias_value":"JDBNSSL7","created_at":"2026-06-09T02:07:50Z"}],"graph_snapshots":[{"event_id":"sha256:804a35e97f6d4807c13144dbf69f34882d197715a8eab944290c50124ea708fd","target":"graph","created_at":"2026-06-09T02:07:50Z","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/2606.08960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1,968 tasks across five terminal-agent benchmarks and find 323 (16%) hackable by frontier models given only the task description. This corrupts both leaderboard rankings and RL training signal, yet the standard response is manual and reactive.\n  We introduce the hacker-fixer loop, a method for building exploit-resistant verifiers without per-task manual patching. The loop alternates three LLM agents: a hacker tries to pass the verifier without sol","authors_text":"Aditi Raghunathan, Ivan Bercovich, Ivgeni Segal, Kexun Zhang, Shashwat Saxena, Ziqian Zhong","cross_cats":["cs.AI","cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-08T03:00:56Z","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08960","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:bbf5cc6dc80f5dd4560b7662fa5b761baedfa6651579086e308b4f00ab511516","target":"record","created_at":"2026-06-09T02:07:50Z","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":"3abf44ebf17ca669d8740e7a0533d4962b8f775b3e211a32d72a9b990347a6d9","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-08T03:00:56Z","title_canon_sha256":"84c30a74b34596d006804b8581b935d59b40e89bdc2b99711ea453c05dcaef80"},"schema_version":"1.0","source":{"id":"2606.08960","kind":"arxiv","version":1}},"canonical_sha256":"48c2d9497f67c8a498d3ef4efc89bf3be0f90480ed2852718c5ea7883f519d39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48c2d9497f67c8a498d3ef4efc89bf3be0f90480ed2852718c5ea7883f519d39","first_computed_at":"2026-06-09T02:07:50.394741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:50.394741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FZRmUk/ebkcT2zMA8CQ+9HBEhaqpqaHv9JdNKrMUeOYKYDhXunD84Axg4tzZKr9HGdCwX/x9vo6SyMjEr4oSBw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:50.395629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08960","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbf5cc6dc80f5dd4560b7662fa5b761baedfa6651579086e308b4f00ab511516","sha256:804a35e97f6d4807c13144dbf69f34882d197715a8eab944290c50124ea708fd"],"state_sha256":"715e52c89b87e6ee329b4b1afac14bbb5cb57592a3d6873641d4554080f46367"}