{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BS276OFM4IOJ22QOZE23TAKC47","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":"3dcab8da46f072e2bcbe9d2b7f927f79bfb12c71f560c7ab7c96eee4f578e68d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T07:07:57Z","title_canon_sha256":"0b84f10a5e5042a199a8eb7b465bb95e0640583a86ff98e730e5f9e3f47bbc1b"},"schema_version":"1.0","source":{"id":"2608.11727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11727","created_at":"2026-08-13T01:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11727v1","created_at":"2026-08-13T01:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11727","created_at":"2026-08-13T01:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"BS276OFM4IOJ","created_at":"2026-08-13T01:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"BS276OFM4IOJ22QO","created_at":"2026-08-13T01:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"BS276OFM","created_at":"2026-08-13T01:27:56Z"}],"graph_snapshots":[{"event_id":"sha256:f659eca7ef67169ae659e2815f453162a8e906b9813e1ee26928afc91ddc278e","target":"graph","created_at":"2026-08-13T01:27:56Z","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/2608.11727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference: they concentrate rules in the user turn, while coding-agent benchmarks emphasize final task success. We introduce Harness-IF, which scores operational rules one at a time from execution evidence: 60 realistic multi-turn coding items drawn from a 642-rule library, 256 rules receiving verdicts, placed on the five configurable surfaces a deployed agent reads. To separate compliance from coincidence we introduce Against-Prior Accuracy (AP-Acc), wh","authors_text":"Changxin Pu, Ge Zhang, Haodong Wang, Haoran Que, Hong Zeng, Jin Chen, Shen Yan, Wenhao Huang, Zhongfei Hou, Zining Huang, Zuo Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T07:07:57Z","title":"Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11727","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":"sha256:218e0fb304cd6e2fb92531ebad7c9187cd91577bdd07f179bbf8a8bcafb8785d","target":"record","created_at":"2026-08-13T01:27:56Z","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":"3dcab8da46f072e2bcbe9d2b7f927f79bfb12c71f560c7ab7c96eee4f578e68d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T07:07:57Z","title_canon_sha256":"0b84f10a5e5042a199a8eb7b465bb95e0640583a86ff98e730e5f9e3f47bbc1b"},"schema_version":"1.0","source":{"id":"2608.11727","kind":"arxiv","version":1}},"canonical_sha256":"0cb5ff38ace21c9d6a0ec935b98142e7f3ec581422aa57f5c0f87f8adaeecdfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cb5ff38ace21c9d6a0ec935b98142e7f3ec581422aa57f5c0f87f8adaeecdfb","first_computed_at":"2026-08-13T01:27:56.607791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:27:56.607791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/k+MJdKVkwAbI5loLb2ikOzdhWdpmFoXt2r9fh5/3zkatERm3GKt2fVHbYZ22KIjce1SRQwv8jxmc9+GsTDoCQ==","signature_status":"signed_v1","signed_at":"2026-08-13T01:27:56.610118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:218e0fb304cd6e2fb92531ebad7c9187cd91577bdd07f179bbf8a8bcafb8785d","sha256:f659eca7ef67169ae659e2815f453162a8e906b9813e1ee26928afc91ddc278e"],"state_sha256":"480bbe2cd5cfd54b2b6c7f6b0fbf2d3a451e86b3a625efb42b0a84e82ba2df2d"}