{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q6IPFHEMVQBKHY2PNHK3ZEXG3A","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":"5726a137ae59ae22861117eefa227da84a9a6c64b207cd137d4ebef15ca0b0fd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-21T21:41:34Z","title_canon_sha256":"4c6de65e2fc674db32c09da8b3d44d4271a66275898f2d5266dee1b6b9bc68f5"},"schema_version":"1.0","source":{"id":"2606.22678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22678","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22678v1","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22678","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"Q6IPFHEMVQBK","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"Q6IPFHEMVQBKHY2P","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"Q6IPFHEM","created_at":"2026-06-23T02:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:850e4ea906a2b2faec3ce4388701469dc58d86f4417228b2b9ece4779036d88c","target":"graph","created_at":"2026-06-23T02:13:44Z","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/2606.22678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-world software engineering tasks. Existing benchmarks evaluate these agents almost exclusively on outcome correctness: whether generated code passes tests or resolves issues. We argue that this outcome-only lens is insufficient: an agent that arrives at a correct solution through reckless trial-and-error, without planning, verification, or graceful recovery, is fundamentally less reliable than one that follows sound engineering discipline. We introduce R","authors_text":"Meher Bhaskar Madiraju, Meher Sai Preetam Madiraju","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-21T21:41:34Z","title":"RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22678","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:a8e226899128de503d6f562649589ba833326cd0a471a0b57c7c0135041bc2a5","target":"record","created_at":"2026-06-23T02:13:44Z","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":"5726a137ae59ae22861117eefa227da84a9a6c64b207cd137d4ebef15ca0b0fd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-21T21:41:34Z","title_canon_sha256":"4c6de65e2fc674db32c09da8b3d44d4271a66275898f2d5266dee1b6b9bc68f5"},"schema_version":"1.0","source":{"id":"2606.22678","kind":"arxiv","version":1}},"canonical_sha256":"8790f29c8cac02a3e34f69d5bc92e6d816b57251136e7cca88d70bb5c00522d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8790f29c8cac02a3e34f69d5bc92e6d816b57251136e7cca88d70bb5c00522d9","first_computed_at":"2026-06-23T02:13:44.630563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:44.630563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W7SSaLClzd9KUk22a6fiEPWP9jorjDCxB8YiWsGo+DO63GibFxhc/LlXY5MOycbChDwbfI0mHCwJPj1wgOZQAA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:44.630969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8e226899128de503d6f562649589ba833326cd0a471a0b57c7c0135041bc2a5","sha256:850e4ea906a2b2faec3ce4388701469dc58d86f4417228b2b9ece4779036d88c"],"state_sha256":"1944f7e1c414f44f3bb51bcdf9cce9625aa98f89e5bf599cd91c34db6da2a1e8"}