{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q6IPFHEMVQBKHY2PNHK3ZEXG3A","short_pith_number":"pith:Q6IPFHEM","schema_version":"1.0","canonical_sha256":"8790f29c8cac02a3e34f69d5bc92e6d816b57251136e7cca88d70bb5c00522d9","source":{"kind":"arxiv","id":"2606.22678","version":1},"attestation_state":"computed","paper":{"title":"RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Meher Bhaskar Madiraju, Meher Sai Preetam Madiraju","submitted_at":"2026-06-21T21:41:34Z","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"},"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":"2606.22678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-21T21:41:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c6de65e2fc674db32c09da8b3d44d4271a66275898f2d5266dee1b6b9bc68f5","abstract_canon_sha256":"5726a137ae59ae22861117eefa227da84a9a6c64b207cd137d4ebef15ca0b0fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:44.630969Z","signature_b64":"W7SSaLClzd9KUk22a6fiEPWP9jorjDCxB8YiWsGo+DO63GibFxhc/LlXY5MOycbChDwbfI0mHCwJPj1wgOZQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8790f29c8cac02a3e34f69d5bc92e6d816b57251136e7cca88d70bb5c00522d9","last_reissued_at":"2026-06-23T02:13:44.630563Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:44.630563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Meher Bhaskar Madiraju, Meher Sai Preetam Madiraju","submitted_at":"2026-06-21T21:41:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22678","kind":"arxiv","version":1},"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/2606.22678/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":"2606.22678","created_at":"2026-06-23T02:13:44.630630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22678v1","created_at":"2026-06-23T02:13:44.630630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22678","created_at":"2026-06-23T02:13:44.630630+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6IPFHEMVQBK","created_at":"2026-06-23T02:13:44.630630+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6IPFHEMVQBKHY2P","created_at":"2026-06-23T02:13:44.630630+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6IPFHEM","created_at":"2026-06-23T02:13:44.630630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A","json":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A.json","graph_json":"https://pith.science/api/pith-number/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/graph.json","events_json":"https://pith.science/api/pith-number/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/events.json","paper":"https://pith.science/paper/Q6IPFHEM"},"agent_actions":{"view_html":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A","download_json":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A.json","view_paper":"https://pith.science/paper/Q6IPFHEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22678&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/action/storage_attestation","attest_author":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/action/author_attestation","sign_citation":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/action/citation_signature","submit_replication":"https://pith.science/pith/Q6IPFHEMVQBKHY2PNHK3ZEXG3A/action/replication_record"}},"created_at":"2026-06-23T02:13:44.630630+00:00","updated_at":"2026-06-23T02:13:44.630630+00:00"}