{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PL7ZTNCKKM2FQHUP7YSMQU7FQL","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":"a117206bf2d158dfd6b7cd0306112466b2a8750d96fc8080d0677d2ebbdf1fe9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-01T18:20:27Z","title_canon_sha256":"444c79c981bc2e014a42479a931c73cff1aa2b5c9dba04f4f5d9ee446d43a421"},"schema_version":"1.0","source":{"id":"2607.01360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01360","created_at":"2026-07-03T00:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01360v1","created_at":"2026-07-03T00:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01360","created_at":"2026-07-03T00:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"PL7ZTNCKKM2F","created_at":"2026-07-03T00:16:58Z"},{"alias_kind":"pith_short_16","alias_value":"PL7ZTNCKKM2FQHUP","created_at":"2026-07-03T00:16:58Z"},{"alias_kind":"pith_short_8","alias_value":"PL7ZTNCK","created_at":"2026-07-03T00:16:58Z"}],"graph_snapshots":[{"event_id":"sha256:c4235a387bf390a651ce1bea3cd69afc5fb5c402a119a62a61c038bfc83634a2","target":"graph","created_at":"2026-07-03T00:16:58Z","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/2607.01360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are typically evaluated on code generation and program repair using binary functional correctness: a generated program or patch either passes or fails a test suite. This protocol is simple but coarse, as it ignores partial progress, feedback use, regressions, and the refinement trajectory through which models often improve code. We introduce PAIR-Bench, a progressive and adaptive benchmark for evaluating code improvement: transforming an incorrect or incomplete program into a more correct one through feedback-guided refinement. PAIR-Bench uses progressive hinting, ","authors_text":"Aashish Yadavally, Cuong Chi Le, Minh Le-Anh, Tien N. Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-01T18:20:27Z","title":"Benchmarking Code Improvement with Progressive, Adaptive, and Interactive Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01360","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":"sha256:7d090421e5acdc27d86479dda42a9756bc27226d6bf1d677e1bcf239025aa6fe","target":"record","created_at":"2026-07-03T00:16:58Z","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":"a117206bf2d158dfd6b7cd0306112466b2a8750d96fc8080d0677d2ebbdf1fe9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-01T18:20:27Z","title_canon_sha256":"444c79c981bc2e014a42479a931c73cff1aa2b5c9dba04f4f5d9ee446d43a421"},"schema_version":"1.0","source":{"id":"2607.01360","kind":"arxiv","version":1}},"canonical_sha256":"7aff99b44a5334581e8ffe24c853e582e76cbbe21c2d1028fe9381357c7b38cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7aff99b44a5334581e8ffe24c853e582e76cbbe21c2d1028fe9381357c7b38cd","first_computed_at":"2026-07-03T00:16:58.298942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T00:16:58.298942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aLWyplNm/yecuMPSPOog5rEQhZhKbQKmT2dYcYcA77MNpYzfXjZ/Nn7k2U/TqHHtpXY14lyiT6mhXD1vlqUsCQ==","signature_status":"signed_v1","signed_at":"2026-07-03T00:16:58.299302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d090421e5acdc27d86479dda42a9756bc27226d6bf1d677e1bcf239025aa6fe","sha256:c4235a387bf390a651ce1bea3cd69afc5fb5c402a119a62a61c038bfc83634a2"],"state_sha256":"1d558305dd9e4e6a8e4a6fb23569c0f2c71581748edabf505f455d1bc85bcbdf"}