{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5OFBTEW4KVZRGUS4KUDO6K7NZB","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":"9485c2a10f774a0ad250e8cea2c259d9a91201a886ba36707894a00a1ad0fe81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T16:48:57Z","title_canon_sha256":"c3e36f1fe014ed9ac16aae854c64edd5044ed09a890341b154431e964f73fc3f"},"schema_version":"1.0","source":{"id":"2505.14597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14597","created_at":"2026-07-05T11:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14597v1","created_at":"2026-07-05T11:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14597","created_at":"2026-07-05T11:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"5OFBTEW4KVZR","created_at":"2026-07-05T11:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"5OFBTEW4KVZRGUS4","created_at":"2026-07-05T11:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"5OFBTEW4","created_at":"2026-07-05T11:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:ffeca3725b43ffd08d76b9a438574da886bb617e0c8444fb1b46914ec2aae477","target":"graph","created_at":"2026-07-05T11:06:16Z","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/2505.14597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code Sensitivity refers to the ability of Code LLMs to recognize and respond to details changes in problem descriptions. While current code benchmarks and instruction data focus on difficulty and diversity, sensitivity is overlooked. We first introduce the CTF-Code benchmark, constructed using counterfactual perturbations, minimizing input changes while maximizing output changes. The evaluation shows that many LLMs have a more than 10\\% performance drop compared to the original problems. To fully utilize sensitivity, CTF-Instruct, an incremental instruction fine-tuning framework, extends on ex","authors_text":"Mingzheng Xu, Qingfu Zhu, Shijie Xuyang, Tianhao Cheng, Wanxiang Che, Xianzhen Luo, Yixuan Wang, Yuantao Fan, Zheng Chu, Zhiming Zhang, Zhiyuan Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T16:48:57Z","title":"Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14597","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":"sha256:5d6e6f2ed6e4d75cb126334ca917223bb2a163dca5485498b99b103f3ac7a347","target":"record","created_at":"2026-07-05T11:06:16Z","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":"9485c2a10f774a0ad250e8cea2c259d9a91201a886ba36707894a00a1ad0fe81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T16:48:57Z","title_canon_sha256":"c3e36f1fe014ed9ac16aae854c64edd5044ed09a890341b154431e964f73fc3f"},"schema_version":"1.0","source":{"id":"2505.14597","kind":"arxiv","version":1}},"canonical_sha256":"eb8a1992dc557313525c5506ef2bedc8526bf70d9fe91ab0cf09bf6e1f431a1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb8a1992dc557313525c5506ef2bedc8526bf70d9fe91ab0cf09bf6e1f431a1d","first_computed_at":"2026-07-05T11:06:16.257380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:16.257380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bLVZ/EHPgfUmXIynAhT+IqDfcht7yy6Q871z3b5G1CTGxjcbgocrQoXJ2yz5EcQn8Hvhb+Q9j7O2+VGKhiDRDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:16.257897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d6e6f2ed6e4d75cb126334ca917223bb2a163dca5485498b99b103f3ac7a347","sha256:ffeca3725b43ffd08d76b9a438574da886bb617e0c8444fb1b46914ec2aae477"],"state_sha256":"f2cbaaf877aa9b6f6740f7ffd27562f8ecf9493805fff99342ec5516a212fd7e"}