{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CZPVNULIFB5DYQYU2APQBB4EIY","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":"61b61f7e85210903e80be60aea45bc5e1bd5de05b2385c53959291f91fe15c2f","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-08T17:59:19Z","title_canon_sha256":"e86ef6a82061807db60246f7e94f208a25f38cbb7ab27ef3aef35bd7b74cdedb"},"schema_version":"1.0","source":{"id":"2510.07315","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.07315","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2510.07315v2","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.07315","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"CZPVNULIFB5D","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"CZPVNULIFB5DYQYU","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"CZPVNULI","created_at":"2026-06-08T01:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:a2ab291bcd649946c99e58096f49cd470f8abb2719711c05ee42aba539e9171a","target":"graph","created_at":"2026-06-08T01:03:49Z","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/2510.07315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their vibe check. Vibe check reflects human preference and goes beyond functionality: the solution should feel right, read cleanly, preserve intent, and remain correct. However, current code evaluation remains anchored to pass@k and captures only functional correctness, overlooking non-functional instructions that users routinely apply. In this paper, we hypothesize that instruction following is the missing piece underl","authors_text":"Benoit Schillings, Dan Garrette, Jeremiah Liu, Jiao Sun, Jiawei Han, Ming Zhong, Nan Xu, Qingze Wang, Shyam Upadhyay, Ting-Yun Chang, Xiance Si, Xiang Zhou","cross_cats":["cs.AI","cs.LG","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-08T17:59:19Z","title":"SWE-IF: Aligning Code Evaluation with Human Preference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.07315","kind":"arxiv","version":2},"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:d9fb6dd276fe25a3fc006c0e71f1270be403c52f32913ab0ab9d59919765cbc8","target":"record","created_at":"2026-06-08T01:03:49Z","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":"61b61f7e85210903e80be60aea45bc5e1bd5de05b2385c53959291f91fe15c2f","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-08T17:59:19Z","title_canon_sha256":"e86ef6a82061807db60246f7e94f208a25f38cbb7ab27ef3aef35bd7b74cdedb"},"schema_version":"1.0","source":{"id":"2510.07315","kind":"arxiv","version":2}},"canonical_sha256":"165f56d168287a3c4314d01f00878446149f847eaf40fd9cf2a3f61b68f50240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"165f56d168287a3c4314d01f00878446149f847eaf40fd9cf2a3f61b68f50240","first_computed_at":"2026-06-08T01:03:49.478507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:49.478507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GYJm4UsarQEfDwtR8dcLXaFfmaFTZH3CtEFEjxrKEsOmnLrE0TYfLCm1Rno8m/E91HNfsZFAwyf/94Jq+MxABw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:49.479349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.07315","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9fb6dd276fe25a3fc006c0e71f1270be403c52f32913ab0ab9d59919765cbc8","sha256:a2ab291bcd649946c99e58096f49cd470f8abb2719711c05ee42aba539e9171a"],"state_sha256":"bbcabef2a3d1bfdd34d6604ee1d2ca154ef62b3567d219d6527c6acc2f5914d1"}