{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RXRGM7AQY4XBAXEMLTJWH4YL7N","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":"9be34a2529413970716ce321ee50b55a8341d85bd97f9c88b3eab41c03c3d8ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:44:33Z","title_canon_sha256":"860dbe3b7fa3cd22521baa295ddce749c7d16f121ab4f6371566ac88638a9818"},"schema_version":"1.0","source":{"id":"2507.02833","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02833","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02833v3","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02833","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"RXRGM7AQY4XB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RXRGM7AQY4XBAXEM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RXRGM7AQ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:12a69cac06a4ccc563e6436519428351d024efd0a8a3789fc16f7444c4032bfa","target":"graph","created_at":"2026-05-17T23:38:49Z","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"},"paper":{"abstract_excerpt":"A crucial factor for successful human and AI interaction is the ability of language models or chatbots to follow human instructions precisely. A common feature of instructions are output constraints like ``only answer with yes or no\" or ``mention the word `abrakadabra' at least 3 times\" that the user adds to craft a more useful answer. Even today's strongest models struggle with fulfilling such constraints. We find that most models strongly overfit on a small set of verifiable constraints from the benchmarks that test these abilities, a skill called precise instruction following, and are not a","authors_text":"Hamish Ivison, Hannaneh Hajishirzi, Nathan Lambert, Pradeep Dasigi, Saumya Malik, Shengyi Huang, Valentina Pyatkin, Victoria Graf","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:44:33Z","title":"Generalizing Verifiable Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02833","kind":"arxiv","version":3},"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:bcccdd23995c749706e2f3caceff984b4013cd0c1e7a144769c0e488e8e10060","target":"record","created_at":"2026-05-17T23:38:49Z","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":"9be34a2529413970716ce321ee50b55a8341d85bd97f9c88b3eab41c03c3d8ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:44:33Z","title_canon_sha256":"860dbe3b7fa3cd22521baa295ddce749c7d16f121ab4f6371566ac88638a9818"},"schema_version":"1.0","source":{"id":"2507.02833","kind":"arxiv","version":3}},"canonical_sha256":"8de2667c10c72e105c8c5cd363f30bfb7bf9f17d7b87b15d538cb6b46b096fdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8de2667c10c72e105c8c5cd363f30bfb7bf9f17d7b87b15d538cb6b46b096fdc","first_computed_at":"2026-05-17T23:38:49.193712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.193712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Dr9xDbGCWmU67Vy9WqR7PbIErH1a7JVNCfj2Xm+ChHYsvBzGW1eUzeDk60pI+T2cpihrJ6vcF83YENkYrX1CQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.194365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02833","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcccdd23995c749706e2f3caceff984b4013cd0c1e7a144769c0e488e8e10060","sha256:12a69cac06a4ccc563e6436519428351d024efd0a8a3789fc16f7444c4032bfa"],"state_sha256":"e0633f47c7f8e0ea2afc677d0114853b79f5a7c88987c646ad8891542316afb6"}