{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H4LLEKWR75ZYALUVAHRALBHZP4","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":"6d40ddf09446597be44b6a9b1231517b9cd6de37c497d27bf072c704d26865d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T14:43:51Z","title_canon_sha256":"7f2c7aaa72684e41d43d75f78ab088deaf91ee8afdae7332f047d10a4eb5c3a2"},"schema_version":"1.0","source":{"id":"2411.07037","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07037","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07037v3","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07037","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"H4LLEKWR75ZY","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"pith_short_16","alias_value":"H4LLEKWR75ZYALUV","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"pith_short_8","alias_value":"H4LLEKWR","created_at":"2026-07-05T11:42:24Z"}],"graph_snapshots":[{"event_id":"sha256:c2829b086012c536b49266a8e3d782cbcbf2601a25ccac258b4f5287fb259a73","target":"graph","created_at":"2026-07-05T11:42:24Z","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/2411.07037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) evolve in natural language processing (NLP), their ability to stably follow instructions in long-context inputs has become critical for real-world applications. However, existing benchmarks seldom focus on instruction-following in long-context scenarios or stability on different inputs. To bridge this gap, we introduce LIFBench, a scalable dataset designed to evaluate LLMs' instruction-following capabilities and stability across long contexts. LIFBench comprises three long-context scenarios and eleven diverse tasks, featuring 2,766 instructions generated through","authors_text":"He Yan, Junmin Zhu, Minhao Wang, Wei Zhang, Xiangju Lu, Xiaodong Wu, Xiaoming Shi, Yichen Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T14:43:51Z","title":"LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07037","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:e9c157db305cad1b191547b5d368adbb8196d54a3e4e6a894ec783fd0f52868a","target":"record","created_at":"2026-07-05T11:42:24Z","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":"6d40ddf09446597be44b6a9b1231517b9cd6de37c497d27bf072c704d26865d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T14:43:51Z","title_canon_sha256":"7f2c7aaa72684e41d43d75f78ab088deaf91ee8afdae7332f047d10a4eb5c3a2"},"schema_version":"1.0","source":{"id":"2411.07037","kind":"arxiv","version":3}},"canonical_sha256":"3f16b22ad1ff73802e9501e20584f97f2497521ede9984600554dca4b08c0a5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f16b22ad1ff73802e9501e20584f97f2497521ede9984600554dca4b08c0a5c","first_computed_at":"2026-07-05T11:42:24.074846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:24.074846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PgKZ3EZTVIPA3InGiH88P2V3e7ZvgE8ntuj7ksKWzmKE8Tq61O+arBRPTPoYJtyuQ4fkF6TzJiR5oCvl1eInDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:24.075351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07037","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9c157db305cad1b191547b5d368adbb8196d54a3e4e6a894ec783fd0f52868a","sha256:c2829b086012c536b49266a8e3d782cbcbf2601a25ccac258b4f5287fb259a73"],"state_sha256":"2d8298dd17eee53c89278ab2510a191a83ec84762bde621ad26eed5424641a4e"}