{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W7O4RW2ZGHNIFOXSDFMTJA26OY","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":"8eff69306e543ac7678b4c70b83726744cfefcaeefb99c4cee8e8368635da963","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T02:42:41Z","title_canon_sha256":"323fce018310459f2dd15bbbdf9aba3caa3e8b24747500be6b69d483c637018c"},"schema_version":"1.0","source":{"id":"2605.23170","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23170","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23170v1","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23170","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_12","alias_value":"W7O4RW2ZGHNI","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_16","alias_value":"W7O4RW2ZGHNIFOXS","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_8","alias_value":"W7O4RW2Z","created_at":"2026-05-25T02:01:41Z"}],"graph_snapshots":[{"event_id":"sha256:7a3f5fb47487688d38dd0f2fe17c7d416fc56c61571fff39e6da811d9b0bdee4","target":"graph","created_at":"2026-05-25T02:01:41Z","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/2605.23170/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Position-controlled evaluation is standard for retrieval tasks such as Needle-in-a-Haystack and RULER, but mainstream reasoning benchmarks do not control positional placement of target tasks in long contexts. We audit 11 long-context benchmarks and find none jointly controls task position, filler content, and context length for reasoning. An audit of four flagship long-context releases finds no main result-table entry for NIAH, RULER, or LongBench-family benchmarks, while agentic and coding benchmarks appear in main result-tables across all four. We propose Context Rot Evaluation (CRE), a cont","authors_text":"Chuyifei Zhang, Hongyu Cui, Jitao Sang, Xiaowen Huang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T02:42:41Z","title":"Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23170","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":"sha256:31d0a1e459ef8e4f445adec60e8495293e625f593633a8c3e7163de907c9e815","target":"record","created_at":"2026-05-25T02:01:41Z","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":"8eff69306e543ac7678b4c70b83726744cfefcaeefb99c4cee8e8368635da963","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T02:42:41Z","title_canon_sha256":"323fce018310459f2dd15bbbdf9aba3caa3e8b24747500be6b69d483c637018c"},"schema_version":"1.0","source":{"id":"2605.23170","kind":"arxiv","version":1}},"canonical_sha256":"b7ddc8db5931da82baf2195934835e761a2b5991326aa6f0a8fd95919965450e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7ddc8db5931da82baf2195934835e761a2b5991326aa6f0a8fd95919965450e","first_computed_at":"2026-05-25T02:01:41.373904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:41.373904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yxJ5yUNvTZQMQgNuXFW1G6twLv/udZnkfkCZHVxCHq7fr/k1VeI/p7a9ZnM2Y167VNHH5JqpNf0gXCTmy/kZCA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:41.374633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23170","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31d0a1e459ef8e4f445adec60e8495293e625f593633a8c3e7163de907c9e815","sha256:7a3f5fb47487688d38dd0f2fe17c7d416fc56c61571fff39e6da811d9b0bdee4"],"state_sha256":"d90067b47d60df119411678e47f1b010428fa6d0776ec441fec834ef591abc29"}