{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QSJIIV5BWMQUK7L26S6QUBEOJM","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":"5639c76a9163935f3d9378596c3b0dd18670f38a6315d80191bd324451c08dab","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T22:51:41Z","title_canon_sha256":"634af8ed72d289d544d6031a23e9511e5c95687f599f90afcf427fc1200a871d"},"schema_version":"1.0","source":{"id":"2607.09665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09665","created_at":"2026-07-14T00:18:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09665v1","created_at":"2026-07-14T00:18:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09665","created_at":"2026-07-14T00:18:29Z"},{"alias_kind":"pith_short_12","alias_value":"QSJIIV5BWMQU","created_at":"2026-07-14T00:18:29Z"},{"alias_kind":"pith_short_16","alias_value":"QSJIIV5BWMQUK7L2","created_at":"2026-07-14T00:18:29Z"},{"alias_kind":"pith_short_8","alias_value":"QSJIIV5B","created_at":"2026-07-14T00:18:29Z"}],"graph_snapshots":[{"event_id":"sha256:e3f20cb8a56f08d857f623e1dcfb9663689e39cdeff350fff1a918e48cdc98ee","target":"graph","created_at":"2026-07-14T00:18:29Z","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/2607.09665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt wrappers often differ only in formatting, yet they can change model scores enough to flip leaderboard conclusions. We study this variance under a token-controlled protocol and introduce two complementary metrics: the Format Sensitivity Index (FSI), the accuracy range induced by wrapper choice, and the Parseability Sensitivity Index (PSI), the corresponding range in answer parseability. Across 140,000 OpenRouter generations spanning 7 QA tasks, 5 wrapper families, and 4 instruct models from 7B to 72B parameters, we find that mean FSI varies by over 30x across models and is largely explai","authors_text":"Deep Pankajbhai Mehta","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T22:51:41Z","title":"Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09665","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":"sha256:34f9621a640cf3b03dfd6a3d2c199ca25d039cf95102fccfd0329feb5c998f64","target":"record","created_at":"2026-07-14T00:18:29Z","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":"5639c76a9163935f3d9378596c3b0dd18670f38a6315d80191bd324451c08dab","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T22:51:41Z","title_canon_sha256":"634af8ed72d289d544d6031a23e9511e5c95687f599f90afcf427fc1200a871d"},"schema_version":"1.0","source":{"id":"2607.09665","kind":"arxiv","version":1}},"canonical_sha256":"84928457a1b321457d7af4bd0a048e4b04d2fdd039f932b21ec4aec5b013ba0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84928457a1b321457d7af4bd0a048e4b04d2fdd039f932b21ec4aec5b013ba0b","first_computed_at":"2026-07-14T00:18:29.500756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:29.500756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k26it/cAXwKpmXjaLeXtVphOFt0rXCd78G0+oPRju/H37npfs/6Ok0F9BV1rNJytr3N36XasDRtcOC66uYRlBg==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:29.501547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34f9621a640cf3b03dfd6a3d2c199ca25d039cf95102fccfd0329feb5c998f64","sha256:e3f20cb8a56f08d857f623e1dcfb9663689e39cdeff350fff1a918e48cdc98ee"],"state_sha256":"01f62797be894a501c49f7aafd77d8da6be702d73f5917e33ee61a41bc255f3e"}