{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HTKZFNP2PYKGBMGWLQQ56PTY5F","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":"57e04b3e12e873ccc375089ae94b96b204591f34631934c60c7f336cf1e64eb2","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T17:53:26Z","title_canon_sha256":"1af5c0c54df21f6de485a2b0f1df4373e4aed334b717e303736ce901f4515e63"},"schema_version":"1.0","source":{"id":"2606.26079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26079","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26079v1","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26079","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"HTKZFNP2PYKG","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"HTKZFNP2PYKGBMGW","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"HTKZFNP2","created_at":"2026-06-25T01:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:d737f9b862d3784bb5f72711884f4fc1b20740c8ca8fd5bb26dff729f71fd95a","target":"graph","created_at":"2026-06-25T01:18:47Z","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/2606.26079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard benchmarks for multimodal large language models (MLLMs) score each item on one canonical ordering and miss whether order-irrelevant shuffling changes the answer, a baseline reliability property called for by emerging AI evaluation guidelines. We introduce Facet-Probe, a five-facet audit (option, evidence-chunk, document-rank, image-set, and mixed-modality ordering) of 18 frontier and open-weight MLLMs. A Bayesian item-response model separates ordering noise from per-facet bias, and a same-ordering control estimates the decoder-stochastic floor for observed flips. We find that none of ","authors_text":"Akshay Paruchuri, Ehsan Adeli, Sanmi Koyejo","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T17:53:26Z","title":"Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26079","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:dac71407f63ad0964807cbb1433064ccf9bbe1bd131864a2c2a0e11d24980cc6","target":"record","created_at":"2026-06-25T01:18:47Z","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":"57e04b3e12e873ccc375089ae94b96b204591f34631934c60c7f336cf1e64eb2","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T17:53:26Z","title_canon_sha256":"1af5c0c54df21f6de485a2b0f1df4373e4aed334b717e303736ce901f4515e63"},"schema_version":"1.0","source":{"id":"2606.26079","kind":"arxiv","version":1}},"canonical_sha256":"3cd592b5fa7e1460b0d65c21df3e78e97ef4061e92d5250c6c513ff5a157a21d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cd592b5fa7e1460b0d65c21df3e78e97ef4061e92d5250c6c513ff5a157a21d","first_computed_at":"2026-06-25T01:18:47.982748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:47.982748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PSN0cCELupZC6LayRbjnEZAQr+Jj7jXQb3SIfT5BVOcdLvIjaTjB56RSWndZJNZhpeSBSK4Hk9mXFpAbpYh7AQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:47.983138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dac71407f63ad0964807cbb1433064ccf9bbe1bd131864a2c2a0e11d24980cc6","sha256:d737f9b862d3784bb5f72711884f4fc1b20740c8ca8fd5bb26dff729f71fd95a"],"state_sha256":"66b917b828c25f5b335ae63def1de377c43f89d26584c1f4cdbb80121c179bae"}