{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2LU6EFPNRVWVSXMR5GWTMOQCGH","short_pith_number":"pith:2LU6EFPN","canonical_record":{"source":{"id":"2608.06202","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-08-06T15:58:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ffbeb5e9de248be8141d525810ea49fd216462d22ab0a6aebbb2daca75b35f39","abstract_canon_sha256":"54338edfdf36190cf46e027d59758f04b2664ec242eb5956fff49e46340b4b7b"},"schema_version":"1.0"},"canonical_sha256":"d2e9e215ed8d6d595d91e9ad363a0231e44c957630ceec726447178b27091207","source":{"kind":"arxiv","id":"2608.06202","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06202","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06202v1","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06202","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"2LU6EFPNRVWV","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"2LU6EFPNRVWVSXMR","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"2LU6EFPN","created_at":"2026-08-07T01:40:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2LU6EFPNRVWVSXMR5GWTMOQCGH","target":"record","payload":{"canonical_record":{"source":{"id":"2608.06202","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-08-06T15:58:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ffbeb5e9de248be8141d525810ea49fd216462d22ab0a6aebbb2daca75b35f39","abstract_canon_sha256":"54338edfdf36190cf46e027d59758f04b2664ec242eb5956fff49e46340b4b7b"},"schema_version":"1.0"},"canonical_sha256":"d2e9e215ed8d6d595d91e9ad363a0231e44c957630ceec726447178b27091207","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:40:55.932798Z","signature_b64":"zJxpVzzNUYMU2xu8PKZ/ytW6j3JAgRl7pu5dAya3TqPiBwM0osGXWM/4PHHu5T+Td8mqDRxfETomYXBZaYQ+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2e9e215ed8d6d595d91e9ad363a0231e44c957630ceec726447178b27091207","last_reissued_at":"2026-08-07T01:40:55.930900Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:40:55.930900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.06202","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-07T01:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3oso2xcShPMIefE2IhCgKlndO2INXdaGRwIn/4OhfRuAzmbE1YMPljrfCFq1hQHWmvxbfnmEOYF1ClPCUfB2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:45:21.158109Z"},"content_sha256":"74c431072e18d7c3800b7ffe387d89e3293c6cf0d4e86b463f7bcd966e6ccc87","schema_version":"1.0","event_id":"sha256:74c431072e18d7c3800b7ffe387d89e3293c6cf0d4e86b463f7bcd966e6ccc87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2LU6EFPNRVWVSXMR5GWTMOQCGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Dana\\'e Metaxa, Emma Lurie, Ro Encarnaci\\'on, Tina Behzad","submitted_at":"2026-08-06T15:58:32Z","abstract_excerpt":"Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet most evaluations rely on a single access modality (model APIs), perform a single run per prompt, and report accuracy as the primary outcome metric, without accounting for conditions such as web search that may have effects on model behavior in deployment. We audit these assumptions for one of the most widely-used LLMs, comparing two modalities, ChatGPT's chat UI and OpenAI's API, with and without web search enabled. We use a stratified total sampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06202","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.06202/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-07T01:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TF+t8Ibq/6m3p6vZB/Ca1aib9s5vxhOKP6uRT7d/8v1RE2xqA0nACYJnywErW689AI/P4NJixSggIdafo9G1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:45:21.158726Z"},"content_sha256":"09730ac25ebb42202983f84125e25513f38e94295e0d8430f32239a021e2140b","schema_version":"1.0","event_id":"sha256:09730ac25ebb42202983f84125e25513f38e94295e0d8430f32239a021e2140b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2LU6EFPNRVWVSXMR5GWTMOQCGH/bundle.json","state_url":"https://pith.science/pith/2LU6EFPNRVWVSXMR5GWTMOQCGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2LU6EFPNRVWVSXMR5GWTMOQCGH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T13:45:21Z","links":{"resolver":"https://pith.science/pith/2LU6EFPNRVWVSXMR5GWTMOQCGH","bundle":"https://pith.science/pith/2LU6EFPNRVWVSXMR5GWTMOQCGH/bundle.json","state":"https://pith.science/pith/2LU6EFPNRVWVSXMR5GWTMOQCGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2LU6EFPNRVWVSXMR5GWTMOQCGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2LU6EFPNRVWVSXMR5GWTMOQCGH","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":"54338edfdf36190cf46e027d59758f04b2664ec242eb5956fff49e46340b4b7b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-08-06T15:58:32Z","title_canon_sha256":"ffbeb5e9de248be8141d525810ea49fd216462d22ab0a6aebbb2daca75b35f39"},"schema_version":"1.0","source":{"id":"2608.06202","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06202","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06202v1","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06202","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"2LU6EFPNRVWV","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"2LU6EFPNRVWVSXMR","created_at":"2026-08-07T01:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"2LU6EFPN","created_at":"2026-08-07T01:40:55Z"}],"graph_snapshots":[{"event_id":"sha256:09730ac25ebb42202983f84125e25513f38e94295e0d8430f32239a021e2140b","target":"graph","created_at":"2026-08-07T01:40:55Z","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/2608.06202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet most evaluations rely on a single access modality (model APIs), perform a single run per prompt, and report accuracy as the primary outcome metric, without accounting for conditions such as web search that may have effects on model behavior in deployment. We audit these assumptions for one of the most widely-used LLMs, comparing two modalities, ChatGPT's chat UI and OpenAI's API, with and without web search enabled. We use a stratified total sampl","authors_text":"Dana\\'e Metaxa, Emma Lurie, Ro Encarnaci\\'on, Tina Behzad","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-08-06T15:58:32Z","title":"What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06202","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":"sha256:74c431072e18d7c3800b7ffe387d89e3293c6cf0d4e86b463f7bcd966e6ccc87","target":"record","created_at":"2026-08-07T01:40:55Z","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":"54338edfdf36190cf46e027d59758f04b2664ec242eb5956fff49e46340b4b7b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-08-06T15:58:32Z","title_canon_sha256":"ffbeb5e9de248be8141d525810ea49fd216462d22ab0a6aebbb2daca75b35f39"},"schema_version":"1.0","source":{"id":"2608.06202","kind":"arxiv","version":1}},"canonical_sha256":"d2e9e215ed8d6d595d91e9ad363a0231e44c957630ceec726447178b27091207","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2e9e215ed8d6d595d91e9ad363a0231e44c957630ceec726447178b27091207","first_computed_at":"2026-08-07T01:40:55.930900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T01:40:55.930900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zJxpVzzNUYMU2xu8PKZ/ytW6j3JAgRl7pu5dAya3TqPiBwM0osGXWM/4PHHu5T+Td8mqDRxfETomYXBZaYQ+Cw==","signature_status":"signed_v1","signed_at":"2026-08-07T01:40:55.932798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06202","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74c431072e18d7c3800b7ffe387d89e3293c6cf0d4e86b463f7bcd966e6ccc87","sha256:09730ac25ebb42202983f84125e25513f38e94295e0d8430f32239a021e2140b"],"state_sha256":"87b3acb49fe4c9bb85b14047bc2f7c4e86a883a482f58cff1074fde18b005739"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1dDRVYTLciBGaqCPTBZijc3ufWiXg1URHyj1lHEGHtiNMNaFcNDbduDiW4YWJLZq8jv5cpfaJfeDne+j6mDDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T13:45:21.165334Z","bundle_sha256":"397e288e9d947193faf9cfb7b35e74c4991f88347209850af1b6e0cb81bdc4f5"}}