{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y4DHJPMO5S4XSXY7CZNNL5W2CK","short_pith_number":"pith:Y4DHJPMO","canonical_record":{"source":{"id":"2506.00264","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:55:18Z","cross_cats_sorted":[],"title_canon_sha256":"2b56fa48a8d2fc07828cefc276c6cec36a7110d4a0d344557faa5c56384e497c","abstract_canon_sha256":"4c1b532dac56103c04d20087bab2013b3d4ddb92c140045a7601170a9b89d8f8"},"schema_version":"1.0"},"canonical_sha256":"c70674bd8eecb9795f1f165ad5f6da12acf29a9addcc2882636af8d48bc0cad2","source":{"kind":"arxiv","id":"2506.00264","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00264","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00264v2","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00264","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"Y4DHJPMO5S4X","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"Y4DHJPMO5S4XSXY7","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"Y4DHJPMO","created_at":"2026-07-05T11:15:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y4DHJPMO5S4XSXY7CZNNL5W2CK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00264","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:55:18Z","cross_cats_sorted":[],"title_canon_sha256":"2b56fa48a8d2fc07828cefc276c6cec36a7110d4a0d344557faa5c56384e497c","abstract_canon_sha256":"4c1b532dac56103c04d20087bab2013b3d4ddb92c140045a7601170a9b89d8f8"},"schema_version":"1.0"},"canonical_sha256":"c70674bd8eecb9795f1f165ad5f6da12acf29a9addcc2882636af8d48bc0cad2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:47.464024Z","signature_b64":"wJ11TeFj34YbeMnlQu4TNMN0s67Is4k7k+wUxA4iPeBN3sU6RKmgpOrPXwqQdzwKo5+MQkEEtWDqOJ5DYiJTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c70674bd8eecb9795f1f165ad5f6da12acf29a9addcc2882636af8d48bc0cad2","last_reissued_at":"2026-07-05T11:15:47.463466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:47.463466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00264","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqpbAFpbFX6ZtvDOz6iEgcqTC6bInhYU1REamy4LD3sascxXD6TAb/z0iNvCBhZ8GwWh8vS80sMPpw3LqcgVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:23:21.677344Z"},"content_sha256":"72d7571bd3b0954a2e4d1b2bc3ca0add561c9ac4b9c68a7f1a2e616502076b66","schema_version":"1.0","event_id":"sha256:72d7571bd3b0954a2e4d1b2bc3ca0add561c9ac4b9c68a7f1a2e616502076b66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y4DHJPMO5S4XSXY7CZNNL5W2CK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hamidreza Saffari, Mohammadamin Shafiei, Nafise Sadat Moosavi","submitted_at":"2025-05-30T21:55:18Z","abstract_excerpt":"As Large Language Models are increasingly deployed in high-stakes domains, their ability to detect false assumptions and reason critically is crucial for ensuring reliable outputs. False-premise questions (FPQs) serve as an important evaluation method by exposing cases where flawed assumptions lead to incorrect responses. While existing benchmarks focus on single-hop FPQs, real-world reasoning often requires multi-hop inference, where models must verify consistency across multiple reasoning steps rather than relying on surface-level cues. To address this gap, we introduce MultiHoax, a benchmar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00264","kind":"arxiv","version":2},"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/2506.00264/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":"2026-07-05T11:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+5dGUhwqSw93pEHx1skjbBfl+KYbzMGV+z7n2Z5BIwDNJtaTbzmYGatZsIP5eOWafH+W+U6FN7SvYyk9ds7QAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:23:21.677717Z"},"content_sha256":"e2efecf2bd0e1d38ed81851d3529d5c4767fe15c946008ea388a4088bf35a0b0","schema_version":"1.0","event_id":"sha256:e2efecf2bd0e1d38ed81851d3529d5c4767fe15c946008ea388a4088bf35a0b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y4DHJPMO5S4XSXY7CZNNL5W2CK/bundle.json","state_url":"https://pith.science/pith/Y4DHJPMO5S4XSXY7CZNNL5W2CK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y4DHJPMO5S4XSXY7CZNNL5W2CK/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":"2026-08-18T05:23:21Z","links":{"resolver":"https://pith.science/pith/Y4DHJPMO5S4XSXY7CZNNL5W2CK","bundle":"https://pith.science/pith/Y4DHJPMO5S4XSXY7CZNNL5W2CK/bundle.json","state":"https://pith.science/pith/Y4DHJPMO5S4XSXY7CZNNL5W2CK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y4DHJPMO5S4XSXY7CZNNL5W2CK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y4DHJPMO5S4XSXY7CZNNL5W2CK","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":"4c1b532dac56103c04d20087bab2013b3d4ddb92c140045a7601170a9b89d8f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:55:18Z","title_canon_sha256":"2b56fa48a8d2fc07828cefc276c6cec36a7110d4a0d344557faa5c56384e497c"},"schema_version":"1.0","source":{"id":"2506.00264","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00264","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00264v2","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00264","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"Y4DHJPMO5S4X","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"Y4DHJPMO5S4XSXY7","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"Y4DHJPMO","created_at":"2026-07-05T11:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:e2efecf2bd0e1d38ed81851d3529d5c4767fe15c946008ea388a4088bf35a0b0","target":"graph","created_at":"2026-07-05T11:15:47Z","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/2506.00264/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models are increasingly deployed in high-stakes domains, their ability to detect false assumptions and reason critically is crucial for ensuring reliable outputs. False-premise questions (FPQs) serve as an important evaluation method by exposing cases where flawed assumptions lead to incorrect responses. While existing benchmarks focus on single-hop FPQs, real-world reasoning often requires multi-hop inference, where models must verify consistency across multiple reasoning steps rather than relying on surface-level cues. To address this gap, we introduce MultiHoax, a benchmar","authors_text":"Hamidreza Saffari, Mohammadamin Shafiei, Nafise Sadat Moosavi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:55:18Z","title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00264","kind":"arxiv","version":2},"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":"sha256:72d7571bd3b0954a2e4d1b2bc3ca0add561c9ac4b9c68a7f1a2e616502076b66","target":"record","created_at":"2026-07-05T11:15:47Z","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":"4c1b532dac56103c04d20087bab2013b3d4ddb92c140045a7601170a9b89d8f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:55:18Z","title_canon_sha256":"2b56fa48a8d2fc07828cefc276c6cec36a7110d4a0d344557faa5c56384e497c"},"schema_version":"1.0","source":{"id":"2506.00264","kind":"arxiv","version":2}},"canonical_sha256":"c70674bd8eecb9795f1f165ad5f6da12acf29a9addcc2882636af8d48bc0cad2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c70674bd8eecb9795f1f165ad5f6da12acf29a9addcc2882636af8d48bc0cad2","first_computed_at":"2026-07-05T11:15:47.463466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:47.463466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wJ11TeFj34YbeMnlQu4TNMN0s67Is4k7k+wUxA4iPeBN3sU6RKmgpOrPXwqQdzwKo5+MQkEEtWDqOJ5DYiJTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:47.464024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00264","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72d7571bd3b0954a2e4d1b2bc3ca0add561c9ac4b9c68a7f1a2e616502076b66","sha256:e2efecf2bd0e1d38ed81851d3529d5c4767fe15c946008ea388a4088bf35a0b0"],"state_sha256":"cb079fa53efcee5e91a359ec1fed8d67a315d4cda7acb7a639d7b433560c173f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xnc4tIHKPLYqmRo9+pmcOUtI8qvc9CsMTu1ReKN0N7z5XU/xuamV87cN3kmJ1B55ms8sg0V0JTNSmBnlHthBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T05:23:21.680159Z","bundle_sha256":"7b6c0cabb9fd07373c0334a79f39566cad11403e48c8f01f4ff830cf157343d6"}}