{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IVLXORGSX75YQ7ZVM3LH6QGYMY","short_pith_number":"pith:IVLXORGS","canonical_record":{"source":{"id":"2412.00166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T14:42:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e2882ed96a46da44d4df8fa3ab0fe1bdd610bb726540de69f0e7732603a0d7f","abstract_canon_sha256":"eca5d2ff6d30444f9b55baf4f9c6214d510c82f1e5b0e59d42cb962db3bd12e3"},"schema_version":"1.0"},"canonical_sha256":"45577744d2bffb887f3566d67f40d866264ff4e6e0511bc809c7b55957362986","source":{"kind":"arxiv","id":"2412.00166","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00166","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00166v1","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00166","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_12","alias_value":"IVLXORGSX75Y","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_16","alias_value":"IVLXORGSX75YQ7ZV","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_8","alias_value":"IVLXORGS","created_at":"2026-07-05T10:22:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IVLXORGSX75YQ7ZVM3LH6QGYMY","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T14:42:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e2882ed96a46da44d4df8fa3ab0fe1bdd610bb726540de69f0e7732603a0d7f","abstract_canon_sha256":"eca5d2ff6d30444f9b55baf4f9c6214d510c82f1e5b0e59d42cb962db3bd12e3"},"schema_version":"1.0"},"canonical_sha256":"45577744d2bffb887f3566d67f40d866264ff4e6e0511bc809c7b55957362986","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:10.722479Z","signature_b64":"m6bKTG3oftpOArrBMKaJWewxAeBuv1JxlUPYWGwDesFM7CZzbpPD8J0XSgIMM7k/yyVVqVrS9qSeeJ13ECPCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45577744d2bffb887f3566d67f40d866264ff4e6e0511bc809c7b55957362986","last_reissued_at":"2026-07-05T10:22:10.721927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:10.721927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00166","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":"2026-07-05T10:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4SY2Odse8jq8zxlBCcOlt9SO06DF46RCBQmZoD0fqkEEmeVnRYLHuC4uGIGOMEOwEDyiEYjqqw6gFtr3PD2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:17:37.381471Z"},"content_sha256":"33453302e300bfb52f7ea718e74d777218d9c3606f5931327895ce0c71cc2fb0","schema_version":"1.0","event_id":"sha256:33453302e300bfb52f7ea718e74d777218d9c3606f5931327895ce0c71cc2fb0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IVLXORGSX75YQ7ZVM3LH6QGYMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To Ensemble or Not: Assessing Majority Voting Strategies for Phishing Detection with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Chehab, Fouad Trad","submitted_at":"2024-11-29T14:42:23Z","abstract_excerpt":"The effectiveness of Large Language Models (LLMs) significantly relies on the quality of the prompts they receive. However, even when processing identical prompts, LLMs can yield varying outcomes due to differences in their training processes. To leverage the collective intelligence of multiple LLMs and enhance their performance, this study investigates three majority voting strategies for text classification, focusing on phishing URL detection. The strategies are: (1) a prompt-based ensemble, which utilizes majority voting across the responses generated by a single LLM to various prompts; (2)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00166","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/2412.00166/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":"2026-07-05T10:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cmEnkgQEP+K4giIUKW22fMUT8b/y7OyFw//cl9NUxq3lv0rkksxvAyhcOFeFHPgs0q8GyxvYZx8oQ0/jyNw4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:17:37.391928Z"},"content_sha256":"ca88b220cc461242c66c04edc5ddebc13c1a256c3533ca6ea4d259c0775a83da","schema_version":"1.0","event_id":"sha256:ca88b220cc461242c66c04edc5ddebc13c1a256c3533ca6ea4d259c0775a83da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVLXORGSX75YQ7ZVM3LH6QGYMY/bundle.json","state_url":"https://pith.science/pith/IVLXORGSX75YQ7ZVM3LH6QGYMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVLXORGSX75YQ7ZVM3LH6QGYMY/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":"2026-08-15T19:17:37Z","links":{"resolver":"https://pith.science/pith/IVLXORGSX75YQ7ZVM3LH6QGYMY","bundle":"https://pith.science/pith/IVLXORGSX75YQ7ZVM3LH6QGYMY/bundle.json","state":"https://pith.science/pith/IVLXORGSX75YQ7ZVM3LH6QGYMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVLXORGSX75YQ7ZVM3LH6QGYMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IVLXORGSX75YQ7ZVM3LH6QGYMY","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":"eca5d2ff6d30444f9b55baf4f9c6214d510c82f1e5b0e59d42cb962db3bd12e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T14:42:23Z","title_canon_sha256":"1e2882ed96a46da44d4df8fa3ab0fe1bdd610bb726540de69f0e7732603a0d7f"},"schema_version":"1.0","source":{"id":"2412.00166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00166","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00166v1","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00166","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_12","alias_value":"IVLXORGSX75Y","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_16","alias_value":"IVLXORGSX75YQ7ZV","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_8","alias_value":"IVLXORGS","created_at":"2026-07-05T10:22:10Z"}],"graph_snapshots":[{"event_id":"sha256:ca88b220cc461242c66c04edc5ddebc13c1a256c3533ca6ea4d259c0775a83da","target":"graph","created_at":"2026-07-05T10:22:10Z","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/2412.00166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The effectiveness of Large Language Models (LLMs) significantly relies on the quality of the prompts they receive. However, even when processing identical prompts, LLMs can yield varying outcomes due to differences in their training processes. To leverage the collective intelligence of multiple LLMs and enhance their performance, this study investigates three majority voting strategies for text classification, focusing on phishing URL detection. The strategies are: (1) a prompt-based ensemble, which utilizes majority voting across the responses generated by a single LLM to various prompts; (2)","authors_text":"Ali Chehab, Fouad Trad","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T14:42:23Z","title":"To Ensemble or Not: Assessing Majority Voting Strategies for Phishing Detection with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00166","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":"sha256:33453302e300bfb52f7ea718e74d777218d9c3606f5931327895ce0c71cc2fb0","target":"record","created_at":"2026-07-05T10:22:10Z","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":"eca5d2ff6d30444f9b55baf4f9c6214d510c82f1e5b0e59d42cb962db3bd12e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T14:42:23Z","title_canon_sha256":"1e2882ed96a46da44d4df8fa3ab0fe1bdd610bb726540de69f0e7732603a0d7f"},"schema_version":"1.0","source":{"id":"2412.00166","kind":"arxiv","version":1}},"canonical_sha256":"45577744d2bffb887f3566d67f40d866264ff4e6e0511bc809c7b55957362986","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45577744d2bffb887f3566d67f40d866264ff4e6e0511bc809c7b55957362986","first_computed_at":"2026-07-05T10:22:10.721927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:10.721927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m6bKTG3oftpOArrBMKaJWewxAeBuv1JxlUPYWGwDesFM7CZzbpPD8J0XSgIMM7k/yyVVqVrS9qSeeJ13ECPCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:10.722479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33453302e300bfb52f7ea718e74d777218d9c3606f5931327895ce0c71cc2fb0","sha256:ca88b220cc461242c66c04edc5ddebc13c1a256c3533ca6ea4d259c0775a83da"],"state_sha256":"3a3949dbf1b4eb6c2ed36de50e24f3ee3706831d8d05fa9ecc766cdb3d621e30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lHvlcN0FBBh8GX++Rwg5pUs6r0ubzJKQi1Hxghptxv4elibXGbXDol9q0yD8KeavYrvooMIEnUai7le/MqSoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:17:37.399191Z","bundle_sha256":"750d879868647c84f9f3502e7b895db53c1d2ae407fdd66b78b874364786f8a9"}}