{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CR7ZYOF2ERK5XMQ37UV27JNGXG","short_pith_number":"pith:CR7ZYOF2","schema_version":"1.0","canonical_sha256":"147f9c38ba2455dbb21bfd2bafa5a6b99a37f0604d1eadd3986447384597f127","source":{"kind":"arxiv","id":"2504.14429","version":1},"attestation_state":"computed","paper":{"title":"ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmad Khalil, Alioune Ngom, Mahmoud Khalil","submitted_at":"2025-04-20T00:10:44Z","abstract_excerpt":"Large Language Models (LLMs) have transformed natural language processing (NLP) tasks, but they suffer from hallucination, generating plausible yet factually incorrect content. This issue extends to Video-Language Models (VideoLLMs), where textual descriptions may inaccurately represent visual content, resulting in multi-modal hallucinations. In this paper, we address hallucination in ResNetVLLM, a video-language model combining ResNet visual encoders with LLMs. We introduce a two-step protocol: (1) a faithfulness detection strategy that uses a modified Lynx model to assess semantic alignment "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.14429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T00:10:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3da5e908515e2c68a7ee2b1d4456ccb3d8387fed1892166d0ce8a3a5e233394c","abstract_canon_sha256":"cdaddddcd855369a50c0d8b10b949f51d8a808cd085f468b7046022f40592f31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:43.219744Z","signature_b64":"1U2tDGHqs3ljwLvQGEF0YyiqFadPTksfUDhuSWn3VHJ4KvoJCnDZ4i3nv93VMx0xJP+HrF7P1zZFZZSTVy+NBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"147f9c38ba2455dbb21bfd2bafa5a6b99a37f0604d1eadd3986447384597f127","last_reissued_at":"2026-07-05T10:51:43.219222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:43.219222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmad Khalil, Alioune Ngom, Mahmoud Khalil","submitted_at":"2025-04-20T00:10:44Z","abstract_excerpt":"Large Language Models (LLMs) have transformed natural language processing (NLP) tasks, but they suffer from hallucination, generating plausible yet factually incorrect content. This issue extends to Video-Language Models (VideoLLMs), where textual descriptions may inaccurately represent visual content, resulting in multi-modal hallucinations. In this paper, we address hallucination in ResNetVLLM, a video-language model combining ResNet visual encoders with LLMs. We introduce a two-step protocol: (1) a faithfulness detection strategy that uses a modified Lynx model to assess semantic alignment "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14429","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/2504.14429/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.14429","created_at":"2026-07-05T10:51:43.219287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14429v1","created_at":"2026-07-05T10:51:43.219287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14429","created_at":"2026-07-05T10:51:43.219287+00:00"},{"alias_kind":"pith_short_12","alias_value":"CR7ZYOF2ERK5","created_at":"2026-07-05T10:51:43.219287+00:00"},{"alias_kind":"pith_short_16","alias_value":"CR7ZYOF2ERK5XMQ3","created_at":"2026-07-05T10:51:43.219287+00:00"},{"alias_kind":"pith_short_8","alias_value":"CR7ZYOF2","created_at":"2026-07-05T10:51:43.219287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05741","citing_title":"Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG","json":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG.json","graph_json":"https://pith.science/api/pith-number/CR7ZYOF2ERK5XMQ37UV27JNGXG/graph.json","events_json":"https://pith.science/api/pith-number/CR7ZYOF2ERK5XMQ37UV27JNGXG/events.json","paper":"https://pith.science/paper/CR7ZYOF2"},"agent_actions":{"view_html":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG","download_json":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG.json","view_paper":"https://pith.science/paper/CR7ZYOF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14429&json=true","fetch_graph":"https://pith.science/api/pith-number/CR7ZYOF2ERK5XMQ37UV27JNGXG/graph.json","fetch_events":"https://pith.science/api/pith-number/CR7ZYOF2ERK5XMQ37UV27JNGXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG/action/storage_attestation","attest_author":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG/action/author_attestation","sign_citation":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG/action/citation_signature","submit_replication":"https://pith.science/pith/CR7ZYOF2ERK5XMQ37UV27JNGXG/action/replication_record"}},"created_at":"2026-07-05T10:51:43.219287+00:00","updated_at":"2026-07-05T10:51:43.219287+00:00"}