{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BFTB57P7R22EBECXZPWVWAISDE","short_pith_number":"pith:BFTB57P7","schema_version":"1.0","canonical_sha256":"09661efdff8eb4409057cbed5b0112192b621523d72a830e9660342a8d42e959","source":{"kind":"arxiv","id":"2507.04410","version":1},"attestation_state":"computed","paper":{"title":"Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CV","authors_text":"Hung Cao, Huy Hoan Le, Thi Le Chi Dang, Truong Thanh Hung Nguyen, Van Sy Thinh Nguyen, Vo Thanh Khang Nguyen","submitted_at":"2025-07-06T14:54:07Z","abstract_excerpt":"This paper presents our submission to the ACMMM25 - Grand Challenge on Multimedia Verification. We developed a multi-agent verification system that combines Multimodal Large Language Models (MLLMs) with specialized verification tools to detect multimedia misinformation. Our system operates through six stages: raw data processing, planning, information extraction, deep research, evidence collection, and report generation. The core Deep Researcher Agent employs four tools: reverse image search, metadata analysis, fact-checking databases, and verified news processing that extracts spatial, tempor"},"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":"2507.04410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T14:54:07Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"85b06981d30796d94cb34b50ea1c3529ef3696cd91bb04655c16c751b573eea6","abstract_canon_sha256":"73a39c59f178a34c4e4c5a01f590b5c7d067f4eef7626361e2ce324aeae6ff40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:47.398883Z","signature_b64":"6ABpI6ZyJSnLqohIGcBqd7Ch5LEqsY86oZAePzUQCgzYJpTRIMslyCdh6LKMz+PberCk3wkAoLvk/DlUYuUAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09661efdff8eb4409057cbed5b0112192b621523d72a830e9660342a8d42e959","last_reissued_at":"2026-07-05T11:32:47.398348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:47.398348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CV","authors_text":"Hung Cao, Huy Hoan Le, Thi Le Chi Dang, Truong Thanh Hung Nguyen, Van Sy Thinh Nguyen, Vo Thanh Khang Nguyen","submitted_at":"2025-07-06T14:54:07Z","abstract_excerpt":"This paper presents our submission to the ACMMM25 - Grand Challenge on Multimedia Verification. We developed a multi-agent verification system that combines Multimodal Large Language Models (MLLMs) with specialized verification tools to detect multimedia misinformation. Our system operates through six stages: raw data processing, planning, information extraction, deep research, evidence collection, and report generation. The core Deep Researcher Agent employs four tools: reverse image search, metadata analysis, fact-checking databases, and verified news processing that extracts spatial, tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04410","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/2507.04410/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":"2507.04410","created_at":"2026-07-05T11:32:47.398420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04410v1","created_at":"2026-07-05T11:32:47.398420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04410","created_at":"2026-07-05T11:32:47.398420+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFTB57P7R22E","created_at":"2026-07-05T11:32:47.398420+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFTB57P7R22EBECX","created_at":"2026-07-05T11:32:47.398420+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFTB57P7","created_at":"2026-07-05T11:32:47.398420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE","json":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE.json","graph_json":"https://pith.science/api/pith-number/BFTB57P7R22EBECXZPWVWAISDE/graph.json","events_json":"https://pith.science/api/pith-number/BFTB57P7R22EBECXZPWVWAISDE/events.json","paper":"https://pith.science/paper/BFTB57P7"},"agent_actions":{"view_html":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE","download_json":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE.json","view_paper":"https://pith.science/paper/BFTB57P7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04410&json=true","fetch_graph":"https://pith.science/api/pith-number/BFTB57P7R22EBECXZPWVWAISDE/graph.json","fetch_events":"https://pith.science/api/pith-number/BFTB57P7R22EBECXZPWVWAISDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE/action/storage_attestation","attest_author":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE/action/author_attestation","sign_citation":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE/action/citation_signature","submit_replication":"https://pith.science/pith/BFTB57P7R22EBECXZPWVWAISDE/action/replication_record"}},"created_at":"2026-07-05T11:32:47.398420+00:00","updated_at":"2026-07-05T11:32:47.398420+00:00"}