{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OQSSLYGUR5JADEMUNTEVM352EE","short_pith_number":"pith:OQSSLYGU","schema_version":"1.0","canonical_sha256":"742525e0d48f520191946cc9566fba211d258da3fd179c0c680c61578ffb2236","source":{"kind":"arxiv","id":"2506.05890","version":1},"attestation_state":"computed","paper":{"title":"Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huan Liu, Weihua Chen, Xu Zhou, Yang Yang, Yiheng Li, Zhen Lei, Zichang Tan","submitted_at":"2025-06-06T08:59:07Z","abstract_excerpt":"To tackle the threat of fake news, the task of detecting and grounding multi-modal media manipulation DGM4 has received increasing attention. However, most state-of-the-art methods fail to explore the fine-grained consistency within local content, usually resulting in an inadequate perception of detailed forgery and unreliable results. In this paper, we propose a novel approach named Contextual-Semantic Consistency Learning (CSCL) to enhance the fine-grained perception ability of forgery for DGM4. Two branches for image and text modalities are established, each of which contains two cascaded d"},"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":"2506.05890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T08:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"e3b40665ba88b9e210e66dcad3fc15bf7f090489a4814291a73f67417f9ffd8d","abstract_canon_sha256":"e5e87926616ce072a1654b5578fe3d33d07548332b93dd67ff14b52cd4c30b82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:12.037524Z","signature_b64":"TBzlSg2lslGcc1e3PhnoLXbmi1tIfMdbroNgn37BpE77HpJRm2fC/7alNCLewZvKtmXIjA79fu/S3tTkOltcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"742525e0d48f520191946cc9566fba211d258da3fd179c0c680c61578ffb2236","last_reissued_at":"2026-07-05T11:17:12.036673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:12.036673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huan Liu, Weihua Chen, Xu Zhou, Yang Yang, Yiheng Li, Zhen Lei, Zichang Tan","submitted_at":"2025-06-06T08:59:07Z","abstract_excerpt":"To tackle the threat of fake news, the task of detecting and grounding multi-modal media manipulation DGM4 has received increasing attention. However, most state-of-the-art methods fail to explore the fine-grained consistency within local content, usually resulting in an inadequate perception of detailed forgery and unreliable results. In this paper, we propose a novel approach named Contextual-Semantic Consistency Learning (CSCL) to enhance the fine-grained perception ability of forgery for DGM4. Two branches for image and text modalities are established, each of which contains two cascaded d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05890","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/2506.05890/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":"2506.05890","created_at":"2026-07-05T11:17:12.036740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05890v1","created_at":"2026-07-05T11:17:12.036740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05890","created_at":"2026-07-05T11:17:12.036740+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQSSLYGUR5JA","created_at":"2026-07-05T11:17:12.036740+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQSSLYGUR5JADEMU","created_at":"2026-07-05T11:17:12.036740+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQSSLYGU","created_at":"2026-07-05T11:17:12.036740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE","json":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE.json","graph_json":"https://pith.science/api/pith-number/OQSSLYGUR5JADEMUNTEVM352EE/graph.json","events_json":"https://pith.science/api/pith-number/OQSSLYGUR5JADEMUNTEVM352EE/events.json","paper":"https://pith.science/paper/OQSSLYGU"},"agent_actions":{"view_html":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE","download_json":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE.json","view_paper":"https://pith.science/paper/OQSSLYGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05890&json=true","fetch_graph":"https://pith.science/api/pith-number/OQSSLYGUR5JADEMUNTEVM352EE/graph.json","fetch_events":"https://pith.science/api/pith-number/OQSSLYGUR5JADEMUNTEVM352EE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE/action/storage_attestation","attest_author":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE/action/author_attestation","sign_citation":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE/action/citation_signature","submit_replication":"https://pith.science/pith/OQSSLYGUR5JADEMUNTEVM352EE/action/replication_record"}},"created_at":"2026-07-05T11:17:12.036740+00:00","updated_at":"2026-07-05T11:17:12.036740+00:00"}