{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DAMSAMODK2TBHH7DFNHH7QSIMY","short_pith_number":"pith:DAMSAMOD","schema_version":"1.0","canonical_sha256":"18192031c356a6139fe32b4e7fc248662c7511a1715dcca90da698dfd5cba8f9","source":{"kind":"arxiv","id":"2605.19630","version":1},"attestation_state":"computed","paper":{"title":"EMO-BOOST: Emotion-Augmented Audio-Visual Features for Improved Generalization in Deepfake Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anna Rohrbach, Aritra Marik, Marcel Klemt","submitted_at":"2026-05-19T10:11:10Z","abstract_excerpt":"With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it impossible to collect data for each manipulation to train a deepfake detection model. Thus, generalizing to deepfakes unseen during training is one of the major challenges in current deepfake detection research. To tackle this challenge, we employ high-level semantic cues and argue that these cues can support low-level focused approaches in generalizing to unseen types of manipulations. In this work, we study emotions as a high-level semantic cue."},"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":"2605.19630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T10:11:10Z","cross_cats_sorted":[],"title_canon_sha256":"cb8de07e403d0b74573c89d7d262bdbd09d0af9e1ebbdebfc5a7281e23b0ecaa","abstract_canon_sha256":"74474ef220f276632efc48d103c00e18a01bc6d3c8bbf683e3c89ba6d905e09b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:54.971964Z","signature_b64":"Qp5dpEjmL/hT88JOXeKe/PCKI1MmuR+h411a6wfB82mp50ypzmUlKMlN/ko99ZaaURyL0/4KkZknkdMAe+kuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18192031c356a6139fe32b4e7fc248662c7511a1715dcca90da698dfd5cba8f9","last_reissued_at":"2026-05-20T01:05:54.971423Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:54.971423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMO-BOOST: Emotion-Augmented Audio-Visual Features for Improved Generalization in Deepfake Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anna Rohrbach, Aritra Marik, Marcel Klemt","submitted_at":"2026-05-19T10:11:10Z","abstract_excerpt":"With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it impossible to collect data for each manipulation to train a deepfake detection model. Thus, generalizing to deepfakes unseen during training is one of the major challenges in current deepfake detection research. To tackle this challenge, we employ high-level semantic cues and argue that these cues can support low-level focused approaches in generalizing to unseen types of manipulations. In this work, we study emotions as a high-level semantic cue."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19630","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/2605.19630/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":"2605.19630","created_at":"2026-05-20T01:05:54.971506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19630v1","created_at":"2026-05-20T01:05:54.971506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19630","created_at":"2026-05-20T01:05:54.971506+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAMSAMODK2TB","created_at":"2026-05-20T01:05:54.971506+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAMSAMODK2TBHH7D","created_at":"2026-05-20T01:05:54.971506+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAMSAMOD","created_at":"2026-05-20T01:05:54.971506+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/DAMSAMODK2TBHH7DFNHH7QSIMY","json":"https://pith.science/pith/DAMSAMODK2TBHH7DFNHH7QSIMY.json","graph_json":"https://pith.science/api/pith-number/DAMSAMODK2TBHH7DFNHH7QSIMY/graph.json","events_json":"https://pith.science/api/pith-number/DAMSAMODK2TBHH7DFNHH7QSIMY/events.json","paper":"https://pith.science/paper/DAMSAMOD"},"agent_actions":{"view_html":"https://pith.science/pith/DAMSAMODK2TBHH7DFNHH7QSIMY","download_json":"https://pith.science/pith/DAMSAMODK2TBHH7DFNHH7QSIMY.json","view_paper":"https://pith.science/paper/DAMSAMOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19630&json=true","fetch_graph":"https://pith.science/api/pith-number/DAMSAMODK2TBHH7DFNHH7QSIMY/graph.json","fetch_events":"https://pith.science/api/pith-number/DAMSAMODK2TBHH7DFNHH7QSIMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAMSAMODK2TBHH7DFNHH7QSIMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAMSAMODK2TBHH7DFNHH7QSIMY/action/storage_attestation","attest_author":"https://pith.science/pith/DAMSAMODK2TBHH7DFNHH7QSIMY/action/author_attestation","sign_citation":"https://pith.science/pith/DAMSAMODK2TBHH7DFNHH7QSIMY/action/citation_signature","submit_replication":"https://pith.science/pith/DAMSAMODK2TBHH7DFNHH7QSIMY/action/replication_record"}},"created_at":"2026-05-20T01:05:54.971506+00:00","updated_at":"2026-05-20T01:05:54.971506+00:00"}