{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NPUEXBYPFPDOEMLUS5BBYET5AX","short_pith_number":"pith:NPUEXBYP","schema_version":"1.0","canonical_sha256":"6be84b870f2bc6e2317497421c127d05d2a20a6b77bd034e81629b9458d06fbe","source":{"kind":"arxiv","id":"2607.16369","version":1},"attestation_state":"computed","paper":{"title":"Component-Level Ensemble Fusion for Speech and Environmental Sound Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Andr\\'e Runewicz, Karla Sch\\\"afer, Martin Steinebach","submitted_at":"2026-07-17T14:00:32Z","abstract_excerpt":"This paper describes our submission to the ICME 2026 ESDD2 challenge on environment-aware speech and sound deepfake detection. The task requires five-class classification of audio clips in which speech, environmental sound, both components, or neither component may be spoofed. We propose a component-level ensemble system based on four publicly available pre-trained anti-spoofing models: XLSR-Mamba, DF-Arena, SLS, and TCM-ADD. Each model is fine-tuned on the official CompSpoofV2 development data using three binary heads for original, speech, and environmental sound detection. We further train R"},"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":"2607.16369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-17T14:00:32Z","cross_cats_sorted":[],"title_canon_sha256":"1bde78a121c23bd2483709874d06cf60664d9d13567b6b6af1f1b7d41d142fce","abstract_canon_sha256":"6670f3604b40e36b1003e06921e4fce1c1f679c0d8dc58d3fe0c96c99f62267c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:14.497445Z","signature_b64":"YkiYNE081iCKdBC49bCQ3PgD7iZbYvGrmPEvuDQDLDN1AnSCb1ohDsV53y3DB1SZ9cOHFsR+hfuaNXx1Qu3uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be84b870f2bc6e2317497421c127d05d2a20a6b77bd034e81629b9458d06fbe","last_reissued_at":"2026-07-21T00:20:14.496586Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:14.496586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Component-Level Ensemble Fusion for Speech and Environmental Sound Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Andr\\'e Runewicz, Karla Sch\\\"afer, Martin Steinebach","submitted_at":"2026-07-17T14:00:32Z","abstract_excerpt":"This paper describes our submission to the ICME 2026 ESDD2 challenge on environment-aware speech and sound deepfake detection. The task requires five-class classification of audio clips in which speech, environmental sound, both components, or neither component may be spoofed. We propose a component-level ensemble system based on four publicly available pre-trained anti-spoofing models: XLSR-Mamba, DF-Arena, SLS, and TCM-ADD. Each model is fine-tuned on the official CompSpoofV2 development data using three binary heads for original, speech, and environmental sound detection. We further train R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16369","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/2607.16369/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":"2607.16369","created_at":"2026-07-21T00:20:14.497026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16369v1","created_at":"2026-07-21T00:20:14.497026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16369","created_at":"2026-07-21T00:20:14.497026+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPUEXBYPFPDO","created_at":"2026-07-21T00:20:14.497026+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPUEXBYPFPDOEMLU","created_at":"2026-07-21T00:20:14.497026+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPUEXBYP","created_at":"2026-07-21T00:20:14.497026+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/NPUEXBYPFPDOEMLUS5BBYET5AX","json":"https://pith.science/pith/NPUEXBYPFPDOEMLUS5BBYET5AX.json","graph_json":"https://pith.science/api/pith-number/NPUEXBYPFPDOEMLUS5BBYET5AX/graph.json","events_json":"https://pith.science/api/pith-number/NPUEXBYPFPDOEMLUS5BBYET5AX/events.json","paper":"https://pith.science/paper/NPUEXBYP"},"agent_actions":{"view_html":"https://pith.science/pith/NPUEXBYPFPDOEMLUS5BBYET5AX","download_json":"https://pith.science/pith/NPUEXBYPFPDOEMLUS5BBYET5AX.json","view_paper":"https://pith.science/paper/NPUEXBYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16369&json=true","fetch_graph":"https://pith.science/api/pith-number/NPUEXBYPFPDOEMLUS5BBYET5AX/graph.json","fetch_events":"https://pith.science/api/pith-number/NPUEXBYPFPDOEMLUS5BBYET5AX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPUEXBYPFPDOEMLUS5BBYET5AX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPUEXBYPFPDOEMLUS5BBYET5AX/action/storage_attestation","attest_author":"https://pith.science/pith/NPUEXBYPFPDOEMLUS5BBYET5AX/action/author_attestation","sign_citation":"https://pith.science/pith/NPUEXBYPFPDOEMLUS5BBYET5AX/action/citation_signature","submit_replication":"https://pith.science/pith/NPUEXBYPFPDOEMLUS5BBYET5AX/action/replication_record"}},"created_at":"2026-07-21T00:20:14.497026+00:00","updated_at":"2026-07-21T00:20:14.497026+00:00"}