{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XAEDKGH264V27D3F4EYSAVFHUF","short_pith_number":"pith:XAEDKGH2","schema_version":"1.0","canonical_sha256":"b8083518faf72baf8f65e1312054a7a179d4964012802ff8bbbd140c26f803e7","source":{"kind":"arxiv","id":"2210.10212","version":1},"attestation_state":"computed","paper":{"title":"Multi-Source Transformer Architectures for Audiovisual Scene Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Wim Boes","submitted_at":"2022-10-18T23:42:42Z","abstract_excerpt":"In this technical report, the systems we submitted for subtask 1B of the DCASE 2021 challenge, regarding audiovisual scene classification, are described in detail. They are essentially multi-source transformers employing a combination of auditory and visual features to make predictions. These models are evaluated utilizing the macro-averaged multi-class cross-entropy and accuracy metrics.\n  In terms of the macro-averaged multi-class cross-entropy, our best model achieved a score of 0.620 on the validation data. This is slightly better than the performance of the baseline system (0.658).\n  With"},"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":"2210.10212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-18T23:42:42Z","cross_cats_sorted":["cs.CV","cs.SD","eess.IV"],"title_canon_sha256":"774668523e8dc65a59c0b8edfa84cd788bf5d3719036ccb59297812784d267b4","abstract_canon_sha256":"89eac0522fb74401c579b67758b85b781ea464c64692ba7266bdb755f4b8a7f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:07.451203Z","signature_b64":"wEWnvPatXLRLKo2kGJjxeA/96ygVl10lMgclI4kl2B/Ypo6JIHuq3DfP886k/H1K7soXr3Y+yMR/wKi7yB0sAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8083518faf72baf8f65e1312054a7a179d4964012802ff8bbbd140c26f803e7","last_reissued_at":"2026-07-05T05:08:07.450670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:07.450670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Source Transformer Architectures for Audiovisual Scene Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Wim Boes","submitted_at":"2022-10-18T23:42:42Z","abstract_excerpt":"In this technical report, the systems we submitted for subtask 1B of the DCASE 2021 challenge, regarding audiovisual scene classification, are described in detail. They are essentially multi-source transformers employing a combination of auditory and visual features to make predictions. These models are evaluated utilizing the macro-averaged multi-class cross-entropy and accuracy metrics.\n  In terms of the macro-averaged multi-class cross-entropy, our best model achieved a score of 0.620 on the validation data. This is slightly better than the performance of the baseline system (0.658).\n  With"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10212","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/2210.10212/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":"2210.10212","created_at":"2026-07-05T05:08:07.450726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10212v1","created_at":"2026-07-05T05:08:07.450726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10212","created_at":"2026-07-05T05:08:07.450726+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAEDKGH264V2","created_at":"2026-07-05T05:08:07.450726+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAEDKGH264V27D3F","created_at":"2026-07-05T05:08:07.450726+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAEDKGH2","created_at":"2026-07-05T05:08:07.450726+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/XAEDKGH264V27D3F4EYSAVFHUF","json":"https://pith.science/pith/XAEDKGH264V27D3F4EYSAVFHUF.json","graph_json":"https://pith.science/api/pith-number/XAEDKGH264V27D3F4EYSAVFHUF/graph.json","events_json":"https://pith.science/api/pith-number/XAEDKGH264V27D3F4EYSAVFHUF/events.json","paper":"https://pith.science/paper/XAEDKGH2"},"agent_actions":{"view_html":"https://pith.science/pith/XAEDKGH264V27D3F4EYSAVFHUF","download_json":"https://pith.science/pith/XAEDKGH264V27D3F4EYSAVFHUF.json","view_paper":"https://pith.science/paper/XAEDKGH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10212&json=true","fetch_graph":"https://pith.science/api/pith-number/XAEDKGH264V27D3F4EYSAVFHUF/graph.json","fetch_events":"https://pith.science/api/pith-number/XAEDKGH264V27D3F4EYSAVFHUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAEDKGH264V27D3F4EYSAVFHUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAEDKGH264V27D3F4EYSAVFHUF/action/storage_attestation","attest_author":"https://pith.science/pith/XAEDKGH264V27D3F4EYSAVFHUF/action/author_attestation","sign_citation":"https://pith.science/pith/XAEDKGH264V27D3F4EYSAVFHUF/action/citation_signature","submit_replication":"https://pith.science/pith/XAEDKGH264V27D3F4EYSAVFHUF/action/replication_record"}},"created_at":"2026-07-05T05:08:07.450726+00:00","updated_at":"2026-07-05T05:08:07.450726+00:00"}