{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T3AQFFIL42XQIQ6XSBEFHMHXHS","short_pith_number":"pith:T3AQFFIL","schema_version":"1.0","canonical_sha256":"9ec102950be6af0443d7904853b0f73ca59007a6327c3078ce7e4e6adf2704ca","source":{"kind":"arxiv","id":"2011.07430","version":1},"attestation_state":"computed","paper":{"title":"Audio-Visual Event Recognition through the lens of Adversary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Florian Metze, Juncheng B Li, Kaixin Ma, Po-Yao Huang, Shuhui Qu","submitted_at":"2020-11-15T01:36:09Z","abstract_excerpt":"As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study several key questions related to multimodal learning through the lens of adversarial noises: 1) The trade-off between early/middle/late fusion affecting its robustness and accuracy 2) How do different frequency/time domain features contribute to the robustness? 3) How do different neural modules contribute to the adversarial noise? In our experiment, we construct adversarial exampl"},"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":"2011.07430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-15T01:36:09Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"616a6b3beef9ab55bed6ce7edb82727d16c9052a8ce2f56ffc728d5f061baca0","abstract_canon_sha256":"025ada903ffda53be75bc029ab5c783f329dd997e5c7738d9aec1e77a22e9eb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:49.764880Z","signature_b64":"jlYax5OFPjIFK3ZBAJfIPyfL7dLPeybOjvdIsqS/0QAkZTtuKvZwQKkKqqzcCKgPUNRlJtxh0xmdLNJ24R0kDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ec102950be6af0443d7904853b0f73ca59007a6327c3078ce7e4e6adf2704ca","last_reissued_at":"2026-07-05T01:51:49.764453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:49.764453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Event Recognition through the lens of Adversary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Florian Metze, Juncheng B Li, Kaixin Ma, Po-Yao Huang, Shuhui Qu","submitted_at":"2020-11-15T01:36:09Z","abstract_excerpt":"As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study several key questions related to multimodal learning through the lens of adversarial noises: 1) The trade-off between early/middle/late fusion affecting its robustness and accuracy 2) How do different frequency/time domain features contribute to the robustness? 3) How do different neural modules contribute to the adversarial noise? In our experiment, we construct adversarial exampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07430","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/2011.07430/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":"2011.07430","created_at":"2026-07-05T01:51:49.764511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.07430v1","created_at":"2026-07-05T01:51:49.764511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07430","created_at":"2026-07-05T01:51:49.764511+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3AQFFIL42XQ","created_at":"2026-07-05T01:51:49.764511+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3AQFFIL42XQIQ6X","created_at":"2026-07-05T01:51:49.764511+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3AQFFIL","created_at":"2026-07-05T01:51:49.764511+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/T3AQFFIL42XQIQ6XSBEFHMHXHS","json":"https://pith.science/pith/T3AQFFIL42XQIQ6XSBEFHMHXHS.json","graph_json":"https://pith.science/api/pith-number/T3AQFFIL42XQIQ6XSBEFHMHXHS/graph.json","events_json":"https://pith.science/api/pith-number/T3AQFFIL42XQIQ6XSBEFHMHXHS/events.json","paper":"https://pith.science/paper/T3AQFFIL"},"agent_actions":{"view_html":"https://pith.science/pith/T3AQFFIL42XQIQ6XSBEFHMHXHS","download_json":"https://pith.science/pith/T3AQFFIL42XQIQ6XSBEFHMHXHS.json","view_paper":"https://pith.science/paper/T3AQFFIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.07430&json=true","fetch_graph":"https://pith.science/api/pith-number/T3AQFFIL42XQIQ6XSBEFHMHXHS/graph.json","fetch_events":"https://pith.science/api/pith-number/T3AQFFIL42XQIQ6XSBEFHMHXHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3AQFFIL42XQIQ6XSBEFHMHXHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3AQFFIL42XQIQ6XSBEFHMHXHS/action/storage_attestation","attest_author":"https://pith.science/pith/T3AQFFIL42XQIQ6XSBEFHMHXHS/action/author_attestation","sign_citation":"https://pith.science/pith/T3AQFFIL42XQIQ6XSBEFHMHXHS/action/citation_signature","submit_replication":"https://pith.science/pith/T3AQFFIL42XQIQ6XSBEFHMHXHS/action/replication_record"}},"created_at":"2026-07-05T01:51:49.764511+00:00","updated_at":"2026-07-05T01:51:49.764511+00:00"}