{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U6RT5R6GWU4I6GMLGVKOSAXXJP","short_pith_number":"pith:U6RT5R6G","schema_version":"1.0","canonical_sha256":"a7a33ec7c6b5388f198b3554e902f74bfb6d6da051b11e7e0a8ad896b3b4e749","source":{"kind":"arxiv","id":"2412.11248","version":2},"attestation_state":"computed","paper":{"title":"Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Guo, Jinxing Zhou, Pengcheng Zhao, Yang Zhao, Yanxiang Chen","submitted_at":"2024-12-15T16:54:53Z","abstract_excerpt":"The Audio-Visual Video Parsing task aims to recognize and temporally localize all events occurring in either the audio or visual stream, or both. Capturing accurate event semantics for each audio/visual segment is vital. Prior works directly utilize the extracted holistic audio and visual features for intra- and cross-modal temporal interactions. However, each segment may contain multiple events, resulting in semantically mixed holistic features that can lead to semantic interference during intra- or cross-modal interactions: the event semantics of one segment may incorporate semantics of unre"},"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":"2412.11248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T16:54:53Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"0a4e9117f77be558e35ec12253e5d55ded365ca0e406d6bd5386c3ab685aa810","abstract_canon_sha256":"6dd569851b3599cd75018351bb7dc58a2f91b5aaf6ad86a02425e604df8a1184"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:09.192688Z","signature_b64":"mhSHSINcjIzlTH9yPMfHuhhI/z/zxz0AYRo3L8buBtao47EBzh+MVYWqlTJ48JboSHvVqTc+3XOerOMMGmirDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7a33ec7c6b5388f198b3554e902f74bfb6d6da051b11e7e0a8ad896b3b4e749","last_reissued_at":"2026-07-05T09:50:09.192160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:09.192160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Guo, Jinxing Zhou, Pengcheng Zhao, Yang Zhao, Yanxiang Chen","submitted_at":"2024-12-15T16:54:53Z","abstract_excerpt":"The Audio-Visual Video Parsing task aims to recognize and temporally localize all events occurring in either the audio or visual stream, or both. Capturing accurate event semantics for each audio/visual segment is vital. Prior works directly utilize the extracted holistic audio and visual features for intra- and cross-modal temporal interactions. However, each segment may contain multiple events, resulting in semantically mixed holistic features that can lead to semantic interference during intra- or cross-modal interactions: the event semantics of one segment may incorporate semantics of unre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11248","kind":"arxiv","version":2},"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/2412.11248/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":"2412.11248","created_at":"2026-07-05T09:50:09.192219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11248v2","created_at":"2026-07-05T09:50:09.192219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11248","created_at":"2026-07-05T09:50:09.192219+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6RT5R6GWU4I","created_at":"2026-07-05T09:50:09.192219+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6RT5R6GWU4I6GML","created_at":"2026-07-05T09:50:09.192219+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6RT5R6G","created_at":"2026-07-05T09:50:09.192219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12628","citing_title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP","json":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP.json","graph_json":"https://pith.science/api/pith-number/U6RT5R6GWU4I6GMLGVKOSAXXJP/graph.json","events_json":"https://pith.science/api/pith-number/U6RT5R6GWU4I6GMLGVKOSAXXJP/events.json","paper":"https://pith.science/paper/U6RT5R6G"},"agent_actions":{"view_html":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP","download_json":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP.json","view_paper":"https://pith.science/paper/U6RT5R6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11248&json=true","fetch_graph":"https://pith.science/api/pith-number/U6RT5R6GWU4I6GMLGVKOSAXXJP/graph.json","fetch_events":"https://pith.science/api/pith-number/U6RT5R6GWU4I6GMLGVKOSAXXJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP/action/storage_attestation","attest_author":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP/action/author_attestation","sign_citation":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP/action/citation_signature","submit_replication":"https://pith.science/pith/U6RT5R6GWU4I6GMLGVKOSAXXJP/action/replication_record"}},"created_at":"2026-07-05T09:50:09.192219+00:00","updated_at":"2026-07-05T09:50:09.192219+00:00"}