{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CJNKUUYLALAPC2VH7D5LODUP3G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e043704ec4336c0e989282d540fba33154217dd5639543131c96bb92f4c88eed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T10:51:15Z","title_canon_sha256":"41259537c5d64e489c362356e1d56536362173580e4905a6d7492ecab360197c"},"schema_version":"1.0","source":{"id":"2405.10690","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10690","created_at":"2026-07-05T08:43:55Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10690v4","created_at":"2026-07-05T08:43:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10690","created_at":"2026-07-05T08:43:55Z"},{"alias_kind":"pith_short_12","alias_value":"CJNKUUYLALAP","created_at":"2026-07-05T08:43:55Z"},{"alias_kind":"pith_short_16","alias_value":"CJNKUUYLALAPC2VH","created_at":"2026-07-05T08:43:55Z"},{"alias_kind":"pith_short_8","alias_value":"CJNKUUYL","created_at":"2026-07-05T08:43:55Z"}],"graph_snapshots":[{"event_id":"sha256:15be3c19178685a5aa33f2439d243471890cb193e9fa1a0acf67dc46298d00ad","target":"graph","created_at":"2026-07-05T08:43:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.10690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Weakly supervised audio-visual video parsing (AVVP) methods aim to detect audible-only, visible-only, and audible-visible events using only video-level labels. Existing approaches tackle this by leveraging unimodal and cross-modal contexts. However, we argue that while cross-modal learning is beneficial for detecting audible-visible events, in the weakly supervised scenario, it negatively impacts unaligned audible or visible events by introducing irrelevant modality information. In this paper, we propose CoLeaF, a novel learning framework that optimizes the integration of cross-modal context i","authors_text":"Adrian Hilton, Armin Mustafa, Faegheh Sardari, Philip J. B. Jackson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T10:51:15Z","title":"CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10690","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7466def461358aa3ba6956d2ad601627389e2bcd7a65866f22de79dd6cdd1644","target":"record","created_at":"2026-07-05T08:43:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e043704ec4336c0e989282d540fba33154217dd5639543131c96bb92f4c88eed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T10:51:15Z","title_canon_sha256":"41259537c5d64e489c362356e1d56536362173580e4905a6d7492ecab360197c"},"schema_version":"1.0","source":{"id":"2405.10690","kind":"arxiv","version":4}},"canonical_sha256":"125aaa530b02c0f16aa7f8fab70e8fd992f719753885a7efebe95f65d0f4593e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"125aaa530b02c0f16aa7f8fab70e8fd992f719753885a7efebe95f65d0f4593e","first_computed_at":"2026-07-05T08:43:55.920595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:55.920595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b2aL6tDWIb4axYJnc1zPYWSH6/gMj80Qh8uS+OsoEYheBYY9KCGcQ6kKPewCu4f2wDmClec4NP4kQJTiX7WjDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:55.920994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10690","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7466def461358aa3ba6956d2ad601627389e2bcd7a65866f22de79dd6cdd1644","sha256:15be3c19178685a5aa33f2439d243471890cb193e9fa1a0acf67dc46298d00ad"],"state_sha256":"efb903a15fc3cc55f0deba63d447e354a560cb31f2f34e57e6f5a6d137cc0a08"}