{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WSTNVQJ76NMSRGNIN66FAVNMQM","short_pith_number":"pith:WSTNVQJ7","canonical_record":{"source":{"id":"2505.09615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T17:59:55Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fedc0e55e80bbaf3252766a0d1990684ee98353b495cfc3b3f48d561d24ac421","abstract_canon_sha256":"d658942dae1c84d6c5cf9956f9b55a7250fa9d86a23fe84db83a4cae4c8cd49e"},"schema_version":"1.0"},"canonical_sha256":"b4a6dac13ff3592899a86fbc5055ac83341a3d1bc4ce90a01c70b9a824857352","source":{"kind":"arxiv","id":"2505.09615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09615","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09615v1","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09615","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"WSTNVQJ76NMS","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"WSTNVQJ76NMSRGNI","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"WSTNVQJ7","created_at":"2026-07-05T11:03:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WSTNVQJ76NMSRGNIN66FAVNMQM","target":"record","payload":{"canonical_record":{"source":{"id":"2505.09615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T17:59:55Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fedc0e55e80bbaf3252766a0d1990684ee98353b495cfc3b3f48d561d24ac421","abstract_canon_sha256":"d658942dae1c84d6c5cf9956f9b55a7250fa9d86a23fe84db83a4cae4c8cd49e"},"schema_version":"1.0"},"canonical_sha256":"b4a6dac13ff3592899a86fbc5055ac83341a3d1bc4ce90a01c70b9a824857352","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:11.343236Z","signature_b64":"lFX5W4p1GUWZxlahd1A2hON1PGG0Zd+E6hYaTmRrR5gYXEel7BaOl1zkbVQgOYcUIzSV8IR8QE2IyMtxv+I9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4a6dac13ff3592899a86fbc5055ac83341a3d1bc4ce90a01c70b9a824857352","last_reissued_at":"2026-07-05T11:03:11.342754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:11.342754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.09615","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cxy44B5uOk601ZPC8Qw6bv0QNQpYXC5JgFjh+C2VqBRyItoNF16/6o09lp8aeCHI8RQ6fgkstc0zuTOetdgrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:15:09.192119Z"},"content_sha256":"224b7db69c8ad0304f8ca43457789f3719de543bead59f08fb4a3ee3e4b1d092","schema_version":"1.0","event_id":"sha256:224b7db69c8ad0304f8ca43457789f3719de543bead59f08fb4a3ee3e4b1d092"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WSTNVQJ76NMSRGNIN66FAVNMQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Fran\\c{c}ois Germain, Janek Ebbers, Michael Jeffrey Jones, Moitreya Chatterjee, Yu-Chiang Frank Wang, Yung-Hsuan Lai","submitted_at":"2025-05-14T17:59:55Z","abstract_excerpt":"Audio-Visual Video Parsing (AVVP) entails the challenging task of localizing both uni-modal events (i.e., those occurring exclusively in either the visual or acoustic modality of a video) and multi-modal events (i.e., those occurring in both modalities concurrently). Moreover, the prohibitive cost of annotating training data with the class labels of all these events, along with their start and end times, imposes constraints on the scalability of AVVP techniques unless they can be trained in a weakly-supervised setting, where only modality-agnostic, video-level labels are available in the train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09615","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/2505.09615/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SxAJwYnc8lrMeB8sJTWkSAdbtMDCN4CDAksctYwO8sLZzVr+ZABpVYe6Dcc4RsELO010GtnPJAp/ZOU/HDKCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:15:09.194258Z"},"content_sha256":"1b1e99bc260e447f55c7c315ac6a24157f2a43ce8114f372490d42a91f2e777e","schema_version":"1.0","event_id":"sha256:1b1e99bc260e447f55c7c315ac6a24157f2a43ce8114f372490d42a91f2e777e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WSTNVQJ76NMSRGNIN66FAVNMQM/bundle.json","state_url":"https://pith.science/pith/WSTNVQJ76NMSRGNIN66FAVNMQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WSTNVQJ76NMSRGNIN66FAVNMQM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-31T16:15:09Z","links":{"resolver":"https://pith.science/pith/WSTNVQJ76NMSRGNIN66FAVNMQM","bundle":"https://pith.science/pith/WSTNVQJ76NMSRGNIN66FAVNMQM/bundle.json","state":"https://pith.science/pith/WSTNVQJ76NMSRGNIN66FAVNMQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WSTNVQJ76NMSRGNIN66FAVNMQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WSTNVQJ76NMSRGNIN66FAVNMQM","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":"d658942dae1c84d6c5cf9956f9b55a7250fa9d86a23fe84db83a4cae4c8cd49e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T17:59:55Z","title_canon_sha256":"fedc0e55e80bbaf3252766a0d1990684ee98353b495cfc3b3f48d561d24ac421"},"schema_version":"1.0","source":{"id":"2505.09615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09615","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09615v1","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09615","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"WSTNVQJ76NMS","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"WSTNVQJ76NMSRGNI","created_at":"2026-07-05T11:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"WSTNVQJ7","created_at":"2026-07-05T11:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:1b1e99bc260e447f55c7c315ac6a24157f2a43ce8114f372490d42a91f2e777e","target":"graph","created_at":"2026-07-05T11:03:11Z","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/2505.09615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Video Parsing (AVVP) entails the challenging task of localizing both uni-modal events (i.e., those occurring exclusively in either the visual or acoustic modality of a video) and multi-modal events (i.e., those occurring in both modalities concurrently). Moreover, the prohibitive cost of annotating training data with the class labels of all these events, along with their start and end times, imposes constraints on the scalability of AVVP techniques unless they can be trained in a weakly-supervised setting, where only modality-agnostic, video-level labels are available in the train","authors_text":"Fran\\c{c}ois Germain, Janek Ebbers, Michael Jeffrey Jones, Moitreya Chatterjee, Yu-Chiang Frank Wang, Yung-Hsuan Lai","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T17:59:55Z","title":"UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09615","kind":"arxiv","version":1},"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":"sha256:224b7db69c8ad0304f8ca43457789f3719de543bead59f08fb4a3ee3e4b1d092","target":"record","created_at":"2026-07-05T11:03:11Z","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":"d658942dae1c84d6c5cf9956f9b55a7250fa9d86a23fe84db83a4cae4c8cd49e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T17:59:55Z","title_canon_sha256":"fedc0e55e80bbaf3252766a0d1990684ee98353b495cfc3b3f48d561d24ac421"},"schema_version":"1.0","source":{"id":"2505.09615","kind":"arxiv","version":1}},"canonical_sha256":"b4a6dac13ff3592899a86fbc5055ac83341a3d1bc4ce90a01c70b9a824857352","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4a6dac13ff3592899a86fbc5055ac83341a3d1bc4ce90a01c70b9a824857352","first_computed_at":"2026-07-05T11:03:11.342754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:11.342754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lFX5W4p1GUWZxlahd1A2hON1PGG0Zd+E6hYaTmRrR5gYXEel7BaOl1zkbVQgOYcUIzSV8IR8QE2IyMtxv+I9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:11.343236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.09615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:224b7db69c8ad0304f8ca43457789f3719de543bead59f08fb4a3ee3e4b1d092","sha256:1b1e99bc260e447f55c7c315ac6a24157f2a43ce8114f372490d42a91f2e777e"],"state_sha256":"ecd23e589741ff362f697fe9f373f2ed7ab2cfb52ac9e98b86164b513863d1f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GL8yQXIpQhO3bebKEZpJDM4usf8xn1wFtzTNTA/J+fo5hNwqHFAskcfpGqkbQVTdgubPZLsjccwfUJKEI4LLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T16:15:09.199608Z","bundle_sha256":"625996a800387881fb179983ef89afb4e73163458671354fffd1c89bc21c573b"}}