{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FBNTMKDWI4LBVZV44BCBXTXLRF","short_pith_number":"pith:FBNTMKDW","canonical_record":{"source":{"id":"2307.02041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T05:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"40749673e5590490de46a6cd02e8ff34631c2529358fbbce25e0919bcb969dfd","abstract_canon_sha256":"7a15e8f6dd1a43239b471292cbb64a10d98a07232d67bda62b624449d71454ba"},"schema_version":"1.0"},"canonical_sha256":"285b36287647161ae6bce0441bceeb895bcb2bb9e70ed50ba115d8c0e77c76f3","source":{"kind":"arxiv","id":"2307.02041","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02041","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02041v1","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02041","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"FBNTMKDWI4LB","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"FBNTMKDWI4LBVZV4","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"FBNTMKDW","created_at":"2026-07-05T06:28:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FBNTMKDWI4LBVZV44BCBXTXLRF","target":"record","payload":{"canonical_record":{"source":{"id":"2307.02041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T05:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"40749673e5590490de46a6cd02e8ff34631c2529358fbbce25e0919bcb969dfd","abstract_canon_sha256":"7a15e8f6dd1a43239b471292cbb64a10d98a07232d67bda62b624449d71454ba"},"schema_version":"1.0"},"canonical_sha256":"285b36287647161ae6bce0441bceeb895bcb2bb9e70ed50ba115d8c0e77c76f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:04.338880Z","signature_b64":"NLfYy9JYRu0c7ezsjRlyeqwPVFTB/3pl7N6Ox/hwtyr87WacanvVh1lBjidYeyrxtjCLxZObYw62Ij+W77CYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"285b36287647161ae6bce0441bceeb895bcb2bb9e70ed50ba115d8c0e77c76f3","last_reissued_at":"2026-07-05T06:28:04.338446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:04.338446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.02041","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":"2026-07-05T06:28:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jucG+rhBSBkCbSN0C64dP7Fi904IXUqKatZCEptx4/MUD0Alco9XLljJZh9CWh4c4+9NPpC6GT/rjcEWyirXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:09:40.551021Z"},"content_sha256":"16d58fc6bea6776d6bc8afcdb15b7b783827d2006ecdf1993c6eafdbc49aca25","schema_version":"1.0","event_id":"sha256:16d58fc6bea6776d6bc8afcdb15b7b783827d2006ecdf1993c6eafdbc49aca25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FBNTMKDWI4LBVZV44BCBXTXLRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Jie Fu, Junyu Gao","submitted_at":"2023-07-05T05:55:10Z","abstract_excerpt":"Weakly-supervised audio-visual video parsing (WS-AVVP) aims to localize the temporal extents of audio, visual and audio-visual event instances as well as identify the corresponding event categories with only video-level category labels for training. Most previous methods pay much attention to refining the supervision for each modality or extracting fruitful cross-modality information for more reliable feature learning. None of them have noticed the imbalanced feature learning between different modalities in the task. In this paper, to balance the feature learning processes of different modalit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02041","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/2307.02041/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":"2026-07-05T06:28:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H/GWTS42GHQSf7CYueXN3kVe/DdcQ960sOsCFua6vgeDqbXzfTZDiNDqAAHH/wyOHON+5L9eCZJv/R8RfevoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:09:40.551703Z"},"content_sha256":"803dcb1076cedff49070c6e34a5bf5d86f21536f5c1b004019e60f2ef9ff80c7","schema_version":"1.0","event_id":"sha256:803dcb1076cedff49070c6e34a5bf5d86f21536f5c1b004019e60f2ef9ff80c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBNTMKDWI4LBVZV44BCBXTXLRF/bundle.json","state_url":"https://pith.science/pith/FBNTMKDWI4LBVZV44BCBXTXLRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBNTMKDWI4LBVZV44BCBXTXLRF/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":"2026-08-06T14:09:40Z","links":{"resolver":"https://pith.science/pith/FBNTMKDWI4LBVZV44BCBXTXLRF","bundle":"https://pith.science/pith/FBNTMKDWI4LBVZV44BCBXTXLRF/bundle.json","state":"https://pith.science/pith/FBNTMKDWI4LBVZV44BCBXTXLRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBNTMKDWI4LBVZV44BCBXTXLRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FBNTMKDWI4LBVZV44BCBXTXLRF","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":"7a15e8f6dd1a43239b471292cbb64a10d98a07232d67bda62b624449d71454ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T05:55:10Z","title_canon_sha256":"40749673e5590490de46a6cd02e8ff34631c2529358fbbce25e0919bcb969dfd"},"schema_version":"1.0","source":{"id":"2307.02041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02041","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02041v1","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02041","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"FBNTMKDWI4LB","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"FBNTMKDWI4LBVZV4","created_at":"2026-07-05T06:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"FBNTMKDW","created_at":"2026-07-05T06:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:803dcb1076cedff49070c6e34a5bf5d86f21536f5c1b004019e60f2ef9ff80c7","target":"graph","created_at":"2026-07-05T06:28:04Z","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/2307.02041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Weakly-supervised audio-visual video parsing (WS-AVVP) aims to localize the temporal extents of audio, visual and audio-visual event instances as well as identify the corresponding event categories with only video-level category labels for training. Most previous methods pay much attention to refining the supervision for each modality or extracting fruitful cross-modality information for more reliable feature learning. None of them have noticed the imbalanced feature learning between different modalities in the task. In this paper, to balance the feature learning processes of different modalit","authors_text":"Changsheng Xu, Jie Fu, Junyu Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T05:55:10Z","title":"Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02041","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":"sha256:16d58fc6bea6776d6bc8afcdb15b7b783827d2006ecdf1993c6eafdbc49aca25","target":"record","created_at":"2026-07-05T06:28:04Z","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":"7a15e8f6dd1a43239b471292cbb64a10d98a07232d67bda62b624449d71454ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T05:55:10Z","title_canon_sha256":"40749673e5590490de46a6cd02e8ff34631c2529358fbbce25e0919bcb969dfd"},"schema_version":"1.0","source":{"id":"2307.02041","kind":"arxiv","version":1}},"canonical_sha256":"285b36287647161ae6bce0441bceeb895bcb2bb9e70ed50ba115d8c0e77c76f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"285b36287647161ae6bce0441bceeb895bcb2bb9e70ed50ba115d8c0e77c76f3","first_computed_at":"2026-07-05T06:28:04.338446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:04.338446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NLfYy9JYRu0c7ezsjRlyeqwPVFTB/3pl7N6Ox/hwtyr87WacanvVh1lBjidYeyrxtjCLxZObYw62Ij+W77CYDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:04.338880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16d58fc6bea6776d6bc8afcdb15b7b783827d2006ecdf1993c6eafdbc49aca25","sha256:803dcb1076cedff49070c6e34a5bf5d86f21536f5c1b004019e60f2ef9ff80c7"],"state_sha256":"226cab056fe8b4cc2a0c3cb775bad739af288cb2c545d4c6701ccefe4bf7d6ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IUy0pKPz/LLDcFXyToKqO7AJ8Tsg78Sz19qWlZJa71hg+/Sg0qTFvyUpXSnRrGXkPId1NfFdtYXrXK3GO6rNCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:09:40.557923Z","bundle_sha256":"935ad6d43a404e97407f6640cb6872f22e44582e7f286f1d50da5ce997c9f1eb"}}