{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YUA27DWEWE2EILPZDJO6VU3IBZ","short_pith_number":"pith:YUA27DWE","canonical_record":{"source":{"id":"2407.02318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-01T12:52:05Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"88ae2c289af48d5a069d2c43ed57f5d0ed4e1220158e0bd6369724185b1fd6d0","abstract_canon_sha256":"d847808640b97cca1d605d3c07831e25128ba6c3de680b0a87a97c00c571d33c"},"schema_version":"1.0"},"canonical_sha256":"c501af8ec4b134442df91a5dead3680e51deb5f979566ee445558a88c1a33dfa","source":{"kind":"arxiv","id":"2407.02318","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02318","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02318v1","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02318","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"YUA27DWEWE2E","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"YUA27DWEWE2EILPZ","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"YUA27DWE","created_at":"2026-07-05T08:39:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YUA27DWEWE2EILPZDJO6VU3IBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-01T12:52:05Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"88ae2c289af48d5a069d2c43ed57f5d0ed4e1220158e0bd6369724185b1fd6d0","abstract_canon_sha256":"d847808640b97cca1d605d3c07831e25128ba6c3de680b0a87a97c00c571d33c"},"schema_version":"1.0"},"canonical_sha256":"c501af8ec4b134442df91a5dead3680e51deb5f979566ee445558a88c1a33dfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:22.584308Z","signature_b64":"B25gWDnvyT44ef1fyK+xadcYFaeJ2YLkN2waCjxYsS7acMhhgeg+/5jmE6DxQWh4ZMESJLSmjkbksKrq981sDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c501af8ec4b134442df91a5dead3680e51deb5f979566ee445558a88c1a33dfa","last_reissued_at":"2026-07-05T08:39:22.583863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:22.583863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02318","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":"2026-07-05T08:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"al/nQ0Lt3IojKv3h5vKyEopYZIvJRQO0f63B8TGj9TI/gIqCXIPSGdxhf7japZFYEa67YmqdYP6uygSemFNKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:53:45.378554Z"},"content_sha256":"d4fa9cda2e523baa6d63a965421f001c80be69973c3c043960752cc38e4e8f67","schema_version":"1.0","event_id":"sha256:d4fa9cda2e523baa6d63a965421f001c80be69973c3c043960752cc38e4e8f67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YUA27DWEWE2EILPZDJO6VU3IBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Solution for Temporal Sound Localisation Task of ICCV 1st Perception Test Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jianfeng Lu, Qingguo Chen, Shou Chen, Xiangyu Wu, Yang Yang, Yurui Huang","submitted_at":"2024-07-01T12:52:05Z","abstract_excerpt":"In this paper, we propose a solution for improving the quality of temporal sound localization. We employ a multimodal fusion approach to combine visual and audio features. High-quality visual features are extracted using a state-of-the-art self-supervised pre-training network, resulting in efficient video feature representations. At the same time, audio features serve as complementary information to help the model better localize the start and end of sounds. The fused features are trained in a multi-scale Transformer for training. In the final test dataset, we achieved a mean average precision"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02318","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/2407.02318/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":"2026-07-05T08:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CX/reHZxMSBEPHoH6ZPDB6FY/mjsS1+P3xTEzw1pkXm7xlsFX1rrsLLGyT00CGFejddoIXtFyXRYiDVPp6ZDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:53:45.379358Z"},"content_sha256":"a097ebd1c7670b48e315dbcd325a9a947324dc0f4a67a56a8f357b4382d825e4","schema_version":"1.0","event_id":"sha256:a097ebd1c7670b48e315dbcd325a9a947324dc0f4a67a56a8f357b4382d825e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YUA27DWEWE2EILPZDJO6VU3IBZ/bundle.json","state_url":"https://pith.science/pith/YUA27DWEWE2EILPZDJO6VU3IBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YUA27DWEWE2EILPZDJO6VU3IBZ/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":"2026-08-03T15:53:45Z","links":{"resolver":"https://pith.science/pith/YUA27DWEWE2EILPZDJO6VU3IBZ","bundle":"https://pith.science/pith/YUA27DWEWE2EILPZDJO6VU3IBZ/bundle.json","state":"https://pith.science/pith/YUA27DWEWE2EILPZDJO6VU3IBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YUA27DWEWE2EILPZDJO6VU3IBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YUA27DWEWE2EILPZDJO6VU3IBZ","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":"d847808640b97cca1d605d3c07831e25128ba6c3de680b0a87a97c00c571d33c","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-01T12:52:05Z","title_canon_sha256":"88ae2c289af48d5a069d2c43ed57f5d0ed4e1220158e0bd6369724185b1fd6d0"},"schema_version":"1.0","source":{"id":"2407.02318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02318","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02318v1","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02318","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"YUA27DWEWE2E","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"YUA27DWEWE2EILPZ","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"YUA27DWE","created_at":"2026-07-05T08:39:22Z"}],"graph_snapshots":[{"event_id":"sha256:a097ebd1c7670b48e315dbcd325a9a947324dc0f4a67a56a8f357b4382d825e4","target":"graph","created_at":"2026-07-05T08:39:22Z","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/2407.02318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a solution for improving the quality of temporal sound localization. We employ a multimodal fusion approach to combine visual and audio features. High-quality visual features are extracted using a state-of-the-art self-supervised pre-training network, resulting in efficient video feature representations. At the same time, audio features serve as complementary information to help the model better localize the start and end of sounds. The fused features are trained in a multi-scale Transformer for training. In the final test dataset, we achieved a mean average precision","authors_text":"Jianfeng Lu, Qingguo Chen, Shou Chen, Xiangyu Wu, Yang Yang, Yurui Huang","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-01T12:52:05Z","title":"The Solution for Temporal Sound Localisation Task of ICCV 1st Perception Test Challenge 2023"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02318","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:d4fa9cda2e523baa6d63a965421f001c80be69973c3c043960752cc38e4e8f67","target":"record","created_at":"2026-07-05T08:39:22Z","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":"d847808640b97cca1d605d3c07831e25128ba6c3de680b0a87a97c00c571d33c","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-01T12:52:05Z","title_canon_sha256":"88ae2c289af48d5a069d2c43ed57f5d0ed4e1220158e0bd6369724185b1fd6d0"},"schema_version":"1.0","source":{"id":"2407.02318","kind":"arxiv","version":1}},"canonical_sha256":"c501af8ec4b134442df91a5dead3680e51deb5f979566ee445558a88c1a33dfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c501af8ec4b134442df91a5dead3680e51deb5f979566ee445558a88c1a33dfa","first_computed_at":"2026-07-05T08:39:22.583863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:22.583863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B25gWDnvyT44ef1fyK+xadcYFaeJ2YLkN2waCjxYsS7acMhhgeg+/5jmE6DxQWh4ZMESJLSmjkbksKrq981sDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:22.584308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4fa9cda2e523baa6d63a965421f001c80be69973c3c043960752cc38e4e8f67","sha256:a097ebd1c7670b48e315dbcd325a9a947324dc0f4a67a56a8f357b4382d825e4"],"state_sha256":"24ffc4e897b881835bf1c1412ea2e34327fcf0cf381ab5386534c15200d6281e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pa69ZB9B9ESHazgPXlbcn8iVhhqdotw3xBVpczkhq+CtW0agxOCuLZ6sAmck8Voz+sKrrrwZfiAvWrNf3imFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:53:45.384356Z","bundle_sha256":"d0daa766d6903413f8301a70c08dee2c0bcbba901c28ca7416b8d0519918b40d"}}