{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QHJXEJTFT7PMGXHBDILFPGCC7L","short_pith_number":"pith:QHJXEJTF","canonical_record":{"source":{"id":"2105.14430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-30T05:13:30Z","cross_cats_sorted":[],"title_canon_sha256":"e0c2810d386c924c55d42e79d57329cf7fc9ce27d98262465b575aa3be1c1ab0","abstract_canon_sha256":"e1e4234ce1295c1a22669523d3a6399ce70f47a42ffae24da8fd2d5a9f13d345"},"schema_version":"1.0"},"canonical_sha256":"81d37226659fdec35ce11a16579842faf6cc4cea4b8d95e87d1fcdbc13882039","source":{"kind":"arxiv","id":"2105.14430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14430","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14430v1","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14430","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"QHJXEJTFT7PM","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"QHJXEJTFT7PMGXHB","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"QHJXEJTF","created_at":"2026-07-05T02:44:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QHJXEJTFT7PMGXHBDILFPGCC7L","target":"record","payload":{"canonical_record":{"source":{"id":"2105.14430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-30T05:13:30Z","cross_cats_sorted":[],"title_canon_sha256":"e0c2810d386c924c55d42e79d57329cf7fc9ce27d98262465b575aa3be1c1ab0","abstract_canon_sha256":"e1e4234ce1295c1a22669523d3a6399ce70f47a42ffae24da8fd2d5a9f13d345"},"schema_version":"1.0"},"canonical_sha256":"81d37226659fdec35ce11a16579842faf6cc4cea4b8d95e87d1fcdbc13882039","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:23.801659Z","signature_b64":"MZZRSaWFvy/ETJic2nnpi6OlnJqqxzjaDM1Hfxd28PzwBhAdeDBRnv3293agAnVR3cpihnjO9n9Ot1IEF435DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81d37226659fdec35ce11a16579842faf6cc4cea4b8d95e87d1fcdbc13882039","last_reissued_at":"2026-07-05T02:44:23.801072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:23.801072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.14430","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":"2026-07-05T02:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1MqGskEbHpE8fq+VvtpSUOqaI+yk/g3NzPK+YJJjl1FjYsTK1anOZpa+fhC/eModZTlVbRqo3uMBFAHaQ3/xCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:34:49.879962Z"},"content_sha256":"1cbe8a126d1bbe73d91dbe6675cd1d75e52130563b6162a5884bff9a928762be","schema_version":"1.0","event_id":"sha256:1cbe8a126d1bbe73d91dbe6675cd1d75e52130563b6162a5884bff9a928762be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QHJXEJTFT7PMGXHBDILFPGCC7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aidong Men, Haiying Wang, Jianning Wu, Shiping Wen, Zhuqing Jiang","submitted_at":"2021-05-30T05:13:30Z","abstract_excerpt":"For multimodal tasks, a good feature extraction network should extract information as much as possible and ensure that the extracted feature embedding and other modal feature embedding have an excellent mutual understanding. The latter is often more critical in feature fusion than the former. Therefore, selecting the optimal feature extraction network collocation is a very important subproblem in multimodal tasks. Most of the existing studies ignore this problem or adopt an ergodic approach. This problem is modeled as an optimization problem in this paper. A novel method is proposed to convert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14430","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/2105.14430/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":"2026-07-05T02:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ewdah6Bj1P95Dp6t8Wrr5+nU0Y6Sebn+8lvnmJOcAP0PiL5kVeuJNZUP0e0QNZFj5tddAzw+mPmo/xOQSgxFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:34:49.880342Z"},"content_sha256":"58edef0b53d875debb84e4ef7d2ff712ab93d97f68a5fc41ae8e2ea7450d951a","schema_version":"1.0","event_id":"sha256:58edef0b53d875debb84e4ef7d2ff712ab93d97f68a5fc41ae8e2ea7450d951a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHJXEJTFT7PMGXHBDILFPGCC7L/bundle.json","state_url":"https://pith.science/pith/QHJXEJTFT7PMGXHBDILFPGCC7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHJXEJTFT7PMGXHBDILFPGCC7L/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":"2026-07-07T15:34:49Z","links":{"resolver":"https://pith.science/pith/QHJXEJTFT7PMGXHBDILFPGCC7L","bundle":"https://pith.science/pith/QHJXEJTFT7PMGXHBDILFPGCC7L/bundle.json","state":"https://pith.science/pith/QHJXEJTFT7PMGXHBDILFPGCC7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHJXEJTFT7PMGXHBDILFPGCC7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QHJXEJTFT7PMGXHBDILFPGCC7L","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":"e1e4234ce1295c1a22669523d3a6399ce70f47a42ffae24da8fd2d5a9f13d345","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-30T05:13:30Z","title_canon_sha256":"e0c2810d386c924c55d42e79d57329cf7fc9ce27d98262465b575aa3be1c1ab0"},"schema_version":"1.0","source":{"id":"2105.14430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14430","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14430v1","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14430","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"QHJXEJTFT7PM","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"QHJXEJTFT7PMGXHB","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"QHJXEJTF","created_at":"2026-07-05T02:44:23Z"}],"graph_snapshots":[{"event_id":"sha256:58edef0b53d875debb84e4ef7d2ff712ab93d97f68a5fc41ae8e2ea7450d951a","target":"graph","created_at":"2026-07-05T02:44:23Z","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/2105.14430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For multimodal tasks, a good feature extraction network should extract information as much as possible and ensure that the extracted feature embedding and other modal feature embedding have an excellent mutual understanding. The latter is often more critical in feature fusion than the former. Therefore, selecting the optimal feature extraction network collocation is a very important subproblem in multimodal tasks. Most of the existing studies ignore this problem or adopt an ergodic approach. This problem is modeled as an optimization problem in this paper. A novel method is proposed to convert","authors_text":"Aidong Men, Haiying Wang, Jianning Wu, Shiping Wen, Zhuqing Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-30T05:13:30Z","title":"Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14430","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":"sha256:1cbe8a126d1bbe73d91dbe6675cd1d75e52130563b6162a5884bff9a928762be","target":"record","created_at":"2026-07-05T02:44:23Z","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":"e1e4234ce1295c1a22669523d3a6399ce70f47a42ffae24da8fd2d5a9f13d345","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-30T05:13:30Z","title_canon_sha256":"e0c2810d386c924c55d42e79d57329cf7fc9ce27d98262465b575aa3be1c1ab0"},"schema_version":"1.0","source":{"id":"2105.14430","kind":"arxiv","version":1}},"canonical_sha256":"81d37226659fdec35ce11a16579842faf6cc4cea4b8d95e87d1fcdbc13882039","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81d37226659fdec35ce11a16579842faf6cc4cea4b8d95e87d1fcdbc13882039","first_computed_at":"2026-07-05T02:44:23.801072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:23.801072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MZZRSaWFvy/ETJic2nnpi6OlnJqqxzjaDM1Hfxd28PzwBhAdeDBRnv3293agAnVR3cpihnjO9n9Ot1IEF435DA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:23.801659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.14430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cbe8a126d1bbe73d91dbe6675cd1d75e52130563b6162a5884bff9a928762be","sha256:58edef0b53d875debb84e4ef7d2ff712ab93d97f68a5fc41ae8e2ea7450d951a"],"state_sha256":"08fa0a2df880d9ba5dae928741055b92ebe5a8b0d851e8286f20ec027af209ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjG6vjD1I8feqxl5ePYbLZGUMJTzmHDMwSMsOWxZoOHNQ8D53wblZhwvkaYXSL7Z3APcKZKRkCY2Oa6PTqEpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:34:49.882340Z","bundle_sha256":"ff6939ed08452f5a0f78221ae09544925fe9b149eb580c888ba7596aab3b13a1"}}