{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3KAHCTAQHWEKOJMRJR7QVIAHGW","short_pith_number":"pith:3KAHCTAQ","canonical_record":{"source":{"id":"2504.09516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-13T11:04:43Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"c2b7bf385cb182a81f10338ebd72452c2622da32f370297fe187f3171e1afbd5","abstract_canon_sha256":"16340c0022e54abec4683c3c0fac59198a7e8806069fb2e1b2d2f52529f05198"},"schema_version":"1.0"},"canonical_sha256":"da80714c103d88a725914c7f0aa007358a3bef6bfe16ef69cb52baf7b1bae487","source":{"kind":"arxiv","id":"2504.09516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09516","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09516v1","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09516","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"3KAHCTAQHWEK","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"3KAHCTAQHWEKOJMR","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"3KAHCTAQ","created_at":"2026-07-05T10:48:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3KAHCTAQHWEKOJMRJR7QVIAHGW","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-13T11:04:43Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"c2b7bf385cb182a81f10338ebd72452c2622da32f370297fe187f3171e1afbd5","abstract_canon_sha256":"16340c0022e54abec4683c3c0fac59198a7e8806069fb2e1b2d2f52529f05198"},"schema_version":"1.0"},"canonical_sha256":"da80714c103d88a725914c7f0aa007358a3bef6bfe16ef69cb52baf7b1bae487","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:38.914229Z","signature_b64":"ilTiqZvWJRSNmcYbAFpr/FmxkHD3Z4a0XKQGJroHzxvlFc5cXdrH/xHIDwSjeoBdre5NZfDeAioyRJq9Jh6vAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da80714c103d88a725914c7f0aa007358a3bef6bfe16ef69cb52baf7b1bae487","last_reissued_at":"2026-07-05T10:48:38.913712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:38.913712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09516","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":"2026-07-05T10:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fmvnhT3YxUQfjI3PK5NHzyHuHPtXIygIHdUTkiVQJ88qPPlgk4X3hO1fMQCI+S/Blmx7yNd59ZULDMprskACBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:58:24.794423Z"},"content_sha256":"15d79bbea64adf023b5630625030dd79a31b6817669c7f02dc293896e560e2e4","schema_version":"1.0","event_id":"sha256:15d79bbea64adf023b5630625030dd79a31b6817669c7f02dc293896e560e2e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3KAHCTAQHWEKOJMRJR7QVIAHGW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FSSUAVL: A Discriminative Framework using Vision Models for Federated Self-Supervised Audio and Image Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiajun Shen, Kin Wai Lau, Ma Lan, Yasar Abbas Ur Rehman, Yuyang Xie","submitted_at":"2025-04-13T11:04:43Z","abstract_excerpt":"Recent studies have demonstrated that vision models can effectively learn multimodal audio-image representations when paired. However, the challenge of enabling deep models to learn representations from unpaired modalities remains unresolved. This issue is especially pertinent in scenarios like Federated Learning (FL), where data is often decentralized, heterogeneous, and lacks a reliable guarantee of paired data. Previous attempts tackled this issue through the use of auxiliary pretrained encoders or generative models on local clients, which invariably raise computational cost with increasing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09516","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/2504.09516/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":"2026-07-05T10:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xiqYxUVzdx42UJBp1hGmI77GtofUFFBQNgmHPTzzEar1Uq7cAa2baf46zIwScqc28L8avn5r7fhCfatCAfvUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:58:24.795063Z"},"content_sha256":"82a4dae70a9ffbcd128155a549ec598868558e50514149b7c3897072591323f8","schema_version":"1.0","event_id":"sha256:82a4dae70a9ffbcd128155a549ec598868558e50514149b7c3897072591323f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3KAHCTAQHWEKOJMRJR7QVIAHGW/bundle.json","state_url":"https://pith.science/pith/3KAHCTAQHWEKOJMRJR7QVIAHGW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3KAHCTAQHWEKOJMRJR7QVIAHGW/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":"2026-08-18T13:58:24Z","links":{"resolver":"https://pith.science/pith/3KAHCTAQHWEKOJMRJR7QVIAHGW","bundle":"https://pith.science/pith/3KAHCTAQHWEKOJMRJR7QVIAHGW/bundle.json","state":"https://pith.science/pith/3KAHCTAQHWEKOJMRJR7QVIAHGW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3KAHCTAQHWEKOJMRJR7QVIAHGW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3KAHCTAQHWEKOJMRJR7QVIAHGW","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":"16340c0022e54abec4683c3c0fac59198a7e8806069fb2e1b2d2f52529f05198","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-13T11:04:43Z","title_canon_sha256":"c2b7bf385cb182a81f10338ebd72452c2622da32f370297fe187f3171e1afbd5"},"schema_version":"1.0","source":{"id":"2504.09516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09516","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09516v1","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09516","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"3KAHCTAQHWEK","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"3KAHCTAQHWEKOJMR","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"3KAHCTAQ","created_at":"2026-07-05T10:48:38Z"}],"graph_snapshots":[{"event_id":"sha256:82a4dae70a9ffbcd128155a549ec598868558e50514149b7c3897072591323f8","target":"graph","created_at":"2026-07-05T10:48:38Z","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/2504.09516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have demonstrated that vision models can effectively learn multimodal audio-image representations when paired. However, the challenge of enabling deep models to learn representations from unpaired modalities remains unresolved. This issue is especially pertinent in scenarios like Federated Learning (FL), where data is often decentralized, heterogeneous, and lacks a reliable guarantee of paired data. Previous attempts tackled this issue through the use of auxiliary pretrained encoders or generative models on local clients, which invariably raise computational cost with increasing","authors_text":"Jiajun Shen, Kin Wai Lau, Ma Lan, Yasar Abbas Ur Rehman, Yuyang Xie","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-13T11:04:43Z","title":"FSSUAVL: A Discriminative Framework using Vision Models for Federated Self-Supervised Audio and Image Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09516","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":"sha256:15d79bbea64adf023b5630625030dd79a31b6817669c7f02dc293896e560e2e4","target":"record","created_at":"2026-07-05T10:48:38Z","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":"16340c0022e54abec4683c3c0fac59198a7e8806069fb2e1b2d2f52529f05198","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-13T11:04:43Z","title_canon_sha256":"c2b7bf385cb182a81f10338ebd72452c2622da32f370297fe187f3171e1afbd5"},"schema_version":"1.0","source":{"id":"2504.09516","kind":"arxiv","version":1}},"canonical_sha256":"da80714c103d88a725914c7f0aa007358a3bef6bfe16ef69cb52baf7b1bae487","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da80714c103d88a725914c7f0aa007358a3bef6bfe16ef69cb52baf7b1bae487","first_computed_at":"2026-07-05T10:48:38.913712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:38.913712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ilTiqZvWJRSNmcYbAFpr/FmxkHD3Z4a0XKQGJroHzxvlFc5cXdrH/xHIDwSjeoBdre5NZfDeAioyRJq9Jh6vAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:38.914229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15d79bbea64adf023b5630625030dd79a31b6817669c7f02dc293896e560e2e4","sha256:82a4dae70a9ffbcd128155a549ec598868558e50514149b7c3897072591323f8"],"state_sha256":"7017e0cf91749dbf0ce49ae8d16981c5b6d9854d8dfd632f7369a6035ceea0ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jp+2B6qhzw/4TqaL4RuD2z7Rs/dNqdpJIRXr/0rt/jGIGvrT4KcKiW0mXdHY1vO/6zQKx1p1ZHn2jihaHVnjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T13:58:24.800623Z","bundle_sha256":"caeb1318f52155f486205a713adbbb352595c9874c943d00ed3787ce60874cc9"}}