{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AG5RDB3ZFZ5VEO2ITSMC34UTFN","short_pith_number":"pith:AG5RDB3Z","schema_version":"1.0","canonical_sha256":"01bb1187792e7b523b489c982df2932b7d89d90698100a7fad7635bf2a543d0f","source":{"kind":"arxiv","id":"2512.02076","version":2},"attestation_state":"computed","paper":{"title":"FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haozhe Wu","submitted_at":"2025-11-30T17:13:35Z","abstract_excerpt":"We propose FDRMFL, a task-driven multimodal feature extraction framework for federated regression under non-IID data distributions. Extracting predictive features from high-dimensional multimodal inputs is particularly challenging in this setting: data cannot leave each client, local samples are scarce and heterogeneously distributed, and unsupervised dimensionality reduction discards task-relevant information while federated training introduces representation drift across communication rounds. FDRMFL addresses these challenges through a unified four-term local objective: MSE prediction loss, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2512.02076","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-30T17:13:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"941ae572f5e479f3fbc525d67859d98be7e8a2bff3a44a85564b1f98a86ed0b8","abstract_canon_sha256":"459deb21cefe1991b2b6559e068f4f0ad9a66d79b19f914890024fef2f7fa264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:35.118614Z","signature_b64":"ZF3GO+GyZpBeHcHYi188vvvCVQA8s757o2xjBuBAWZlpT4uonMbAr+35i6o2pkLweMCruXn/umaQYjmrZ/PABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01bb1187792e7b523b489c982df2932b7d89d90698100a7fad7635bf2a543d0f","last_reissued_at":"2026-07-09T01:20:35.118026Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:35.118026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haozhe Wu","submitted_at":"2025-11-30T17:13:35Z","abstract_excerpt":"We propose FDRMFL, a task-driven multimodal feature extraction framework for federated regression under non-IID data distributions. Extracting predictive features from high-dimensional multimodal inputs is particularly challenging in this setting: data cannot leave each client, local samples are scarce and heterogeneously distributed, and unsupervised dimensionality reduction discards task-relevant information while federated training introduces representation drift across communication rounds. FDRMFL addresses these challenges through a unified four-term local objective: MSE prediction loss, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02076","kind":"arxiv","version":2},"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/2512.02076/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2512.02076","created_at":"2026-07-09T01:20:35.118085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.02076v2","created_at":"2026-07-09T01:20:35.118085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02076","created_at":"2026-07-09T01:20:35.118085+00:00"},{"alias_kind":"pith_short_12","alias_value":"AG5RDB3ZFZ5V","created_at":"2026-07-09T01:20:35.118085+00:00"},{"alias_kind":"pith_short_16","alias_value":"AG5RDB3ZFZ5VEO2I","created_at":"2026-07-09T01:20:35.118085+00:00"},{"alias_kind":"pith_short_8","alias_value":"AG5RDB3Z","created_at":"2026-07-09T01:20:35.118085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN","json":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN.json","graph_json":"https://pith.science/api/pith-number/AG5RDB3ZFZ5VEO2ITSMC34UTFN/graph.json","events_json":"https://pith.science/api/pith-number/AG5RDB3ZFZ5VEO2ITSMC34UTFN/events.json","paper":"https://pith.science/paper/AG5RDB3Z"},"agent_actions":{"view_html":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN","download_json":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN.json","view_paper":"https://pith.science/paper/AG5RDB3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.02076&json=true","fetch_graph":"https://pith.science/api/pith-number/AG5RDB3ZFZ5VEO2ITSMC34UTFN/graph.json","fetch_events":"https://pith.science/api/pith-number/AG5RDB3ZFZ5VEO2ITSMC34UTFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN/action/storage_attestation","attest_author":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN/action/author_attestation","sign_citation":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN/action/citation_signature","submit_replication":"https://pith.science/pith/AG5RDB3ZFZ5VEO2ITSMC34UTFN/action/replication_record"}},"created_at":"2026-07-09T01:20:35.118085+00:00","updated_at":"2026-07-09T01:20:35.118085+00:00"}