{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N2ZZTJ54KEZML6235UN2M5VOKL","short_pith_number":"pith:N2ZZTJ54","schema_version":"1.0","canonical_sha256":"6eb399a7bc5132c5fb5bed1ba676ae52e004a19a2fd4c55410d03ee2ab15c00a","source":{"kind":"arxiv","id":"2505.00318","version":1},"attestation_state":"computed","paper":{"title":"FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bingyang Cheng, Guangxu Zhu, Ming Tang, Shuai Wang, Wei-Bin Kou, Yik-Chung Wu","submitted_at":"2025-05-01T05:37:43Z","abstract_excerpt":"Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a promising paradigm for enhancing the generalization of AD models through privacy-preserving distributed learning. However, these FL AD models face significant temporal catastrophic forgetting when deployed in dynamically evolving environments, where continuous adaptation causes abrupt erosion of historical knowledge. This paper proposes Federated Exponentia"},"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":"2505.00318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-01T05:37:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6b8762fd888e7f500f12c9dc34dc9d6e45c770b30b2a1ed231087abd37ca722e","abstract_canon_sha256":"c36635fe2a0ad9442c369a75786bc9a77405e5e93b7cd2990bd18272dec0fc2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:11.516621Z","signature_b64":"nBOoviqFDKE6/oDiNN6VZKOfEvcFKqfPIVchJBUzsq1PJNsWDeTNOvQ2UnPCI/Vf27RCyMzPggBrci1DgExzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb399a7bc5132c5fb5bed1ba676ae52e004a19a2fd4c55410d03ee2ab15c00a","last_reissued_at":"2026-07-05T10:57:11.516084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:11.516084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bingyang Cheng, Guangxu Zhu, Ming Tang, Shuai Wang, Wei-Bin Kou, Yik-Chung Wu","submitted_at":"2025-05-01T05:37:43Z","abstract_excerpt":"Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a promising paradigm for enhancing the generalization of AD models through privacy-preserving distributed learning. However, these FL AD models face significant temporal catastrophic forgetting when deployed in dynamically evolving environments, where continuous adaptation causes abrupt erosion of historical knowledge. This paper proposes Federated Exponentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00318","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/2505.00318/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":"2505.00318","created_at":"2026-07-05T10:57:11.516155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00318v1","created_at":"2026-07-05T10:57:11.516155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00318","created_at":"2026-07-05T10:57:11.516155+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2ZZTJ54KEZM","created_at":"2026-07-05T10:57:11.516155+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2ZZTJ54KEZML623","created_at":"2026-07-05T10:57:11.516155+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2ZZTJ54","created_at":"2026-07-05T10:57:11.516155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20276","citing_title":"OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL","json":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL.json","graph_json":"https://pith.science/api/pith-number/N2ZZTJ54KEZML6235UN2M5VOKL/graph.json","events_json":"https://pith.science/api/pith-number/N2ZZTJ54KEZML6235UN2M5VOKL/events.json","paper":"https://pith.science/paper/N2ZZTJ54"},"agent_actions":{"view_html":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL","download_json":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL.json","view_paper":"https://pith.science/paper/N2ZZTJ54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00318&json=true","fetch_graph":"https://pith.science/api/pith-number/N2ZZTJ54KEZML6235UN2M5VOKL/graph.json","fetch_events":"https://pith.science/api/pith-number/N2ZZTJ54KEZML6235UN2M5VOKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL/action/storage_attestation","attest_author":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL/action/author_attestation","sign_citation":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL/action/citation_signature","submit_replication":"https://pith.science/pith/N2ZZTJ54KEZML6235UN2M5VOKL/action/replication_record"}},"created_at":"2026-07-05T10:57:11.516155+00:00","updated_at":"2026-07-05T10:57:11.516155+00:00"}