{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OX4AW57KZERD55BDHGEIRR3BCU","short_pith_number":"pith:OX4AW57K","schema_version":"1.0","canonical_sha256":"75f80b77eac9223ef423398888c761151aa41409ccae0bdd5975261beafb42c9","source":{"kind":"arxiv","id":"2110.11794","version":3},"attestation_state":"computed","paper":{"title":"Federated Unlearning via Class-Discriminative Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.DC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Heng Qi, Junxiao Wang, Song Guo, Xin Xie","submitted_at":"2021-10-22T14:01:42Z","abstract_excerpt":"We explore the problem of selectively forgetting categories from trained CNN classification models in the federated learning (FL). Given that the data used for training cannot be accessed globally in FL, our insights probe deep into the internal influence of each channel. Through the visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we propose a method for scrubbing the model clean of information about particular categories. The method does not require "},"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":"2110.11794","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-22T14:01:42Z","cross_cats_sorted":["cs.CR","cs.DC","cs.LG"],"title_canon_sha256":"7948fe00eef0467626c0749e10a43413f3899281b1d4761825248e1c40b7034b","abstract_canon_sha256":"368b7e49edb96db10efcb8d6dcc14298934b221a131ba21acfd9371bb8243a79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:32.230497Z","signature_b64":"PSi/1eeFlbknOATdy9DlaIiUV4lQ8NcPLX+EaL1SdFaGJxF8yaFa0Zq3cssGu2Zrrg0LfZRfUYZY//9BP489Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75f80b77eac9223ef423398888c761151aa41409ccae0bdd5975261beafb42c9","last_reissued_at":"2026-07-05T03:52:32.230082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:32.230082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Unlearning via Class-Discriminative Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.DC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Heng Qi, Junxiao Wang, Song Guo, Xin Xie","submitted_at":"2021-10-22T14:01:42Z","abstract_excerpt":"We explore the problem of selectively forgetting categories from trained CNN classification models in the federated learning (FL). Given that the data used for training cannot be accessed globally in FL, our insights probe deep into the internal influence of each channel. Through the visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we propose a method for scrubbing the model clean of information about particular categories. The method does not require "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11794","kind":"arxiv","version":3},"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/2110.11794/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":"2110.11794","created_at":"2026-07-05T03:52:32.230141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.11794v3","created_at":"2026-07-05T03:52:32.230141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11794","created_at":"2026-07-05T03:52:32.230141+00:00"},{"alias_kind":"pith_short_12","alias_value":"OX4AW57KZERD","created_at":"2026-07-05T03:52:32.230141+00:00"},{"alias_kind":"pith_short_16","alias_value":"OX4AW57KZERD55BD","created_at":"2026-07-05T03:52:32.230141+00:00"},{"alias_kind":"pith_short_8","alias_value":"OX4AW57K","created_at":"2026-07-05T03:52:32.230141+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/OX4AW57KZERD55BDHGEIRR3BCU","json":"https://pith.science/pith/OX4AW57KZERD55BDHGEIRR3BCU.json","graph_json":"https://pith.science/api/pith-number/OX4AW57KZERD55BDHGEIRR3BCU/graph.json","events_json":"https://pith.science/api/pith-number/OX4AW57KZERD55BDHGEIRR3BCU/events.json","paper":"https://pith.science/paper/OX4AW57K"},"agent_actions":{"view_html":"https://pith.science/pith/OX4AW57KZERD55BDHGEIRR3BCU","download_json":"https://pith.science/pith/OX4AW57KZERD55BDHGEIRR3BCU.json","view_paper":"https://pith.science/paper/OX4AW57K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.11794&json=true","fetch_graph":"https://pith.science/api/pith-number/OX4AW57KZERD55BDHGEIRR3BCU/graph.json","fetch_events":"https://pith.science/api/pith-number/OX4AW57KZERD55BDHGEIRR3BCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OX4AW57KZERD55BDHGEIRR3BCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OX4AW57KZERD55BDHGEIRR3BCU/action/storage_attestation","attest_author":"https://pith.science/pith/OX4AW57KZERD55BDHGEIRR3BCU/action/author_attestation","sign_citation":"https://pith.science/pith/OX4AW57KZERD55BDHGEIRR3BCU/action/citation_signature","submit_replication":"https://pith.science/pith/OX4AW57KZERD55BDHGEIRR3BCU/action/replication_record"}},"created_at":"2026-07-05T03:52:32.230141+00:00","updated_at":"2026-07-05T03:52:32.230141+00:00"}