{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E2E5BMM4OWSMYNO2X4KRIYGUUO","short_pith_number":"pith:E2E5BMM4","schema_version":"1.0","canonical_sha256":"2689d0b19c75a4cc35dabf151460d4a3b2907e00ca056a1d36b7531a92a137fc","source":{"kind":"arxiv","id":"2505.12239","version":2},"attestation_state":"computed","paper":{"title":"Towards Efficient and Exact Forgetting Services in Pre-Trained-Model-based Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Anfeng Liu, Houbing Herbert Song, Huiping Zhuang, Jianheng Tang, Kejia Fan, Mianxiong Dong, Tian Wang, Yajiang Huang, Yunhuai Liu","submitted_at":"2025-05-18T05:28:18Z","abstract_excerpt":"In Continual Learning (CL), using a Pre-Trained Model (PTM) as the feature extractor has become a popular practice. Accompanied by analytic classifiers, the PTM-based methods have achieved state-of-the-art performance in CL, in pursuit of the non-forgetting goal. Meanwhile, actively forgetting specific knowledge acquired during the CL phase is also essential in most service construction paradigms, for example, Mobile Crowd Sensing (MCS), where mobile edge nodes continuously collect sensory data and demand not only non-forgetting adaptation but also specific knowledge forgetting for privacy pre"},"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":"2505.12239","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T05:28:18Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"473f767b1b011c23df744369437c7207ba10e90e4247f5273e0f432bf6dc2ef9","abstract_canon_sha256":"b270e861f976c414a6699ab7816d56652ea724a20ba63b84ae92df84747d6de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:44.624389Z","signature_b64":"tEKDP5qmkzfVUefuvbRKU5KiQ8aDwWOxyq5EwD486YkkOaGzyqnKc3GXPGzYGPK2yOGLplyu7n2S02/F6GJMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2689d0b19c75a4cc35dabf151460d4a3b2907e00ca056a1d36b7531a92a137fc","last_reissued_at":"2026-06-08T01:03:44.623410Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:44.623410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Efficient and Exact Forgetting Services in Pre-Trained-Model-based Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Anfeng Liu, Houbing Herbert Song, Huiping Zhuang, Jianheng Tang, Kejia Fan, Mianxiong Dong, Tian Wang, Yajiang Huang, Yunhuai Liu","submitted_at":"2025-05-18T05:28:18Z","abstract_excerpt":"In Continual Learning (CL), using a Pre-Trained Model (PTM) as the feature extractor has become a popular practice. Accompanied by analytic classifiers, the PTM-based methods have achieved state-of-the-art performance in CL, in pursuit of the non-forgetting goal. Meanwhile, actively forgetting specific knowledge acquired during the CL phase is also essential in most service construction paradigms, for example, Mobile Crowd Sensing (MCS), where mobile edge nodes continuously collect sensory data and demand not only non-forgetting adaptation but also specific knowledge forgetting for privacy pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12239","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/2505.12239/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":"2505.12239","created_at":"2026-06-08T01:03:44.623530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12239v2","created_at":"2026-06-08T01:03:44.623530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12239","created_at":"2026-06-08T01:03:44.623530+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2E5BMM4OWSM","created_at":"2026-06-08T01:03:44.623530+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2E5BMM4OWSMYNO2","created_at":"2026-06-08T01:03:44.623530+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2E5BMM4","created_at":"2026-06-08T01:03:44.623530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.19108","citing_title":"Robust Continual Unlearning against Knowledge Erosion and Forgetting Reversal","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO","json":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO.json","graph_json":"https://pith.science/api/pith-number/E2E5BMM4OWSMYNO2X4KRIYGUUO/graph.json","events_json":"https://pith.science/api/pith-number/E2E5BMM4OWSMYNO2X4KRIYGUUO/events.json","paper":"https://pith.science/paper/E2E5BMM4"},"agent_actions":{"view_html":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO","download_json":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO.json","view_paper":"https://pith.science/paper/E2E5BMM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12239&json=true","fetch_graph":"https://pith.science/api/pith-number/E2E5BMM4OWSMYNO2X4KRIYGUUO/graph.json","fetch_events":"https://pith.science/api/pith-number/E2E5BMM4OWSMYNO2X4KRIYGUUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO/action/storage_attestation","attest_author":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO/action/author_attestation","sign_citation":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO/action/citation_signature","submit_replication":"https://pith.science/pith/E2E5BMM4OWSMYNO2X4KRIYGUUO/action/replication_record"}},"created_at":"2026-06-08T01:03:44.623530+00:00","updated_at":"2026-06-08T01:03:44.623530+00:00"}