{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ","short_pith_number":"pith:3CQ5GGOG","schema_version":"1.0","canonical_sha256":"d8a1d319c686c2cd847e6ef240ade35e68b2f74c8554b234e28759a322926293","source":{"kind":"arxiv","id":"1904.01769","version":2},"attestation_state":"computed","paper":{"title":"M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianming Zhang, Larry S. Davis, Long Mai, Ning Xu, Peng Zhou, Zuxuan Wu","submitted_at":"2019-04-03T04:54:01Z","abstract_excerpt":"Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however, sequentially distill knowledge only from the last model, leading to performance degradation on the old classes in later incremental learning steps. In this paper, we propose a multi-model and multi-level knowledge distillation strategy. Instead of sequentially distilling knowledge only from the last model, we directly leverage all previous model snapshots. In addition"},"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":"1904.01769","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-03T04:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"e3eaa42def04905651cf7fb5808b59f7530c491824780251d04fda0a5c7fcd57","abstract_canon_sha256":"addb46b8d80202701cb78debd07611a1cc8a451543d58a44acf1de7f78ebcdd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:33:05.864831Z","signature_b64":"4aBE9qoPYfxUK2YSYHhvmkbJjcrcmS+2jBSjOnc8zdKwqiemjfQFhZevBTJWGn6LqL1EaK613WE3yKlKz0BNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8a1d319c686c2cd847e6ef240ade35e68b2f74c8554b234e28759a322926293","last_reissued_at":"2026-07-05T01:33:05.864465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:33:05.864465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianming Zhang, Larry S. Davis, Long Mai, Ning Xu, Peng Zhou, Zuxuan Wu","submitted_at":"2019-04-03T04:54:01Z","abstract_excerpt":"Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however, sequentially distill knowledge only from the last model, leading to performance degradation on the old classes in later incremental learning steps. In this paper, we propose a multi-model and multi-level knowledge distillation strategy. Instead of sequentially distilling knowledge only from the last model, we directly leverage all previous model snapshots. In addition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01769","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/1904.01769/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":"1904.01769","created_at":"2026-07-05T01:33:05.864531+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01769v2","created_at":"2026-07-05T01:33:05.864531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01769","created_at":"2026-07-05T01:33:05.864531+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CQ5GGOGQ3BM","created_at":"2026-07-05T01:33:05.864531+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CQ5GGOGQ3BM3BD6","created_at":"2026-07-05T01:33:05.864531+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CQ5GGOG","created_at":"2026-07-05T01:33:05.864531+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/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ","json":"https://pith.science/pith/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ.json","graph_json":"https://pith.science/api/pith-number/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/graph.json","events_json":"https://pith.science/api/pith-number/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/events.json","paper":"https://pith.science/paper/3CQ5GGOG"},"agent_actions":{"view_html":"https://pith.science/pith/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ","download_json":"https://pith.science/pith/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ.json","view_paper":"https://pith.science/paper/3CQ5GGOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01769&json=true","fetch_graph":"https://pith.science/api/pith-number/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/action/storage_attestation","attest_author":"https://pith.science/pith/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/action/author_attestation","sign_citation":"https://pith.science/pith/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/action/citation_signature","submit_replication":"https://pith.science/pith/3CQ5GGOGQ3BM3BD6N3ZEBLPDLZ/action/replication_record"}},"created_at":"2026-07-05T01:33:05.864531+00:00","updated_at":"2026-07-05T01:33:05.864531+00:00"}