{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G4WULR3QGMD65J2Z57NORFFS7R","short_pith_number":"pith:G4WULR3Q","schema_version":"1.0","canonical_sha256":"372d45c7703307eea759efdae894b2fc574f379dd68b48eacb4aad9c2984b5c3","source":{"kind":"arxiv","id":"2505.20135","version":2},"attestation_state":"computed","paper":{"title":"Data-Distill-Net: A Data Distillation Approach Tailored for Reply-based Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deyu Meng, Quanziang Wang, Renzhen Wang, Wenyang Liao, Yichen Wu","submitted_at":"2025-05-26T15:37:10Z","abstract_excerpt":"Replay-based continual learning (CL) methods assume that models trained on a small subset can also effectively minimize the empirical risk of the complete dataset. These methods maintain a memory buffer that stores a sampled subset of data from previous tasks to consolidate past knowledge. However, this assumption is not guaranteed in practice due to the limited capacity of the memory buffer and the heuristic criteria used for buffer data selection. To address this issue, we propose a new dataset distillation framework tailored for CL, which maintains a learnable memory buffer to distill the g"},"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":"2505.20135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T15:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"ac4ff4eff2787db230283c13783c64cdc73f3f8eaa7b6b4e94fe030fe86ff008","abstract_canon_sha256":"59f7fd1a1aad1bd306358a4bf9f7d350550ceb89fbdfcc30fa87b554b1d119d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:22.898569Z","signature_b64":"WLqT3XW/TfSs2VEhr1hTPnxSBemOCHkT+4Q4JxSsNhB3W5KZLSxkBGYPo8wgoI7G+yivpMX2Z1hbll3POTxLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"372d45c7703307eea759efdae894b2fc574f379dd68b48eacb4aad9c2984b5c3","last_reissued_at":"2026-07-05T11:11:22.898069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:22.898069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Distill-Net: A Data Distillation Approach Tailored for Reply-based Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deyu Meng, Quanziang Wang, Renzhen Wang, Wenyang Liao, Yichen Wu","submitted_at":"2025-05-26T15:37:10Z","abstract_excerpt":"Replay-based continual learning (CL) methods assume that models trained on a small subset can also effectively minimize the empirical risk of the complete dataset. These methods maintain a memory buffer that stores a sampled subset of data from previous tasks to consolidate past knowledge. However, this assumption is not guaranteed in practice due to the limited capacity of the memory buffer and the heuristic criteria used for buffer data selection. To address this issue, we propose a new dataset distillation framework tailored for CL, which maintains a learnable memory buffer to distill the g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20135","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/2505.20135/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":"2505.20135","created_at":"2026-07-05T11:11:22.898126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20135v2","created_at":"2026-07-05T11:11:22.898126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20135","created_at":"2026-07-05T11:11:22.898126+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4WULR3QGMD6","created_at":"2026-07-05T11:11:22.898126+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4WULR3QGMD65J2Z","created_at":"2026-07-05T11:11:22.898126+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4WULR3Q","created_at":"2026-07-05T11:11:22.898126+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/G4WULR3QGMD65J2Z57NORFFS7R","json":"https://pith.science/pith/G4WULR3QGMD65J2Z57NORFFS7R.json","graph_json":"https://pith.science/api/pith-number/G4WULR3QGMD65J2Z57NORFFS7R/graph.json","events_json":"https://pith.science/api/pith-number/G4WULR3QGMD65J2Z57NORFFS7R/events.json","paper":"https://pith.science/paper/G4WULR3Q"},"agent_actions":{"view_html":"https://pith.science/pith/G4WULR3QGMD65J2Z57NORFFS7R","download_json":"https://pith.science/pith/G4WULR3QGMD65J2Z57NORFFS7R.json","view_paper":"https://pith.science/paper/G4WULR3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20135&json=true","fetch_graph":"https://pith.science/api/pith-number/G4WULR3QGMD65J2Z57NORFFS7R/graph.json","fetch_events":"https://pith.science/api/pith-number/G4WULR3QGMD65J2Z57NORFFS7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4WULR3QGMD65J2Z57NORFFS7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4WULR3QGMD65J2Z57NORFFS7R/action/storage_attestation","attest_author":"https://pith.science/pith/G4WULR3QGMD65J2Z57NORFFS7R/action/author_attestation","sign_citation":"https://pith.science/pith/G4WULR3QGMD65J2Z57NORFFS7R/action/citation_signature","submit_replication":"https://pith.science/pith/G4WULR3QGMD65J2Z57NORFFS7R/action/replication_record"}},"created_at":"2026-07-05T11:11:22.898126+00:00","updated_at":"2026-07-05T11:11:22.898126+00:00"}