{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4AB4YLVRQ4D6XBO7TWWITOO26V","short_pith_number":"pith:4AB4YLVR","schema_version":"1.0","canonical_sha256":"e003cc2eb18707eb85df9dac89b9daf548a7855afecb6c412e0bf2c6b1fb0d72","source":{"kind":"arxiv","id":"2406.18561","version":1},"attestation_state":"computed","paper":{"title":"SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hye Won Chung, Yongmin Lee","submitted_at":"2024-05-28T06:54:04Z","abstract_excerpt":"Dataset distillation aims to synthesize a small number of images per class (IPC) from a large dataset to approximate full dataset training with minimal performance loss. While effective in very small IPC ranges, many distillation methods become less effective, even underperforming random sample selection, as IPC increases. Our examination of state-of-the-art trajectory-matching based distillation methods across various IPC scales reveals that these methods struggle to incorporate the complex, rare features of harder samples into the synthetic dataset even with the increased IPC, resulting in a"},"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":"2406.18561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T06:54:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"95605e28d3ff18e2f39ddf97bad4d282f4a64ac0a07ff645052d1b0ade2f44b3","abstract_canon_sha256":"6ea0634de72d7721665066f2d1a02789b565d68221037137feb6539f17a0bad1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:22.335354Z","signature_b64":"A1mhjTnmX12ndTuFY+xOXMaGJupLnW2uUzBxIYtnOK0sOCaHE2XqEKBDxbFBLu89KAaCualycijZR5SO0NBYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e003cc2eb18707eb85df9dac89b9daf548a7855afecb6c412e0bf2c6b1fb0d72","last_reissued_at":"2026-07-05T08:37:22.334875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:22.334875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hye Won Chung, Yongmin Lee","submitted_at":"2024-05-28T06:54:04Z","abstract_excerpt":"Dataset distillation aims to synthesize a small number of images per class (IPC) from a large dataset to approximate full dataset training with minimal performance loss. While effective in very small IPC ranges, many distillation methods become less effective, even underperforming random sample selection, as IPC increases. Our examination of state-of-the-art trajectory-matching based distillation methods across various IPC scales reveals that these methods struggle to incorporate the complex, rare features of harder samples into the synthetic dataset even with the increased IPC, resulting in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18561","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/2406.18561/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":"2406.18561","created_at":"2026-07-05T08:37:22.334934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18561v1","created_at":"2026-07-05T08:37:22.334934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18561","created_at":"2026-07-05T08:37:22.334934+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AB4YLVRQ4D6","created_at":"2026-07-05T08:37:22.334934+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AB4YLVRQ4D6XBO7","created_at":"2026-07-05T08:37:22.334934+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AB4YLVR","created_at":"2026-07-05T08:37:22.334934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29837","citing_title":"Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V","json":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V.json","graph_json":"https://pith.science/api/pith-number/4AB4YLVRQ4D6XBO7TWWITOO26V/graph.json","events_json":"https://pith.science/api/pith-number/4AB4YLVRQ4D6XBO7TWWITOO26V/events.json","paper":"https://pith.science/paper/4AB4YLVR"},"agent_actions":{"view_html":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V","download_json":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V.json","view_paper":"https://pith.science/paper/4AB4YLVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18561&json=true","fetch_graph":"https://pith.science/api/pith-number/4AB4YLVRQ4D6XBO7TWWITOO26V/graph.json","fetch_events":"https://pith.science/api/pith-number/4AB4YLVRQ4D6XBO7TWWITOO26V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V/action/storage_attestation","attest_author":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V/action/author_attestation","sign_citation":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V/action/citation_signature","submit_replication":"https://pith.science/pith/4AB4YLVRQ4D6XBO7TWWITOO26V/action/replication_record"}},"created_at":"2026-07-05T08:37:22.334934+00:00","updated_at":"2026-07-05T08:37:22.334934+00:00"}