{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B3KUTWGPDIDBQ6QR4VMZWVPSGV","short_pith_number":"pith:B3KUTWGP","schema_version":"1.0","canonical_sha256":"0ed549d8cf1a06187a11e5599b55f23548859fb3af77a11a0f045b8358d7335a","source":{"kind":"arxiv","id":"2412.04668","version":1},"attestation_state":"computed","paper":{"title":"Diffusion-Augmented Coreset Expansion for Scalable Dataset Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali Abbasi, Chenyang An, Gayathri Mahalingam, Hamed Pirsiavash, Harsh Shrivastava, Maurice Diesendruck, Pramod Sharma, Shima Imani, Soheil Kolouri","submitted_at":"2024-12-05T23:40:27Z","abstract_excerpt":"With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information from extensive datasets into a compact set of synthetic samples by solving a bilevel optimization problem. However, current methods face challenges in computational efficiency, particularly with high-resolution data and complex architectures. Recently, knowledge-distillation-based dataset condensation approaches have made this process more computationally feasible. Yet, with the recent developments of generative fou"},"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":"2412.04668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T23:40:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e313d3baee62fe8d70beeae7269c735218a70094e0c78ce7997f3aedf1cea49","abstract_canon_sha256":"17d6d4c09fdd1d1f57354c82fbc62ec63fdd0db3944574d4e726466cfe0b0945"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:21.699348Z","signature_b64":"e9OxZv0CxW8T/nktijBSAvCnYIZVXxwFNXh4ZdiyjuhZIsd5hcTyvNOf0TRCYvzxkVOCqzd9kfF7KCg5SgMrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ed549d8cf1a06187a11e5599b55f23548859fb3af77a11a0f045b8358d7335a","last_reissued_at":"2026-07-05T09:45:21.698842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:21.698842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-Augmented Coreset Expansion for Scalable Dataset Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali Abbasi, Chenyang An, Gayathri Mahalingam, Hamed Pirsiavash, Harsh Shrivastava, Maurice Diesendruck, Pramod Sharma, Shima Imani, Soheil Kolouri","submitted_at":"2024-12-05T23:40:27Z","abstract_excerpt":"With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information from extensive datasets into a compact set of synthetic samples by solving a bilevel optimization problem. However, current methods face challenges in computational efficiency, particularly with high-resolution data and complex architectures. Recently, knowledge-distillation-based dataset condensation approaches have made this process more computationally feasible. Yet, with the recent developments of generative fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04668","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/2412.04668/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":"2412.04668","created_at":"2026-07-05T09:45:21.698905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04668v1","created_at":"2026-07-05T09:45:21.698905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04668","created_at":"2026-07-05T09:45:21.698905+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3KUTWGPDIDB","created_at":"2026-07-05T09:45:21.698905+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3KUTWGPDIDBQ6QR","created_at":"2026-07-05T09:45:21.698905+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3KUTWGP","created_at":"2026-07-05T09:45:21.698905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05673","citing_title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV","json":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV.json","graph_json":"https://pith.science/api/pith-number/B3KUTWGPDIDBQ6QR4VMZWVPSGV/graph.json","events_json":"https://pith.science/api/pith-number/B3KUTWGPDIDBQ6QR4VMZWVPSGV/events.json","paper":"https://pith.science/paper/B3KUTWGP"},"agent_actions":{"view_html":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV","download_json":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV.json","view_paper":"https://pith.science/paper/B3KUTWGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04668&json=true","fetch_graph":"https://pith.science/api/pith-number/B3KUTWGPDIDBQ6QR4VMZWVPSGV/graph.json","fetch_events":"https://pith.science/api/pith-number/B3KUTWGPDIDBQ6QR4VMZWVPSGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV/action/storage_attestation","attest_author":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV/action/author_attestation","sign_citation":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV/action/citation_signature","submit_replication":"https://pith.science/pith/B3KUTWGPDIDBQ6QR4VMZWVPSGV/action/replication_record"}},"created_at":"2026-07-05T09:45:21.698905+00:00","updated_at":"2026-07-05T09:45:21.698905+00:00"}