{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UHPKWUWWF2BZBS7FCZET4VZ2NK","short_pith_number":"pith:UHPKWUWW","schema_version":"1.0","canonical_sha256":"a1deab52d62e8390cbe516493e573a6a8e1d9de988bb0e9907ba436a225823fa","source":{"kind":"arxiv","id":"2308.07545","version":4},"attestation_state":"computed","paper":{"title":"Vision-Language Dataset Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byron Zhang, Olga Russakovsky, Xindi Wu, Zhiwei Deng","submitted_at":"2023-08-15T03:22:40Z","abstract_excerpt":"Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, preserving sufficient information to quickly train a new model from scratch. However, prior work on dataset distillation has focused exclusively on image classification datasets, whereas modern large-scale datasets are primarily vision-language datasets. In this work, we design the first vision-language dataset distillation method, building on the idea of trajectory matching. A key challenge is that vision-language datasets do not have a set of discrete classes. To overcome this, our proposed method joi"},"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":"2308.07545","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-15T03:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"96809f378b1f547eecfe2379883cb60cd1fb65ede6968ce8a921e5526981720c","abstract_canon_sha256":"09bd5ff7ac2a03c3793dd324736ba27ed6b4e21dbf8d67a28cc72c7a47574a82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:56.692227Z","signature_b64":"lZcpUztEIwPPYtvKCMFKNlZRta/5UcTNr7MC1N8ml4jGZSd4ZJr/QuMOA4zGFFZFIf92VJM8/mUQcBoLCU1sDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1deab52d62e8390cbe516493e573a6a8e1d9de988bb0e9907ba436a225823fa","last_reissued_at":"2026-07-05T08:56:56.691626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:56.691626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Dataset Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byron Zhang, Olga Russakovsky, Xindi Wu, Zhiwei Deng","submitted_at":"2023-08-15T03:22:40Z","abstract_excerpt":"Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, preserving sufficient information to quickly train a new model from scratch. However, prior work on dataset distillation has focused exclusively on image classification datasets, whereas modern large-scale datasets are primarily vision-language datasets. In this work, we design the first vision-language dataset distillation method, building on the idea of trajectory matching. A key challenge is that vision-language datasets do not have a set of discrete classes. To overcome this, our proposed method joi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07545","kind":"arxiv","version":4},"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/2308.07545/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":"2308.07545","created_at":"2026-07-05T08:56:56.691697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07545v4","created_at":"2026-07-05T08:56:56.691697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07545","created_at":"2026-07-05T08:56:56.691697+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHPKWUWWF2BZ","created_at":"2026-07-05T08:56:56.691697+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHPKWUWWF2BZBS7F","created_at":"2026-07-05T08:56:56.691697+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHPKWUWW","created_at":"2026-07-05T08:56:56.691697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22975","citing_title":"TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10666","citing_title":"Omnimodal Dataset Distillation via High-order Proxy Alignment","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK","json":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK.json","graph_json":"https://pith.science/api/pith-number/UHPKWUWWF2BZBS7FCZET4VZ2NK/graph.json","events_json":"https://pith.science/api/pith-number/UHPKWUWWF2BZBS7FCZET4VZ2NK/events.json","paper":"https://pith.science/paper/UHPKWUWW"},"agent_actions":{"view_html":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK","download_json":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK.json","view_paper":"https://pith.science/paper/UHPKWUWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07545&json=true","fetch_graph":"https://pith.science/api/pith-number/UHPKWUWWF2BZBS7FCZET4VZ2NK/graph.json","fetch_events":"https://pith.science/api/pith-number/UHPKWUWWF2BZBS7FCZET4VZ2NK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK/action/storage_attestation","attest_author":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK/action/author_attestation","sign_citation":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK/action/citation_signature","submit_replication":"https://pith.science/pith/UHPKWUWWF2BZBS7FCZET4VZ2NK/action/replication_record"}},"created_at":"2026-07-05T08:56:56.691697+00:00","updated_at":"2026-07-05T08:56:56.691697+00:00"}