{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q2JIXDVBTPHRUECWRW2OSD4TM3","short_pith_number":"pith:Q2JIXDVB","schema_version":"1.0","canonical_sha256":"86928b8ea19bcf1a10568db4e90f9366e9e05949d87f267a790525a69ca26a61","source":{"kind":"arxiv","id":"2404.00264","version":1},"attestation_state":"computed","paper":{"title":"DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aru Maekawa, Kotaro Funakoshi, Manabu Okumura, Satoshi Kosugi","submitted_at":"2024-03-30T06:40:54Z","abstract_excerpt":"Dataset distillation aims to compress a training dataset by creating a small number of informative synthetic samples such that neural networks trained on them perform as well as those trained on the original training dataset. Current text dataset distillation methods create each synthetic sample as a sequence of word embeddings instead of a text to apply gradient-based optimization; however, such embedding-level distilled datasets cannot be used for training other models whose word embedding weights are different from the model used for distillation. To address this issue, we propose a novel t"},"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":"2404.00264","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T06:40:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a636c015f1b23d8ddac6ea0dbdf86982836c3263762739b1894e2503417832f2","abstract_canon_sha256":"98934bcc7a65f463e87337cdc98ea75a6bdb13de42ae7722a1153b612277b152"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:30.457672Z","signature_b64":"IKrVJmua0ns/iNJ2DjcERXEYPG/2Ud+8VLqeZqaA39Ub/OeU5Cct7Bswdbh5LIQ18LpKvIRAUMLm4us371EUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86928b8ea19bcf1a10568db4e90f9366e9e05949d87f267a790525a69ca26a61","last_reissued_at":"2026-07-05T08:02:30.457102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:30.457102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aru Maekawa, Kotaro Funakoshi, Manabu Okumura, Satoshi Kosugi","submitted_at":"2024-03-30T06:40:54Z","abstract_excerpt":"Dataset distillation aims to compress a training dataset by creating a small number of informative synthetic samples such that neural networks trained on them perform as well as those trained on the original training dataset. Current text dataset distillation methods create each synthetic sample as a sequence of word embeddings instead of a text to apply gradient-based optimization; however, such embedding-level distilled datasets cannot be used for training other models whose word embedding weights are different from the model used for distillation. To address this issue, we propose a novel t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00264","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/2404.00264/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":"2404.00264","created_at":"2026-07-05T08:02:30.457171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00264v1","created_at":"2026-07-05T08:02:30.457171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00264","created_at":"2026-07-05T08:02:30.457171+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2JIXDVBTPHR","created_at":"2026-07-05T08:02:30.457171+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2JIXDVBTPHRUECW","created_at":"2026-07-05T08:02:30.457171+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2JIXDVB","created_at":"2026-07-05T08:02:30.457171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.15553","citing_title":"Approximating Language Model Training Data from Weights","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3","json":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3.json","graph_json":"https://pith.science/api/pith-number/Q2JIXDVBTPHRUECWRW2OSD4TM3/graph.json","events_json":"https://pith.science/api/pith-number/Q2JIXDVBTPHRUECWRW2OSD4TM3/events.json","paper":"https://pith.science/paper/Q2JIXDVB"},"agent_actions":{"view_html":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3","download_json":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3.json","view_paper":"https://pith.science/paper/Q2JIXDVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00264&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2JIXDVBTPHRUECWRW2OSD4TM3/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2JIXDVBTPHRUECWRW2OSD4TM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3/action/storage_attestation","attest_author":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3/action/author_attestation","sign_citation":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3/action/citation_signature","submit_replication":"https://pith.science/pith/Q2JIXDVBTPHRUECWRW2OSD4TM3/action/replication_record"}},"created_at":"2026-07-05T08:02:30.457171+00:00","updated_at":"2026-07-05T08:02:30.457171+00:00"}