{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ID6DHKLVGNCLHSX5MJF24BKCCW","short_pith_number":"pith:ID6DHKLV","schema_version":"1.0","canonical_sha256":"40fc33a9753344b3cafd624bae054215b75da9c191ce7ca4549390c387bf4f64","source":{"kind":"arxiv","id":"2505.20888","version":2},"attestation_state":"computed","paper":{"title":"EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengyu Wang, Junbing Yan, Jun Huang, Wenrui Cai, Yuanhao Yue","submitted_at":"2025-05-27T08:32:51Z","abstract_excerpt":"In this paper, we present EasyDistill, a comprehensive toolkit designed for effective black-box and white-box knowledge distillation (KD) of large language models (LLMs). Our framework offers versatile functionalities, including data synthesis, supervised fine-tuning, ranking optimization, and reinforcement learning techniques specifically tailored for KD scenarios. The toolkit accommodates KD functionalities for both System 1 (fast, intuitive) and System 2 (slow, analytical) models. With its modular design and user-friendly interface, EasyDistill empowers researchers and industry practitioner"},"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":"2505.20888","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T08:32:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2048a238c397ebeeb362a3c1e3a00efec69de0e6167a983a3e1f74b476220dc5","abstract_canon_sha256":"421f5488db66f3a571d298522effa27e8d9530face78c65f43d3afe08dc0f3e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:16.882300Z","signature_b64":"QbqMq4+P5tTUNHZ+/vPNYtREwXEEp5hVvVQFsrMF95E8Ok1Gd6ghwwCOBZsUmkywgGdfzS1Xy9wBNJLddZIIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40fc33a9753344b3cafd624bae054215b75da9c191ce7ca4549390c387bf4f64","last_reissued_at":"2026-07-05T11:28:16.881815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:16.881815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengyu Wang, Junbing Yan, Jun Huang, Wenrui Cai, Yuanhao Yue","submitted_at":"2025-05-27T08:32:51Z","abstract_excerpt":"In this paper, we present EasyDistill, a comprehensive toolkit designed for effective black-box and white-box knowledge distillation (KD) of large language models (LLMs). Our framework offers versatile functionalities, including data synthesis, supervised fine-tuning, ranking optimization, and reinforcement learning techniques specifically tailored for KD scenarios. The toolkit accommodates KD functionalities for both System 1 (fast, intuitive) and System 2 (slow, analytical) models. With its modular design and user-friendly interface, EasyDistill empowers researchers and industry practitioner"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20888","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/2505.20888/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":"2505.20888","created_at":"2026-07-05T11:28:16.881868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20888v2","created_at":"2026-07-05T11:28:16.881868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20888","created_at":"2026-07-05T11:28:16.881868+00:00"},{"alias_kind":"pith_short_12","alias_value":"ID6DHKLVGNCL","created_at":"2026-07-05T11:28:16.881868+00:00"},{"alias_kind":"pith_short_16","alias_value":"ID6DHKLVGNCLHSX5","created_at":"2026-07-05T11:28:16.881868+00:00"},{"alias_kind":"pith_short_8","alias_value":"ID6DHKLV","created_at":"2026-07-05T11:28:16.881868+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/ID6DHKLVGNCLHSX5MJF24BKCCW","json":"https://pith.science/pith/ID6DHKLVGNCLHSX5MJF24BKCCW.json","graph_json":"https://pith.science/api/pith-number/ID6DHKLVGNCLHSX5MJF24BKCCW/graph.json","events_json":"https://pith.science/api/pith-number/ID6DHKLVGNCLHSX5MJF24BKCCW/events.json","paper":"https://pith.science/paper/ID6DHKLV"},"agent_actions":{"view_html":"https://pith.science/pith/ID6DHKLVGNCLHSX5MJF24BKCCW","download_json":"https://pith.science/pith/ID6DHKLVGNCLHSX5MJF24BKCCW.json","view_paper":"https://pith.science/paper/ID6DHKLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20888&json=true","fetch_graph":"https://pith.science/api/pith-number/ID6DHKLVGNCLHSX5MJF24BKCCW/graph.json","fetch_events":"https://pith.science/api/pith-number/ID6DHKLVGNCLHSX5MJF24BKCCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ID6DHKLVGNCLHSX5MJF24BKCCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ID6DHKLVGNCLHSX5MJF24BKCCW/action/storage_attestation","attest_author":"https://pith.science/pith/ID6DHKLVGNCLHSX5MJF24BKCCW/action/author_attestation","sign_citation":"https://pith.science/pith/ID6DHKLVGNCLHSX5MJF24BKCCW/action/citation_signature","submit_replication":"https://pith.science/pith/ID6DHKLVGNCLHSX5MJF24BKCCW/action/replication_record"}},"created_at":"2026-07-05T11:28:16.881868+00:00","updated_at":"2026-07-05T11:28:16.881868+00:00"}