{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MX5PU3ZKQOSZ3Y3DBWGLH2GM7X","short_pith_number":"pith:MX5PU3ZK","schema_version":"1.0","canonical_sha256":"65fafa6f2a83a59de3630d8cb3e8ccfdd0abd82788e46ecf895d3d4f8ac8d98c","source":{"kind":"arxiv","id":"2205.14570","version":3},"attestation_state":"computed","paper":{"title":"MiniDisc: Minimal Distillation Schedule for Language Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Dawei Song, Jiahao Liu, Jingang Wang, Qifan Wang, Wei Wu, Yang Yang","submitted_at":"2022-05-29T04:22:48Z","abstract_excerpt":"Recent studies have uncovered that language model distillation is less effective when facing a large capacity gap between the teacher and the student, and introduced teacher assistant-based distillation to bridge the gap. As a connection, the scale and the performance of the teacher assistant is of vital importance to bring the knowledge from the teacher to the student. However, existing teacher assistant-based methods require maximally many trials before scheduling an optimal teacher assistant. To this end, we propose a minimal distillation schedule (MiniDisc) for scheduling the optimal teach"},"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":"2205.14570","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-29T04:22:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e438ae7af38b469176f3c2e58109f2ab32b0ad9fcfd36a96389aa3b9a99689e7","abstract_canon_sha256":"84aacf250371bca6efa891a2aa9a44d101ca643f60dba291abe7e8cbbf5d0989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:24.172814Z","signature_b64":"zHwZUqzjuJ7k8o6ytZk+qKfrGyc5DR6kwAqo0/nm6gr1KnWl5j7mlAlMBHBrtSFG5BVVos4ro9A0FJSRkstkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65fafa6f2a83a59de3630d8cb3e8ccfdd0abd82788e46ecf895d3d4f8ac8d98c","last_reissued_at":"2026-07-05T07:38:24.172386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:24.172386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MiniDisc: Minimal Distillation Schedule for Language Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Dawei Song, Jiahao Liu, Jingang Wang, Qifan Wang, Wei Wu, Yang Yang","submitted_at":"2022-05-29T04:22:48Z","abstract_excerpt":"Recent studies have uncovered that language model distillation is less effective when facing a large capacity gap between the teacher and the student, and introduced teacher assistant-based distillation to bridge the gap. As a connection, the scale and the performance of the teacher assistant is of vital importance to bring the knowledge from the teacher to the student. However, existing teacher assistant-based methods require maximally many trials before scheduling an optimal teacher assistant. To this end, we propose a minimal distillation schedule (MiniDisc) for scheduling the optimal teach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14570","kind":"arxiv","version":3},"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/2205.14570/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":"2205.14570","created_at":"2026-07-05T07:38:24.172447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14570v3","created_at":"2026-07-05T07:38:24.172447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14570","created_at":"2026-07-05T07:38:24.172447+00:00"},{"alias_kind":"pith_short_12","alias_value":"MX5PU3ZKQOSZ","created_at":"2026-07-05T07:38:24.172447+00:00"},{"alias_kind":"pith_short_16","alias_value":"MX5PU3ZKQOSZ3Y3D","created_at":"2026-07-05T07:38:24.172447+00:00"},{"alias_kind":"pith_short_8","alias_value":"MX5PU3ZK","created_at":"2026-07-05T07:38:24.172447+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/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X","json":"https://pith.science/pith/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X.json","graph_json":"https://pith.science/api/pith-number/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/graph.json","events_json":"https://pith.science/api/pith-number/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/events.json","paper":"https://pith.science/paper/MX5PU3ZK"},"agent_actions":{"view_html":"https://pith.science/pith/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X","download_json":"https://pith.science/pith/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X.json","view_paper":"https://pith.science/paper/MX5PU3ZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14570&json=true","fetch_graph":"https://pith.science/api/pith-number/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/graph.json","fetch_events":"https://pith.science/api/pith-number/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/action/storage_attestation","attest_author":"https://pith.science/pith/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/action/author_attestation","sign_citation":"https://pith.science/pith/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/action/citation_signature","submit_replication":"https://pith.science/pith/MX5PU3ZKQOSZ3Y3DBWGLH2GM7X/action/replication_record"}},"created_at":"2026-07-05T07:38:24.172447+00:00","updated_at":"2026-07-05T07:38:24.172447+00:00"}