{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PDAT22RDFB4VEBFABFKAPN7NCL","short_pith_number":"pith:PDAT22RD","schema_version":"1.0","canonical_sha256":"78c13d6a2328795204a0095407b7ed12dd3e511ae209bdf81b51af00f85a3265","source":{"kind":"arxiv","id":"2302.09632","version":1},"attestation_state":"computed","paper":{"title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Yin, Chen Liang, Haoming Jiang, Tuo Zhao, Xianfeng Tang, Zheng Li","submitted_at":"2023-02-19T17:37:24Z","abstract_excerpt":"Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained model that can be easily fine-tuned on various tasks with small computational costs and memory footprints. Despite the practical benefits, task-agnostic distillation is challenging. Since the teacher model has a significantly larger capacity and stronger representation power than the student model, it is very difficult for the student to produce predictions 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":"2302.09632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-19T17:37:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"107b48e6b36da71406053c7ba7a509d1da7d1c31d031e4a644082bb2cb4b79e2","abstract_canon_sha256":"d2381f19a97349dc44285af1c21618dfd754e6e9120c9fad6a59cea4e511c126"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:28.134620Z","signature_b64":"ndXWj0XN8H1VWjBcbGEtqi4EnA3h5wMuylJ12jaxsFRkDY7SB8RcZeBKrUgLDFD5npe3ByBKIEHcLlxNQx+CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78c13d6a2328795204a0095407b7ed12dd3e511ae209bdf81b51af00f85a3265","last_reissued_at":"2026-07-05T05:43:28.134211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:28.134211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Yin, Chen Liang, Haoming Jiang, Tuo Zhao, Xianfeng Tang, Zheng Li","submitted_at":"2023-02-19T17:37:24Z","abstract_excerpt":"Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained model that can be easily fine-tuned on various tasks with small computational costs and memory footprints. Despite the practical benefits, task-agnostic distillation is challenging. Since the teacher model has a significantly larger capacity and stronger representation power than the student model, it is very difficult for the student to produce predictions t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09632","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/2302.09632/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":"2302.09632","created_at":"2026-07-05T05:43:28.134276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09632v1","created_at":"2026-07-05T05:43:28.134276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09632","created_at":"2026-07-05T05:43:28.134276+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDAT22RDFB4V","created_at":"2026-07-05T05:43:28.134276+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDAT22RDFB4VEBFA","created_at":"2026-07-05T05:43:28.134276+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDAT22RD","created_at":"2026-07-05T05:43:28.134276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02840","citing_title":"Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL","json":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL.json","graph_json":"https://pith.science/api/pith-number/PDAT22RDFB4VEBFABFKAPN7NCL/graph.json","events_json":"https://pith.science/api/pith-number/PDAT22RDFB4VEBFABFKAPN7NCL/events.json","paper":"https://pith.science/paper/PDAT22RD"},"agent_actions":{"view_html":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL","download_json":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL.json","view_paper":"https://pith.science/paper/PDAT22RD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09632&json=true","fetch_graph":"https://pith.science/api/pith-number/PDAT22RDFB4VEBFABFKAPN7NCL/graph.json","fetch_events":"https://pith.science/api/pith-number/PDAT22RDFB4VEBFABFKAPN7NCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL/action/storage_attestation","attest_author":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL/action/author_attestation","sign_citation":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL/action/citation_signature","submit_replication":"https://pith.science/pith/PDAT22RDFB4VEBFABFKAPN7NCL/action/replication_record"}},"created_at":"2026-07-05T05:43:28.134276+00:00","updated_at":"2026-07-05T05:43:28.134276+00:00"}