{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:57IPH3GCLH5GCFZATTW77GMY2U","short_pith_number":"pith:57IPH3GC","schema_version":"1.0","canonical_sha256":"efd0f3ecc259fa6117209cedff9998d53090078f6cb24be20cbf464a0b8ea36f","source":{"kind":"arxiv","id":"2301.08130","version":2},"attestation_state":"computed","paper":{"title":"A Cohesive Distillation Architecture for Neural Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jan Philip Wahle","submitted_at":"2023-01-12T08:01:53Z","abstract_excerpt":"A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study investigates methods for Knowledge Distillation (KD) to provide efficient alternatives to large-scale models. In this context, KD means extracting information about language encoded in a Neural Network and Lexical Knowledge Databases. We developed two methods to test our hypothesis that efficient architectures can gain knowledge from LMs and extract valuable infor"},"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":"2301.08130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-12T08:01:53Z","cross_cats_sorted":[],"title_canon_sha256":"08f24b30ca9edd8d2de894956323ef6db592f8e43727ab824d0983e240e06474","abstract_canon_sha256":"fd6d829d1c5ef99cafb026ac37fe087700748398780625ae2bb86144e97d3931"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:52.622852Z","signature_b64":"d8HW96yZm6dCMTcLXxupUR4SjZdaQaa8VBWhIEcxv6KheoRj3/g6gUeoeNKlrHhEt4MTO1h/2vO1cRamIQ3QAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efd0f3ecc259fa6117209cedff9998d53090078f6cb24be20cbf464a0b8ea36f","last_reissued_at":"2026-07-05T05:36:52.622409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:52.622409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Cohesive Distillation Architecture for Neural Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jan Philip Wahle","submitted_at":"2023-01-12T08:01:53Z","abstract_excerpt":"A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study investigates methods for Knowledge Distillation (KD) to provide efficient alternatives to large-scale models. In this context, KD means extracting information about language encoded in a Neural Network and Lexical Knowledge Databases. We developed two methods to test our hypothesis that efficient architectures can gain knowledge from LMs and extract valuable infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08130","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/2301.08130/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":"2301.08130","created_at":"2026-07-05T05:36:52.622466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.08130v2","created_at":"2026-07-05T05:36:52.622466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08130","created_at":"2026-07-05T05:36:52.622466+00:00"},{"alias_kind":"pith_short_12","alias_value":"57IPH3GCLH5G","created_at":"2026-07-05T05:36:52.622466+00:00"},{"alias_kind":"pith_short_16","alias_value":"57IPH3GCLH5GCFZA","created_at":"2026-07-05T05:36:52.622466+00:00"},{"alias_kind":"pith_short_8","alias_value":"57IPH3GC","created_at":"2026-07-05T05:36:52.622466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13825","citing_title":"Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models","ref_index":78,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U","json":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U.json","graph_json":"https://pith.science/api/pith-number/57IPH3GCLH5GCFZATTW77GMY2U/graph.json","events_json":"https://pith.science/api/pith-number/57IPH3GCLH5GCFZATTW77GMY2U/events.json","paper":"https://pith.science/paper/57IPH3GC"},"agent_actions":{"view_html":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U","download_json":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U.json","view_paper":"https://pith.science/paper/57IPH3GC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.08130&json=true","fetch_graph":"https://pith.science/api/pith-number/57IPH3GCLH5GCFZATTW77GMY2U/graph.json","fetch_events":"https://pith.science/api/pith-number/57IPH3GCLH5GCFZATTW77GMY2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U/action/storage_attestation","attest_author":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U/action/author_attestation","sign_citation":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U/action/citation_signature","submit_replication":"https://pith.science/pith/57IPH3GCLH5GCFZATTW77GMY2U/action/replication_record"}},"created_at":"2026-07-05T05:36:52.622466+00:00","updated_at":"2026-07-05T05:36:52.622466+00:00"}