{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MTWFGY6HOWTXCNDEPBFU2XSTGJ","short_pith_number":"pith:MTWFGY6H","schema_version":"1.0","canonical_sha256":"64ec5363c775a7713464784b4d5e53326e7274899e43c948f6ebcc0162254da1","source":{"kind":"arxiv","id":"2607.16721","version":1},"attestation_state":"computed","paper":{"title":"Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anik Jha","submitted_at":"2026-07-18T09:17:41Z","abstract_excerpt":"The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of \"expert\" subnetworks, of which only a few act on any token. That pool is why these models do not fit on the machines most developers own, yet for a user who only wants coding help, most experts encode abilities that will never be invoked. We ask how many experts can be removed, and which, by pruning two recent open-weight MoE models from different families (Qwen3.6-35B-A3B and Gemma-4-26B-A4B) under five selection strategies, judged the way a user would: by whether the mo"},"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":"2607.16721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T09:17:41Z","cross_cats_sorted":[],"title_canon_sha256":"c3965b2ba5a9d44daef79847fd5c121c8895bd8bc344e19e379363bd199971bf","abstract_canon_sha256":"96eb32dfa20a23881c20885be6a92737d3eb8ee69073100c66562719b313d059"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:23.606751Z","signature_b64":"00XxjaE9UgZz4ALWXz3HJjkhyNOAxhXls9CIDQ0yGJdmW/Ra6eSIOqBSYWhoogLaQhx2wDMoW8i7qkBVnLvfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64ec5363c775a7713464784b4d5e53326e7274899e43c948f6ebcc0162254da1","last_reissued_at":"2026-07-21T01:20:23.605986Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:23.605986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anik Jha","submitted_at":"2026-07-18T09:17:41Z","abstract_excerpt":"The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of \"expert\" subnetworks, of which only a few act on any token. That pool is why these models do not fit on the machines most developers own, yet for a user who only wants coding help, most experts encode abilities that will never be invoked. We ask how many experts can be removed, and which, by pruning two recent open-weight MoE models from different families (Qwen3.6-35B-A3B and Gemma-4-26B-A4B) under five selection strategies, judged the way a user would: by whether the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16721","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/2607.16721/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":"2607.16721","created_at":"2026-07-21T01:20:23.606368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16721v1","created_at":"2026-07-21T01:20:23.606368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16721","created_at":"2026-07-21T01:20:23.606368+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTWFGY6HOWTX","created_at":"2026-07-21T01:20:23.606368+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTWFGY6HOWTXCNDE","created_at":"2026-07-21T01:20:23.606368+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTWFGY6H","created_at":"2026-07-21T01:20:23.606368+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/MTWFGY6HOWTXCNDEPBFU2XSTGJ","json":"https://pith.science/pith/MTWFGY6HOWTXCNDEPBFU2XSTGJ.json","graph_json":"https://pith.science/api/pith-number/MTWFGY6HOWTXCNDEPBFU2XSTGJ/graph.json","events_json":"https://pith.science/api/pith-number/MTWFGY6HOWTXCNDEPBFU2XSTGJ/events.json","paper":"https://pith.science/paper/MTWFGY6H"},"agent_actions":{"view_html":"https://pith.science/pith/MTWFGY6HOWTXCNDEPBFU2XSTGJ","download_json":"https://pith.science/pith/MTWFGY6HOWTXCNDEPBFU2XSTGJ.json","view_paper":"https://pith.science/paper/MTWFGY6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16721&json=true","fetch_graph":"https://pith.science/api/pith-number/MTWFGY6HOWTXCNDEPBFU2XSTGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MTWFGY6HOWTXCNDEPBFU2XSTGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTWFGY6HOWTXCNDEPBFU2XSTGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTWFGY6HOWTXCNDEPBFU2XSTGJ/action/storage_attestation","attest_author":"https://pith.science/pith/MTWFGY6HOWTXCNDEPBFU2XSTGJ/action/author_attestation","sign_citation":"https://pith.science/pith/MTWFGY6HOWTXCNDEPBFU2XSTGJ/action/citation_signature","submit_replication":"https://pith.science/pith/MTWFGY6HOWTXCNDEPBFU2XSTGJ/action/replication_record"}},"created_at":"2026-07-21T01:20:23.606368+00:00","updated_at":"2026-07-21T01:20:23.606368+00:00"}