{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UR37AWQ5SWKHK7OCA442MBL24A","short_pith_number":"pith:UR37AWQ5","schema_version":"1.0","canonical_sha256":"a477f05a1d9594757dc20739a6057ae0392dc16e010d199a5b831e2e765b5b6f","source":{"kind":"arxiv","id":"2606.04980","version":1},"attestation_state":"computed","paper":{"title":"AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Conzelmann, Michael W. Mahoney, Shiwei Liu, T. Konstantin Rusch, Wanqi Yang, Xiawu Zheng, Yuexiao Ma","submitted_at":"2026-06-03T15:03:18Z","abstract_excerpt":"Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in memory. Mixed-precision quantization can substantially reduce this footprint by assigning different bit-widths to different experts. Existing approaches, however, typically rely on calibration data to estimate expert importance and determine bit allocation. For frontier MoE LLMs, the original training data, and hence the true training distribution, is proprietary and inaccessible. As a result, calibration sets are inev"},"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":"2606.04980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T15:03:18Z","cross_cats_sorted":[],"title_canon_sha256":"dfb41cd358275574630bf52da4d95ced08f7c79bb1c88261a094e67f2630d01e","abstract_canon_sha256":"1e64b377038b8e3a181d878b30665e39f3e6eb05e8b08ac91031e93397999ef9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:59.382146Z","signature_b64":"l24B1vj0ED91s4oXhbCTROaz3PVfMdPg/Ld2VEb/iX3MHW8+UzJC8eOU35rSO3syp9Kc14sIj2I+jEUAYthhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a477f05a1d9594757dc20739a6057ae0392dc16e010d199a5b831e2e765b5b6f","last_reissued_at":"2026-06-04T01:09:59.381275Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:59.381275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Conzelmann, Michael W. Mahoney, Shiwei Liu, T. Konstantin Rusch, Wanqi Yang, Xiawu Zheng, Yuexiao Ma","submitted_at":"2026-06-03T15:03:18Z","abstract_excerpt":"Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in memory. Mixed-precision quantization can substantially reduce this footprint by assigning different bit-widths to different experts. Existing approaches, however, typically rely on calibration data to estimate expert importance and determine bit allocation. For frontier MoE LLMs, the original training data, and hence the true training distribution, is proprietary and inaccessible. As a result, calibration sets are inev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04980","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/2606.04980/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":"2606.04980","created_at":"2026-06-04T01:09:59.381443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04980v1","created_at":"2026-06-04T01:09:59.381443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04980","created_at":"2026-06-04T01:09:59.381443+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR37AWQ5SWKH","created_at":"2026-06-04T01:09:59.381443+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR37AWQ5SWKHK7OC","created_at":"2026-06-04T01:09:59.381443+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR37AWQ5","created_at":"2026-06-04T01:09:59.381443+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/UR37AWQ5SWKHK7OCA442MBL24A","json":"https://pith.science/pith/UR37AWQ5SWKHK7OCA442MBL24A.json","graph_json":"https://pith.science/api/pith-number/UR37AWQ5SWKHK7OCA442MBL24A/graph.json","events_json":"https://pith.science/api/pith-number/UR37AWQ5SWKHK7OCA442MBL24A/events.json","paper":"https://pith.science/paper/UR37AWQ5"},"agent_actions":{"view_html":"https://pith.science/pith/UR37AWQ5SWKHK7OCA442MBL24A","download_json":"https://pith.science/pith/UR37AWQ5SWKHK7OCA442MBL24A.json","view_paper":"https://pith.science/paper/UR37AWQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04980&json=true","fetch_graph":"https://pith.science/api/pith-number/UR37AWQ5SWKHK7OCA442MBL24A/graph.json","fetch_events":"https://pith.science/api/pith-number/UR37AWQ5SWKHK7OCA442MBL24A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR37AWQ5SWKHK7OCA442MBL24A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR37AWQ5SWKHK7OCA442MBL24A/action/storage_attestation","attest_author":"https://pith.science/pith/UR37AWQ5SWKHK7OCA442MBL24A/action/author_attestation","sign_citation":"https://pith.science/pith/UR37AWQ5SWKHK7OCA442MBL24A/action/citation_signature","submit_replication":"https://pith.science/pith/UR37AWQ5SWKHK7OCA442MBL24A/action/replication_record"}},"created_at":"2026-06-04T01:09:59.381443+00:00","updated_at":"2026-06-04T01:09:59.381443+00:00"}