{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JWYASC6GKUTG3PMUCRLUPVXVTV","short_pith_number":"pith:JWYASC6G","schema_version":"1.0","canonical_sha256":"4db0090bc655266dbd94145747d6f59d4c2d2fb9696a4cff87761e36fd90c9a8","source":{"kind":"arxiv","id":"2608.04048","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Dong, Haihao Shen, Wenhua Cheng, Yu Luo","submitted_at":"2026-08-04T08:32:05Z","abstract_excerpt":"Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput. However, conventional quantization methods typically require a separate checkpoint for each target bit-width. We introduce Recurrent Residual Quantization (RRQ), a post-training quantization (PTQ) framework that represents weights as a low-bit quantized base together with a sequence of quantized residual corrections, enabling multiple effective precisions from a single checkpoint. Starting from a 2-bit model obtained via post-training quanti"},"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":"2608.04048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T08:32:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c4e1aba778956ec7db7ecc06a501497246832e4f8745625f475e1efb0d60137","abstract_canon_sha256":"aeb4b836be6893b853c273a64a4c0ea0b1914c2c207f2c148f4dd9d96c304687"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:28:04.383619Z","signature_b64":"L+pVLee2cRagNpPhgDZEcQ3RKJHft8aCRhgLehF1yd0prnb0xzh+CUWaMeStkgtg9ZtZCidGrT1e3qv97h4KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4db0090bc655266dbd94145747d6f59d4c2d2fb9696a4cff87761e36fd90c9a8","last_reissued_at":"2026-08-06T01:28:04.382208Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:28:04.382208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Dong, Haihao Shen, Wenhua Cheng, Yu Luo","submitted_at":"2026-08-04T08:32:05Z","abstract_excerpt":"Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput. However, conventional quantization methods typically require a separate checkpoint for each target bit-width. We introduce Recurrent Residual Quantization (RRQ), a post-training quantization (PTQ) framework that represents weights as a low-bit quantized base together with a sequence of quantized residual corrections, enabling multiple effective precisions from a single checkpoint. Starting from a 2-bit model obtained via post-training quanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04048","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/2608.04048/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":"2608.04048","created_at":"2026-08-06T01:28:04.383957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04048v1","created_at":"2026-08-06T01:28:04.383957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04048","created_at":"2026-08-06T01:28:04.383957+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWYASC6GKUTG","created_at":"2026-08-06T01:28:04.383957+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWYASC6GKUTG3PMU","created_at":"2026-08-06T01:28:04.383957+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWYASC6G","created_at":"2026-08-06T01:28:04.383957+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/JWYASC6GKUTG3PMUCRLUPVXVTV","json":"https://pith.science/pith/JWYASC6GKUTG3PMUCRLUPVXVTV.json","graph_json":"https://pith.science/api/pith-number/JWYASC6GKUTG3PMUCRLUPVXVTV/graph.json","events_json":"https://pith.science/api/pith-number/JWYASC6GKUTG3PMUCRLUPVXVTV/events.json","paper":"https://pith.science/paper/JWYASC6G"},"agent_actions":{"view_html":"https://pith.science/pith/JWYASC6GKUTG3PMUCRLUPVXVTV","download_json":"https://pith.science/pith/JWYASC6GKUTG3PMUCRLUPVXVTV.json","view_paper":"https://pith.science/paper/JWYASC6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04048&json=true","fetch_graph":"https://pith.science/api/pith-number/JWYASC6GKUTG3PMUCRLUPVXVTV/graph.json","fetch_events":"https://pith.science/api/pith-number/JWYASC6GKUTG3PMUCRLUPVXVTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWYASC6GKUTG3PMUCRLUPVXVTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWYASC6GKUTG3PMUCRLUPVXVTV/action/storage_attestation","attest_author":"https://pith.science/pith/JWYASC6GKUTG3PMUCRLUPVXVTV/action/author_attestation","sign_citation":"https://pith.science/pith/JWYASC6GKUTG3PMUCRLUPVXVTV/action/citation_signature","submit_replication":"https://pith.science/pith/JWYASC6GKUTG3PMUCRLUPVXVTV/action/replication_record"}},"created_at":"2026-08-06T01:28:04.383957+00:00","updated_at":"2026-08-06T01:28:04.383957+00:00"}