{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M2RFEHUPL6ZIYEVXAQ6GLU4EPO","short_pith_number":"pith:M2RFEHUP","schema_version":"1.0","canonical_sha256":"66a2521e8f5fb28c12b7043c65d3847baa3f76a84c87f23fe2bc5b8c25380e84","source":{"kind":"arxiv","id":"2606.00365","version":1},"attestation_state":"computed","paper":{"title":"SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Anand Raghunathan, Aradhana Mohan Parvathy, Arnab Raha, Deepak A. Mathaikutty, Shamik Kundu, Soumendu Kumar Ghosh, Souvik Kundu","submitted_at":"2026-05-29T21:07:27Z","abstract_excerpt":"The rapid growth in sizes of Large language models (LLMs) results in high compute and memory costs during inference. Quantization has been a significant pathway to addressing this challenge. In the quest to push the limits of quantization, weights, which are static, can often be quantized aggressively (e.g. 4 bits), while activations often require higher precision (e.g., 8 bits) to preserve accuracy, forcing hardware to operate with higher-precision datapaths. We leverage the statistical property that a significant fraction of activations are concentrated around zero, resulting in sparsity in "},"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":"2606.00365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-29T21:07:27Z","cross_cats_sorted":[],"title_canon_sha256":"6feeb80bf3f69044f17ac12bf4ef9c48cc8904811270dc9d6b9866b765b665cb","abstract_canon_sha256":"4a9ef354a408afc4a28b911e7b9f3870c84dfc0ed7de816ae14fd74cb45d6af6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:52.755518Z","signature_b64":"T8Y/3KjpXrXlXHVzeLGqlPbSunpDPINacg45dN2iMMJzIexHIa0uudA3hxOTezBCO25Vvj7XH24LGXbUEa4fCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66a2521e8f5fb28c12b7043c65d3847baa3f76a84c87f23fe2bc5b8c25380e84","last_reissued_at":"2026-06-02T01:03:52.755089Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:52.755089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Anand Raghunathan, Aradhana Mohan Parvathy, Arnab Raha, Deepak A. Mathaikutty, Shamik Kundu, Soumendu Kumar Ghosh, Souvik Kundu","submitted_at":"2026-05-29T21:07:27Z","abstract_excerpt":"The rapid growth in sizes of Large language models (LLMs) results in high compute and memory costs during inference. Quantization has been a significant pathway to addressing this challenge. In the quest to push the limits of quantization, weights, which are static, can often be quantized aggressively (e.g. 4 bits), while activations often require higher precision (e.g., 8 bits) to preserve accuracy, forcing hardware to operate with higher-precision datapaths. We leverage the statistical property that a significant fraction of activations are concentrated around zero, resulting in sparsity in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00365","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/2606.00365/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":"2606.00365","created_at":"2026-06-02T01:03:52.755147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00365v1","created_at":"2026-06-02T01:03:52.755147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00365","created_at":"2026-06-02T01:03:52.755147+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2RFEHUPL6ZI","created_at":"2026-06-02T01:03:52.755147+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2RFEHUPL6ZIYEVX","created_at":"2026-06-02T01:03:52.755147+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2RFEHUP","created_at":"2026-06-02T01:03:52.755147+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/M2RFEHUPL6ZIYEVXAQ6GLU4EPO","json":"https://pith.science/pith/M2RFEHUPL6ZIYEVXAQ6GLU4EPO.json","graph_json":"https://pith.science/api/pith-number/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/graph.json","events_json":"https://pith.science/api/pith-number/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/events.json","paper":"https://pith.science/paper/M2RFEHUP"},"agent_actions":{"view_html":"https://pith.science/pith/M2RFEHUPL6ZIYEVXAQ6GLU4EPO","download_json":"https://pith.science/pith/M2RFEHUPL6ZIYEVXAQ6GLU4EPO.json","view_paper":"https://pith.science/paper/M2RFEHUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00365&json=true","fetch_graph":"https://pith.science/api/pith-number/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/graph.json","fetch_events":"https://pith.science/api/pith-number/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/action/storage_attestation","attest_author":"https://pith.science/pith/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/action/author_attestation","sign_citation":"https://pith.science/pith/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/action/citation_signature","submit_replication":"https://pith.science/pith/M2RFEHUPL6ZIYEVXAQ6GLU4EPO/action/replication_record"}},"created_at":"2026-06-02T01:03:52.755147+00:00","updated_at":"2026-06-02T01:03:52.755147+00:00"}