{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LS7USMMZMIMEP5ZJYFNJFRSE6X","short_pith_number":"pith:LS7USMMZ","schema_version":"1.0","canonical_sha256":"5cbf493199621847f729c15a92c644f5e310bd11c564b2398275f8b76f2fa3df","source":{"kind":"arxiv","id":"2408.13617","version":1},"attestation_state":"computed","paper":{"title":"SiTe CiM: Signed Ternary Computing-in-Memory for Ultra-Low Precision Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Akul Malhotra, Anand Raghunathan, Niharika Thakuria, Reena Elangovan, Sandeep K. Thirumala, Sumeet K. Gupta","submitted_at":"2024-08-24T16:10:33Z","abstract_excerpt":"Ternary Deep Neural Networks (DNN) have shown a large potential for highly energy-constrained systems by virtue of their low power operation (due to ultra-low precision) with only a mild degradation in accuracy. To enable an energy-efficient hardware substrate for such systems, we propose a compute-enabled memory design, referred to as SiTe-CiM, which features computing-in-memory (CiM) of dot products between signed ternary (SiTe) inputs and weights. SiTe CiM is based on cross-coupling of two bit cells to enable CiM of dot products in the signed ternary regime. We explore SiTe CiM with 8T-SRAM"},"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":"2408.13617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AR","submitted_at":"2024-08-24T16:10:33Z","cross_cats_sorted":[],"title_canon_sha256":"fd9f40eac5ccba9f6a59dd10f036b8570198f9acb576ccf0499552468d208ef5","abstract_canon_sha256":"1545876e77489ec917ca611c1789a933d353138755a9baafdd51456b4a9dd309"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:53.083724Z","signature_b64":"p1d6bWcj8aJm3NCGygU0jaYPgtXgxTtiz3cdMkqD4s4XFakjrRTPYdNkP9PKNxg+12yJCN4DuMQvfum5FIhPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cbf493199621847f729c15a92c644f5e310bd11c564b2398275f8b76f2fa3df","last_reissued_at":"2026-07-05T08:58:53.083240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:53.083240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SiTe CiM: Signed Ternary Computing-in-Memory for Ultra-Low Precision Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Akul Malhotra, Anand Raghunathan, Niharika Thakuria, Reena Elangovan, Sandeep K. Thirumala, Sumeet K. Gupta","submitted_at":"2024-08-24T16:10:33Z","abstract_excerpt":"Ternary Deep Neural Networks (DNN) have shown a large potential for highly energy-constrained systems by virtue of their low power operation (due to ultra-low precision) with only a mild degradation in accuracy. To enable an energy-efficient hardware substrate for such systems, we propose a compute-enabled memory design, referred to as SiTe-CiM, which features computing-in-memory (CiM) of dot products between signed ternary (SiTe) inputs and weights. SiTe CiM is based on cross-coupling of two bit cells to enable CiM of dot products in the signed ternary regime. We explore SiTe CiM with 8T-SRAM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13617","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/2408.13617/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":"2408.13617","created_at":"2026-07-05T08:58:53.083302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13617v1","created_at":"2026-07-05T08:58:53.083302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13617","created_at":"2026-07-05T08:58:53.083302+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS7USMMZMIME","created_at":"2026-07-05T08:58:53.083302+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS7USMMZMIMEP5ZJ","created_at":"2026-07-05T08:58:53.083302+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS7USMMZ","created_at":"2026-07-05T08:58:53.083302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04483","citing_title":"STRIDe: Cross-Coupled STT-MRAM Enabling Robust In-Memory-Computing for Deep Neural Network Accelerators","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X","json":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X.json","graph_json":"https://pith.science/api/pith-number/LS7USMMZMIMEP5ZJYFNJFRSE6X/graph.json","events_json":"https://pith.science/api/pith-number/LS7USMMZMIMEP5ZJYFNJFRSE6X/events.json","paper":"https://pith.science/paper/LS7USMMZ"},"agent_actions":{"view_html":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X","download_json":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X.json","view_paper":"https://pith.science/paper/LS7USMMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13617&json=true","fetch_graph":"https://pith.science/api/pith-number/LS7USMMZMIMEP5ZJYFNJFRSE6X/graph.json","fetch_events":"https://pith.science/api/pith-number/LS7USMMZMIMEP5ZJYFNJFRSE6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X/action/storage_attestation","attest_author":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X/action/author_attestation","sign_citation":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X/action/citation_signature","submit_replication":"https://pith.science/pith/LS7USMMZMIMEP5ZJYFNJFRSE6X/action/replication_record"}},"created_at":"2026-07-05T08:58:53.083302+00:00","updated_at":"2026-07-05T08:58:53.083302+00:00"}