{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZR47IK3YMTAKU34T43PRZU5IQ7","short_pith_number":"pith:ZR47IK3Y","schema_version":"1.0","canonical_sha256":"cc79f42b7864c0aa6f93e6df1cd3a887c4b60fb7b98a0ff55f4eb2427225e0f8","source":{"kind":"arxiv","id":"2606.13089","version":1},"attestation_state":"computed","paper":{"title":"Multi-Objective Coevolution of Prompts and Templates for Circuit Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Lukas Sekanina, Martin Tomasovic","submitted_at":"2026-06-11T09:14:37Z","abstract_excerpt":"Approximate multipliers deliberately relax computational accuracy to achieve gains in power efficiency, latency, and silicon area, which makes them well-suited for error-resilient applications such as neural networks. In this work, we introduce a co-evolutionary algorithm that leverages an off-the-shelf large language model (LLM) without requiring domain-specific training to automate the design of optimized 8-bit approximate multipliers. The approach simultaneously evolves a population of candidate circuits and a population of prompt templates that steer LLM-driven modifications. Experimental "},"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":"2606.13089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-06-11T09:14:37Z","cross_cats_sorted":[],"title_canon_sha256":"16d7d24edb8393380dc99cd670ba9d64c5a89ab9f1393fd2d2bd98085360d973","abstract_canon_sha256":"1ef2db1986d3c983b64cdbd15a6bee8246221091825a4ea85c89450c632787dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:39.746522Z","signature_b64":"sXgPjQ0iP2mgpF7LWfGi7I69zGQW7xJgLEuQWJyQcF2DsYOwCVSmtz8zsDWcuIgCcn+fcMgfT828+dH1KKGaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc79f42b7864c0aa6f93e6df1cd3a887c4b60fb7b98a0ff55f4eb2427225e0f8","last_reissued_at":"2026-06-12T01:09:39.746144Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:39.746144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Objective Coevolution of Prompts and Templates for Circuit Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Lukas Sekanina, Martin Tomasovic","submitted_at":"2026-06-11T09:14:37Z","abstract_excerpt":"Approximate multipliers deliberately relax computational accuracy to achieve gains in power efficiency, latency, and silicon area, which makes them well-suited for error-resilient applications such as neural networks. In this work, we introduce a co-evolutionary algorithm that leverages an off-the-shelf large language model (LLM) without requiring domain-specific training to automate the design of optimized 8-bit approximate multipliers. The approach simultaneously evolves a population of candidate circuits and a population of prompt templates that steer LLM-driven modifications. Experimental "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13089","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/2606.13089/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":"2606.13089","created_at":"2026-06-12T01:09:39.746201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13089v1","created_at":"2026-06-12T01:09:39.746201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13089","created_at":"2026-06-12T01:09:39.746201+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZR47IK3YMTAK","created_at":"2026-06-12T01:09:39.746201+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZR47IK3YMTAKU34T","created_at":"2026-06-12T01:09:39.746201+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZR47IK3Y","created_at":"2026-06-12T01:09:39.746201+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/ZR47IK3YMTAKU34T43PRZU5IQ7","json":"https://pith.science/pith/ZR47IK3YMTAKU34T43PRZU5IQ7.json","graph_json":"https://pith.science/api/pith-number/ZR47IK3YMTAKU34T43PRZU5IQ7/graph.json","events_json":"https://pith.science/api/pith-number/ZR47IK3YMTAKU34T43PRZU5IQ7/events.json","paper":"https://pith.science/paper/ZR47IK3Y"},"agent_actions":{"view_html":"https://pith.science/pith/ZR47IK3YMTAKU34T43PRZU5IQ7","download_json":"https://pith.science/pith/ZR47IK3YMTAKU34T43PRZU5IQ7.json","view_paper":"https://pith.science/paper/ZR47IK3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13089&json=true","fetch_graph":"https://pith.science/api/pith-number/ZR47IK3YMTAKU34T43PRZU5IQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZR47IK3YMTAKU34T43PRZU5IQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZR47IK3YMTAKU34T43PRZU5IQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZR47IK3YMTAKU34T43PRZU5IQ7/action/storage_attestation","attest_author":"https://pith.science/pith/ZR47IK3YMTAKU34T43PRZU5IQ7/action/author_attestation","sign_citation":"https://pith.science/pith/ZR47IK3YMTAKU34T43PRZU5IQ7/action/citation_signature","submit_replication":"https://pith.science/pith/ZR47IK3YMTAKU34T43PRZU5IQ7/action/replication_record"}},"created_at":"2026-06-12T01:09:39.746201+00:00","updated_at":"2026-06-12T01:09:39.746201+00:00"}