{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5TMAFHCP3J3AKTDL5JJWLSTCB3","short_pith_number":"pith:5TMAFHCP","schema_version":"1.0","canonical_sha256":"ecd8029c4fda76054c6bea5365ca620ed7e1fcacd0d6253246df7c62462f6b82","source":{"kind":"arxiv","id":"2506.08785","version":1},"attestation_state":"computed","paper":{"title":"POLARON: Precision-aware On-device Learning and Adaptive Runtime-cONfigurable AI acceleration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CC","eess.IV"],"primary_cat":"cs.AR","authors_text":"Mukul Lokhande, Santosh Kumar Vishvakarma","submitted_at":"2025-06-10T13:33:02Z","abstract_excerpt":"The increasing complexity of AI models requires flexible hardware capable of supporting diverse precision formats, particularly for energy-constrained edge platforms. This work presents PARV-CE, a SIMD-enabled, multi-precision MAC engine that performs efficient multiply-accumulate operations using a unified data-path for 4/8/16-bit fixed-point, floating point, and posit formats. The architecture incorporates a layer adaptive precision strategy to align computational accuracy with workload sensitivity, optimizing both performance and energy usage. PARV-CE integrates quantization-aware execution"},"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":"2506.08785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-06-10T13:33:02Z","cross_cats_sorted":["cs.AI","cs.CC","eess.IV"],"title_canon_sha256":"d45ff40230b3ffd85e2ebfcb7b41def2a623403db3de4c48feff30cf8795c163","abstract_canon_sha256":"8299ef41d773220fe52183014c9c55db4e399de6741fcff740c6efe278e83c1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:13.177024Z","signature_b64":"Ka0Z8XGJf025JNKC+QWHYocBjB/muc9BzH3yK+wxMkDKYJow6I2q2TYqgOaUDKodW73fNzlpZsE50a0eMUSgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecd8029c4fda76054c6bea5365ca620ed7e1fcacd0d6253246df7c62462f6b82","last_reissued_at":"2026-07-05T11:19:13.176563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:13.176563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POLARON: Precision-aware On-device Learning and Adaptive Runtime-cONfigurable AI acceleration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CC","eess.IV"],"primary_cat":"cs.AR","authors_text":"Mukul Lokhande, Santosh Kumar Vishvakarma","submitted_at":"2025-06-10T13:33:02Z","abstract_excerpt":"The increasing complexity of AI models requires flexible hardware capable of supporting diverse precision formats, particularly for energy-constrained edge platforms. This work presents PARV-CE, a SIMD-enabled, multi-precision MAC engine that performs efficient multiply-accumulate operations using a unified data-path for 4/8/16-bit fixed-point, floating point, and posit formats. The architecture incorporates a layer adaptive precision strategy to align computational accuracy with workload sensitivity, optimizing both performance and energy usage. PARV-CE integrates quantization-aware execution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08785","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/2506.08785/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":"2506.08785","created_at":"2026-07-05T11:19:13.176615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08785v1","created_at":"2026-07-05T11:19:13.176615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08785","created_at":"2026-07-05T11:19:13.176615+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TMAFHCP3J3A","created_at":"2026-07-05T11:19:13.176615+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TMAFHCP3J3AKTDL","created_at":"2026-07-05T11:19:13.176615+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TMAFHCP","created_at":"2026-07-05T11:19:13.176615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.16703","citing_title":"ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3","json":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3.json","graph_json":"https://pith.science/api/pith-number/5TMAFHCP3J3AKTDL5JJWLSTCB3/graph.json","events_json":"https://pith.science/api/pith-number/5TMAFHCP3J3AKTDL5JJWLSTCB3/events.json","paper":"https://pith.science/paper/5TMAFHCP"},"agent_actions":{"view_html":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3","download_json":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3.json","view_paper":"https://pith.science/paper/5TMAFHCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08785&json=true","fetch_graph":"https://pith.science/api/pith-number/5TMAFHCP3J3AKTDL5JJWLSTCB3/graph.json","fetch_events":"https://pith.science/api/pith-number/5TMAFHCP3J3AKTDL5JJWLSTCB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3/action/storage_attestation","attest_author":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3/action/author_attestation","sign_citation":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3/action/citation_signature","submit_replication":"https://pith.science/pith/5TMAFHCP3J3AKTDL5JJWLSTCB3/action/replication_record"}},"created_at":"2026-07-05T11:19:13.176615+00:00","updated_at":"2026-07-05T11:19:13.176615+00:00"}