{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TS2HCLT6HAXROCN5BSGCUXOR4H","short_pith_number":"pith:TS2HCLT6","schema_version":"1.0","canonical_sha256":"9cb4712e7e382f1709bd0c8c2a5dd1e1d0c2b59d393fdc0e73bf431be3e0f2e4","source":{"kind":"arxiv","id":"2506.21371","version":1},"attestation_state":"computed","paper":{"title":"MAx-DNN: Multi-Level Arithmetic Approximation for Energy-Efficient DNN Hardware Accelerators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Dimitrios Soudris, Georgios Makris, Kiamal Pekmestzi, Sotirios Xydis, Vasileios Leon","submitted_at":"2025-06-26T15:21:12Z","abstract_excerpt":"Nowadays, the rapid growth of Deep Neural Network (DNN) architectures has established them as the defacto approach for providing advanced Machine Learning tasks with excellent accuracy. Targeting low-power DNN computing, this paper examines the interplay of fine-grained error resilience of DNN workloads in collaboration with hardware approximation techniques, to achieve higher levels of energy efficiency. Utilizing the state-of-the-art ROUP approximate multipliers, we systematically explore their fine-grained distribution across the network according to our layer-, filter-, and kernel-level ap"},"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":"2506.21371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T15:21:12Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"15bdf1c12f6a3146f142a1a41643812887b34980aa5baf8571a67af44481188e","abstract_canon_sha256":"6c453147204382b0d36465e827e6befb294b0e77efc62ddcd39641bf8544b2cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:44.600732Z","signature_b64":"1loU3+Hv2q5yQ8fAm1XRhnqmFTNGeI17ZBqNvcRyUmSHU17xtCNOmTAYEYyBLJAkAiomH+Yp2Z8YTkz6+D/6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cb4712e7e382f1709bd0c8c2a5dd1e1d0c2b59d393fdc0e73bf431be3e0f2e4","last_reissued_at":"2026-07-05T11:27:44.600206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:44.600206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAx-DNN: Multi-Level Arithmetic Approximation for Energy-Efficient DNN Hardware Accelerators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Dimitrios Soudris, Georgios Makris, Kiamal Pekmestzi, Sotirios Xydis, Vasileios Leon","submitted_at":"2025-06-26T15:21:12Z","abstract_excerpt":"Nowadays, the rapid growth of Deep Neural Network (DNN) architectures has established them as the defacto approach for providing advanced Machine Learning tasks with excellent accuracy. Targeting low-power DNN computing, this paper examines the interplay of fine-grained error resilience of DNN workloads in collaboration with hardware approximation techniques, to achieve higher levels of energy efficiency. Utilizing the state-of-the-art ROUP approximate multipliers, we systematically explore their fine-grained distribution across the network according to our layer-, filter-, and kernel-level ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21371","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/2506.21371/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":"2506.21371","created_at":"2026-07-05T11:27:44.600269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21371v1","created_at":"2026-07-05T11:27:44.600269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21371","created_at":"2026-07-05T11:27:44.600269+00:00"},{"alias_kind":"pith_short_12","alias_value":"TS2HCLT6HAXR","created_at":"2026-07-05T11:27:44.600269+00:00"},{"alias_kind":"pith_short_16","alias_value":"TS2HCLT6HAXROCN5","created_at":"2026-07-05T11:27:44.600269+00:00"},{"alias_kind":"pith_short_8","alias_value":"TS2HCLT6","created_at":"2026-07-05T11:27:44.600269+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/TS2HCLT6HAXROCN5BSGCUXOR4H","json":"https://pith.science/pith/TS2HCLT6HAXROCN5BSGCUXOR4H.json","graph_json":"https://pith.science/api/pith-number/TS2HCLT6HAXROCN5BSGCUXOR4H/graph.json","events_json":"https://pith.science/api/pith-number/TS2HCLT6HAXROCN5BSGCUXOR4H/events.json","paper":"https://pith.science/paper/TS2HCLT6"},"agent_actions":{"view_html":"https://pith.science/pith/TS2HCLT6HAXROCN5BSGCUXOR4H","download_json":"https://pith.science/pith/TS2HCLT6HAXROCN5BSGCUXOR4H.json","view_paper":"https://pith.science/paper/TS2HCLT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21371&json=true","fetch_graph":"https://pith.science/api/pith-number/TS2HCLT6HAXROCN5BSGCUXOR4H/graph.json","fetch_events":"https://pith.science/api/pith-number/TS2HCLT6HAXROCN5BSGCUXOR4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TS2HCLT6HAXROCN5BSGCUXOR4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TS2HCLT6HAXROCN5BSGCUXOR4H/action/storage_attestation","attest_author":"https://pith.science/pith/TS2HCLT6HAXROCN5BSGCUXOR4H/action/author_attestation","sign_citation":"https://pith.science/pith/TS2HCLT6HAXROCN5BSGCUXOR4H/action/citation_signature","submit_replication":"https://pith.science/pith/TS2HCLT6HAXROCN5BSGCUXOR4H/action/replication_record"}},"created_at":"2026-07-05T11:27:44.600269+00:00","updated_at":"2026-07-05T11:27:44.600269+00:00"}