{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EVE4G2P5G74CYKCP7Q3DA7TRR4","short_pith_number":"pith:EVE4G2P5","schema_version":"1.0","canonical_sha256":"2549c369fd37f82c284ffc36307e718f05d6f8317cf25b47005832c888aa70b6","source":{"kind":"arxiv","id":"2308.05600","version":1},"attestation_state":"computed","paper":{"title":"NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Arnaud Dapogny, Edouard Yvinec, Kevin Bailly","submitted_at":"2023-08-10T14:19:58Z","abstract_excerpt":"Deep neural network (DNN) deployment has been confined to larger hardware devices due to their expensive computational requirements. This challenge has recently reached another scale with the emergence of large language models (LLMs). In order to reduce both their memory footprint and latency, a promising technique is quantization. It consists in converting floating point representations to low bit-width fixed point representations, usually by assuming a uniform mapping onto a regular grid. This process, referred to in the literature as uniform quantization, may however be ill-suited as most D"},"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":"2308.05600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-10T14:19:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"af00f540cf4d5c75114d285f43ecea027efd799ab795990df667aa4b98277e60","abstract_canon_sha256":"262cf8d34fc0ab03f919ff2cf80116d962e7b413fe1a6aeb4d602d23f7bacf75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:02.884831Z","signature_b64":"eqpDnC/Er6DPRxl/6wm4Ry/+wsYC7lv7x3RB0hvsQGrF9oNRPLsI4JoD7huiVuZ+JuAiiIlBzadwD6nVtbz0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2549c369fd37f82c284ffc36307e718f05d6f8317cf25b47005832c888aa70b6","last_reissued_at":"2026-07-05T06:40:02.884389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:02.884389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Arnaud Dapogny, Edouard Yvinec, Kevin Bailly","submitted_at":"2023-08-10T14:19:58Z","abstract_excerpt":"Deep neural network (DNN) deployment has been confined to larger hardware devices due to their expensive computational requirements. This challenge has recently reached another scale with the emergence of large language models (LLMs). In order to reduce both their memory footprint and latency, a promising technique is quantization. It consists in converting floating point representations to low bit-width fixed point representations, usually by assuming a uniform mapping onto a regular grid. This process, referred to in the literature as uniform quantization, may however be ill-suited as most D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05600","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/2308.05600/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":"2308.05600","created_at":"2026-07-05T06:40:02.884454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.05600v1","created_at":"2026-07-05T06:40:02.884454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05600","created_at":"2026-07-05T06:40:02.884454+00:00"},{"alias_kind":"pith_short_12","alias_value":"EVE4G2P5G74C","created_at":"2026-07-05T06:40:02.884454+00:00"},{"alias_kind":"pith_short_16","alias_value":"EVE4G2P5G74CYKCP","created_at":"2026-07-05T06:40:02.884454+00:00"},{"alias_kind":"pith_short_8","alias_value":"EVE4G2P5","created_at":"2026-07-05T06:40:02.884454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04244","citing_title":"Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4","json":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4.json","graph_json":"https://pith.science/api/pith-number/EVE4G2P5G74CYKCP7Q3DA7TRR4/graph.json","events_json":"https://pith.science/api/pith-number/EVE4G2P5G74CYKCP7Q3DA7TRR4/events.json","paper":"https://pith.science/paper/EVE4G2P5"},"agent_actions":{"view_html":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4","download_json":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4.json","view_paper":"https://pith.science/paper/EVE4G2P5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.05600&json=true","fetch_graph":"https://pith.science/api/pith-number/EVE4G2P5G74CYKCP7Q3DA7TRR4/graph.json","fetch_events":"https://pith.science/api/pith-number/EVE4G2P5G74CYKCP7Q3DA7TRR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4/action/storage_attestation","attest_author":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4/action/author_attestation","sign_citation":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4/action/citation_signature","submit_replication":"https://pith.science/pith/EVE4G2P5G74CYKCP7Q3DA7TRR4/action/replication_record"}},"created_at":"2026-07-05T06:40:02.884454+00:00","updated_at":"2026-07-05T06:40:02.884454+00:00"}