{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4T6XCEZIN75JF24RC3MUURL6GZ","short_pith_number":"pith:4T6XCEZI","schema_version":"1.0","canonical_sha256":"e4fd7113286ffa92eb9116d94a457e3653665286ce15609536940205b8245330","source":{"kind":"arxiv","id":"2103.05363","version":1},"attestation_state":"computed","paper":{"title":"MWQ: Multiscale Wavelet Quantized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.CV","authors_text":"Fang Liu, Fanhua Shang, Licheng Jiao, Qigong Sun, Xiufang Li, Yan Ren","submitted_at":"2021-03-09T11:21:59Z","abstract_excerpt":"Model quantization can reduce the model size and computational latency, it has become an essential technique for the deployment of deep neural networks on resourceconstrained hardware (e.g., mobile phones and embedded devices). The existing quantization methods mainly consider the numerical elements of the weights and activation values, ignoring the relationship between elements. The decline of representation ability and information loss usually lead to the performance degradation. Inspired by the characteristics of images in the frequency domain, we propose a novel multiscale wavelet quantiza"},"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":"2103.05363","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-09T11:21:59Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"b8da45adc7851712fbdd106300eae85bb833711420a21d82e249141a96a27a86","abstract_canon_sha256":"3b9232b6b5e38e41715233f830f1aca3e2a242c0a1d86f30da68a090d197fab7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:25.377014Z","signature_b64":"+xuN9/5LgS6aWYvG2wqjRTqcZMHjwg1ayCl+mtklaoQ0muoJ7cvTPFmvK6n+buw9jWetd62fw/WbXdRkgQ0ECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4fd7113286ffa92eb9116d94a457e3653665286ce15609536940205b8245330","last_reissued_at":"2026-07-05T02:21:25.376602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:25.376602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MWQ: Multiscale Wavelet Quantized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.CV","authors_text":"Fang Liu, Fanhua Shang, Licheng Jiao, Qigong Sun, Xiufang Li, Yan Ren","submitted_at":"2021-03-09T11:21:59Z","abstract_excerpt":"Model quantization can reduce the model size and computational latency, it has become an essential technique for the deployment of deep neural networks on resourceconstrained hardware (e.g., mobile phones and embedded devices). The existing quantization methods mainly consider the numerical elements of the weights and activation values, ignoring the relationship between elements. The decline of representation ability and information loss usually lead to the performance degradation. Inspired by the characteristics of images in the frequency domain, we propose a novel multiscale wavelet quantiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05363","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/2103.05363/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":"2103.05363","created_at":"2026-07-05T02:21:25.376666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05363v1","created_at":"2026-07-05T02:21:25.376666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05363","created_at":"2026-07-05T02:21:25.376666+00:00"},{"alias_kind":"pith_short_12","alias_value":"4T6XCEZIN75J","created_at":"2026-07-05T02:21:25.376666+00:00"},{"alias_kind":"pith_short_16","alias_value":"4T6XCEZIN75JF24R","created_at":"2026-07-05T02:21:25.376666+00:00"},{"alias_kind":"pith_short_8","alias_value":"4T6XCEZI","created_at":"2026-07-05T02:21:25.376666+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/4T6XCEZIN75JF24RC3MUURL6GZ","json":"https://pith.science/pith/4T6XCEZIN75JF24RC3MUURL6GZ.json","graph_json":"https://pith.science/api/pith-number/4T6XCEZIN75JF24RC3MUURL6GZ/graph.json","events_json":"https://pith.science/api/pith-number/4T6XCEZIN75JF24RC3MUURL6GZ/events.json","paper":"https://pith.science/paper/4T6XCEZI"},"agent_actions":{"view_html":"https://pith.science/pith/4T6XCEZIN75JF24RC3MUURL6GZ","download_json":"https://pith.science/pith/4T6XCEZIN75JF24RC3MUURL6GZ.json","view_paper":"https://pith.science/paper/4T6XCEZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05363&json=true","fetch_graph":"https://pith.science/api/pith-number/4T6XCEZIN75JF24RC3MUURL6GZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4T6XCEZIN75JF24RC3MUURL6GZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4T6XCEZIN75JF24RC3MUURL6GZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4T6XCEZIN75JF24RC3MUURL6GZ/action/storage_attestation","attest_author":"https://pith.science/pith/4T6XCEZIN75JF24RC3MUURL6GZ/action/author_attestation","sign_citation":"https://pith.science/pith/4T6XCEZIN75JF24RC3MUURL6GZ/action/citation_signature","submit_replication":"https://pith.science/pith/4T6XCEZIN75JF24RC3MUURL6GZ/action/replication_record"}},"created_at":"2026-07-05T02:21:25.376666+00:00","updated_at":"2026-07-05T02:21:25.376666+00:00"}