{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z3ZZDOLO73G4FPXUNEPECLFNDH","short_pith_number":"pith:Z3ZZDOLO","schema_version":"1.0","canonical_sha256":"cef391b96efecdc2bef4691e412cad19f39ea5f6cbcf81a58e16a973ef6b446d","source":{"kind":"arxiv","id":"2206.00843","version":3},"attestation_state":"computed","paper":{"title":"DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng Wan, Haichuan Yang, Jiayi Yuan, Meng Li, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Celine Lin, Yonggan Fu","submitted_at":"2022-06-02T02:32:47Z","abstract_excerpt":"Efficient deep neural network (DNN) models equipped with compact operators (e.g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e.g., the total number of weights/operations) while maintaining a decent model accuracy. However, existing efficient DNNs are still limited in fulfilling their promise in boosting real-hardware efficiency, due to their commonly adopted compact operators' low hardware utilization. In this work, we open up a new compression paradigm for developing real-hardware efficient DNNs, leading to boosted hardware efficiency while ma"},"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":"2206.00843","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T02:32:47Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"91293b1e74770e9ea9de45d6719aed392cee003d3e2b34960eb3498732bd8c47","abstract_canon_sha256":"b1468bfbffc41aae91dcd30c8c73a905cee22378de0b12cd41edbc66da6d2f71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:45.718018Z","signature_b64":"8BF10HjprXD7B7QaBmKXDTJLxO+GhB661C89UClpTyyJeqjaZG8Rb4a81k+vbd/txYb95GEwH6eYEenpZ/sACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef391b96efecdc2bef4691e412cad19f39ea5f6cbcf81a58e16a973ef6b446d","last_reissued_at":"2026-07-05T09:56:45.717497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:45.717497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng Wan, Haichuan Yang, Jiayi Yuan, Meng Li, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Celine Lin, Yonggan Fu","submitted_at":"2022-06-02T02:32:47Z","abstract_excerpt":"Efficient deep neural network (DNN) models equipped with compact operators (e.g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e.g., the total number of weights/operations) while maintaining a decent model accuracy. However, existing efficient DNNs are still limited in fulfilling their promise in boosting real-hardware efficiency, due to their commonly adopted compact operators' low hardware utilization. In this work, we open up a new compression paradigm for developing real-hardware efficient DNNs, leading to boosted hardware efficiency while ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00843","kind":"arxiv","version":3},"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/2206.00843/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":"2206.00843","created_at":"2026-07-05T09:56:45.717560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00843v3","created_at":"2026-07-05T09:56:45.717560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00843","created_at":"2026-07-05T09:56:45.717560+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3ZZDOLO73G4","created_at":"2026-07-05T09:56:45.717560+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3ZZDOLO73G4FPXU","created_at":"2026-07-05T09:56:45.717560+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3ZZDOLO","created_at":"2026-07-05T09:56:45.717560+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/Z3ZZDOLO73G4FPXUNEPECLFNDH","json":"https://pith.science/pith/Z3ZZDOLO73G4FPXUNEPECLFNDH.json","graph_json":"https://pith.science/api/pith-number/Z3ZZDOLO73G4FPXUNEPECLFNDH/graph.json","events_json":"https://pith.science/api/pith-number/Z3ZZDOLO73G4FPXUNEPECLFNDH/events.json","paper":"https://pith.science/paper/Z3ZZDOLO"},"agent_actions":{"view_html":"https://pith.science/pith/Z3ZZDOLO73G4FPXUNEPECLFNDH","download_json":"https://pith.science/pith/Z3ZZDOLO73G4FPXUNEPECLFNDH.json","view_paper":"https://pith.science/paper/Z3ZZDOLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00843&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3ZZDOLO73G4FPXUNEPECLFNDH/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3ZZDOLO73G4FPXUNEPECLFNDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3ZZDOLO73G4FPXUNEPECLFNDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3ZZDOLO73G4FPXUNEPECLFNDH/action/storage_attestation","attest_author":"https://pith.science/pith/Z3ZZDOLO73G4FPXUNEPECLFNDH/action/author_attestation","sign_citation":"https://pith.science/pith/Z3ZZDOLO73G4FPXUNEPECLFNDH/action/citation_signature","submit_replication":"https://pith.science/pith/Z3ZZDOLO73G4FPXUNEPECLFNDH/action/replication_record"}},"created_at":"2026-07-05T09:56:45.717560+00:00","updated_at":"2026-07-05T09:56:45.717560+00:00"}