{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:D6KCL5NIFZEFL3HYD6OKT2LBWU","short_pith_number":"pith:D6KCL5NI","schema_version":"1.0","canonical_sha256":"1f9425f5a82e4855ecf81f9ca9e961b515c3249e6a6238f42a49aafc307f991d","source":{"kind":"arxiv","id":"1909.13063","version":3},"attestation_state":"computed","paper":{"title":"Training convolutional neural networks with cheap convolutions and online distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiao Xie, Linkai Luo, Shaohui Lin, Yichen Zhang","submitted_at":"2019-09-28T10:16:17Z","abstract_excerpt":"The large memory and computation consumption in convolutional neural networks (CNNs) has been one of the main barriers for deploying them on resource-limited systems. To this end, most cheap convolutions (e.g., group convolution, depth-wise convolution, and shift convolution) have recently been used for memory and computation reduction but with the specific architecture designing. Furthermore, it results in a low discriminability of the compressed networks by directly replacing the standard convolution with these cheap ones. In this paper, we propose to use knowledge distillation to improve th"},"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":"1909.13063","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-28T10:16:17Z","cross_cats_sorted":[],"title_canon_sha256":"cc77392566f08f76aa079db3b30f93dd8419fedcec9dc89896764ae2208c4da5","abstract_canon_sha256":"4ac20ff760bfabbf98965418ad81e35f819bea8dbcf80211b07b14639524bfc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:05.107040Z","signature_b64":"vPlgb5fHM2x1x9db7/hECjEOYJ833+cVCX4REbVMPYyfiLPnu4mnfJJybZ2gg3lgK5wTtlvQVF6eEW+sG3GUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f9425f5a82e4855ecf81f9ca9e961b515c3249e6a6238f42a49aafc307f991d","last_reissued_at":"2026-07-05T00:11:05.106654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:05.106654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training convolutional neural networks with cheap convolutions and online distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiao Xie, Linkai Luo, Shaohui Lin, Yichen Zhang","submitted_at":"2019-09-28T10:16:17Z","abstract_excerpt":"The large memory and computation consumption in convolutional neural networks (CNNs) has been one of the main barriers for deploying them on resource-limited systems. To this end, most cheap convolutions (e.g., group convolution, depth-wise convolution, and shift convolution) have recently been used for memory and computation reduction but with the specific architecture designing. Furthermore, it results in a low discriminability of the compressed networks by directly replacing the standard convolution with these cheap ones. In this paper, we propose to use knowledge distillation to improve th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13063","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/1909.13063/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":"1909.13063","created_at":"2026-07-05T00:11:05.106712+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.13063v3","created_at":"2026-07-05T00:11:05.106712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13063","created_at":"2026-07-05T00:11:05.106712+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6KCL5NIFZEF","created_at":"2026-07-05T00:11:05.106712+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6KCL5NIFZEFL3HY","created_at":"2026-07-05T00:11:05.106712+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6KCL5NI","created_at":"2026-07-05T00:11:05.106712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01462","citing_title":"Pan-infection Foundation Framework Enables Multiple Pathogen Prediction","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU","json":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU.json","graph_json":"https://pith.science/api/pith-number/D6KCL5NIFZEFL3HYD6OKT2LBWU/graph.json","events_json":"https://pith.science/api/pith-number/D6KCL5NIFZEFL3HYD6OKT2LBWU/events.json","paper":"https://pith.science/paper/D6KCL5NI"},"agent_actions":{"view_html":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU","download_json":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU.json","view_paper":"https://pith.science/paper/D6KCL5NI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.13063&json=true","fetch_graph":"https://pith.science/api/pith-number/D6KCL5NIFZEFL3HYD6OKT2LBWU/graph.json","fetch_events":"https://pith.science/api/pith-number/D6KCL5NIFZEFL3HYD6OKT2LBWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU/action/storage_attestation","attest_author":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU/action/author_attestation","sign_citation":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU/action/citation_signature","submit_replication":"https://pith.science/pith/D6KCL5NIFZEFL3HYD6OKT2LBWU/action/replication_record"}},"created_at":"2026-07-05T00:11:05.106712+00:00","updated_at":"2026-07-05T00:11:05.106712+00:00"}