{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IDBJH6SNWY4JJBN7KZVZJHLLNL","short_pith_number":"pith:IDBJH6SN","schema_version":"1.0","canonical_sha256":"40c293fa4db6389485bf566b949d6b6ad1454a000fddacf782479b9f1f2ad95d","source":{"kind":"arxiv","id":"1908.05867","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jingyu Li, Ping Luo, Ruimao Zhang, Wenqi Shao, Xiaogang Wang, Zhanglin Peng, Zhaoyang Zhang","submitted_at":"2019-08-16T06:50:33Z","abstract_excerpt":"Group convolution, which divides the channels of ConvNets into groups, has achieved impressive improvement over the regular convolution operation. However, existing models, eg. ResNeXt, still suffers from the sub-optimal performance due to manually defining the number of groups as a constant over all of the layers. Toward addressing this issue, we present Groupable ConvNet (GroupNet) built by using a novel dynamic grouping convolution (DGConv) operation, which is able to learn the number of groups in an end-to-end manner. The proposed approach has several appealing benefits. (1) DGConv provide"},"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":"1908.05867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-16T06:50:33Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"93ed8493852fb047cbc3ec9616ab65421e8adfbd3b77ad2f2995f64a623da1c3","abstract_canon_sha256":"517faa17fcede70e51733d19400b8aa76f3aa7f2a51bb4cc432b1ec15a905d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:12.084888Z","signature_b64":"tR7W65XgLvuSPrCCUxidQzk6ANOFPSbm2gBmtPFGKwv8/Ebp74if8BErurmkIFQRF2+qRt191Qxw9iaZm54CCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40c293fa4db6389485bf566b949d6b6ad1454a000fddacf782479b9f1f2ad95d","last_reissued_at":"2026-07-04T23:58:12.084564Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:12.084564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jingyu Li, Ping Luo, Ruimao Zhang, Wenqi Shao, Xiaogang Wang, Zhanglin Peng, Zhaoyang Zhang","submitted_at":"2019-08-16T06:50:33Z","abstract_excerpt":"Group convolution, which divides the channels of ConvNets into groups, has achieved impressive improvement over the regular convolution operation. However, existing models, eg. ResNeXt, still suffers from the sub-optimal performance due to manually defining the number of groups as a constant over all of the layers. Toward addressing this issue, we present Groupable ConvNet (GroupNet) built by using a novel dynamic grouping convolution (DGConv) operation, which is able to learn the number of groups in an end-to-end manner. The proposed approach has several appealing benefits. (1) DGConv provide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05867","kind":"arxiv","version":2},"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/1908.05867/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":"1908.05867","created_at":"2026-07-04T23:58:12.084612+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05867v2","created_at":"2026-07-04T23:58:12.084612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05867","created_at":"2026-07-04T23:58:12.084612+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDBJH6SNWY4J","created_at":"2026-07-04T23:58:12.084612+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDBJH6SNWY4JJBN7","created_at":"2026-07-04T23:58:12.084612+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDBJH6SN","created_at":"2026-07-04T23:58:12.084612+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/IDBJH6SNWY4JJBN7KZVZJHLLNL","json":"https://pith.science/pith/IDBJH6SNWY4JJBN7KZVZJHLLNL.json","graph_json":"https://pith.science/api/pith-number/IDBJH6SNWY4JJBN7KZVZJHLLNL/graph.json","events_json":"https://pith.science/api/pith-number/IDBJH6SNWY4JJBN7KZVZJHLLNL/events.json","paper":"https://pith.science/paper/IDBJH6SN"},"agent_actions":{"view_html":"https://pith.science/pith/IDBJH6SNWY4JJBN7KZVZJHLLNL","download_json":"https://pith.science/pith/IDBJH6SNWY4JJBN7KZVZJHLLNL.json","view_paper":"https://pith.science/paper/IDBJH6SN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05867&json=true","fetch_graph":"https://pith.science/api/pith-number/IDBJH6SNWY4JJBN7KZVZJHLLNL/graph.json","fetch_events":"https://pith.science/api/pith-number/IDBJH6SNWY4JJBN7KZVZJHLLNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDBJH6SNWY4JJBN7KZVZJHLLNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDBJH6SNWY4JJBN7KZVZJHLLNL/action/storage_attestation","attest_author":"https://pith.science/pith/IDBJH6SNWY4JJBN7KZVZJHLLNL/action/author_attestation","sign_citation":"https://pith.science/pith/IDBJH6SNWY4JJBN7KZVZJHLLNL/action/citation_signature","submit_replication":"https://pith.science/pith/IDBJH6SNWY4JJBN7KZVZJHLLNL/action/replication_record"}},"created_at":"2026-07-04T23:58:12.084612+00:00","updated_at":"2026-07-04T23:58:12.084612+00:00"}