{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CMIZ3ZR472L2RJNLUIQARLBPXQ","short_pith_number":"pith:CMIZ3ZR4","schema_version":"1.0","canonical_sha256":"13119de63cfe97a8a5aba22008ac2fbc07ab807813698ac32eaa55696e7df281","source":{"kind":"arxiv","id":"2110.03858","version":1},"attestation_state":"computed","paper":{"title":"ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongbing Zhao, Haoran Li, Jiaqi Li, Mingjun Ma, Nannan Li, Yaran Chen, Zicheng Duan, Zixiang Ding","submitted_at":"2021-10-08T02:15:49Z","abstract_excerpt":"Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of the traditional rule-based network pruning methods can not reach a sufficient compression ratio with low accuracy loss and are time-consuming as well as laborious. In this paper, we propose Automatic Block-wise and Channel-wise Network Pruning (ABCP) to jointly search the block-wise and channel-wise pruning action with deep reinforcement learning. A joint sample algorithm is pr"},"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":"2110.03858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-08T02:15:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b17144f8de978efe605742ca4368df00914c8ce31cc642c8ed2c2957095757c8","abstract_canon_sha256":"ee18d4173bebc07b1126b1807441768a4bcd2c729250a45bc0bc0ffb32b99e0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:48.005378Z","signature_b64":"6dGrMRz842Ub6eHNka0Kzrf5aHejPrfXfWduNcVghTdcTk5613NY8m0vR4YUV8bN7bmp5NF5X7ZipS2Due6rCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13119de63cfe97a8a5aba22008ac2fbc07ab807813698ac32eaa55696e7df281","last_reissued_at":"2026-07-05T03:20:48.004887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:48.004887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongbing Zhao, Haoran Li, Jiaqi Li, Mingjun Ma, Nannan Li, Yaran Chen, Zicheng Duan, Zixiang Ding","submitted_at":"2021-10-08T02:15:49Z","abstract_excerpt":"Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of the traditional rule-based network pruning methods can not reach a sufficient compression ratio with low accuracy loss and are time-consuming as well as laborious. In this paper, we propose Automatic Block-wise and Channel-wise Network Pruning (ABCP) to jointly search the block-wise and channel-wise pruning action with deep reinforcement learning. A joint sample algorithm is pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03858","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/2110.03858/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":"2110.03858","created_at":"2026-07-05T03:20:48.004941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03858v1","created_at":"2026-07-05T03:20:48.004941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03858","created_at":"2026-07-05T03:20:48.004941+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMIZ3ZR472L2","created_at":"2026-07-05T03:20:48.004941+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMIZ3ZR472L2RJNL","created_at":"2026-07-05T03:20:48.004941+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMIZ3ZR4","created_at":"2026-07-05T03:20:48.004941+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/CMIZ3ZR472L2RJNLUIQARLBPXQ","json":"https://pith.science/pith/CMIZ3ZR472L2RJNLUIQARLBPXQ.json","graph_json":"https://pith.science/api/pith-number/CMIZ3ZR472L2RJNLUIQARLBPXQ/graph.json","events_json":"https://pith.science/api/pith-number/CMIZ3ZR472L2RJNLUIQARLBPXQ/events.json","paper":"https://pith.science/paper/CMIZ3ZR4"},"agent_actions":{"view_html":"https://pith.science/pith/CMIZ3ZR472L2RJNLUIQARLBPXQ","download_json":"https://pith.science/pith/CMIZ3ZR472L2RJNLUIQARLBPXQ.json","view_paper":"https://pith.science/paper/CMIZ3ZR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03858&json=true","fetch_graph":"https://pith.science/api/pith-number/CMIZ3ZR472L2RJNLUIQARLBPXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CMIZ3ZR472L2RJNLUIQARLBPXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMIZ3ZR472L2RJNLUIQARLBPXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMIZ3ZR472L2RJNLUIQARLBPXQ/action/storage_attestation","attest_author":"https://pith.science/pith/CMIZ3ZR472L2RJNLUIQARLBPXQ/action/author_attestation","sign_citation":"https://pith.science/pith/CMIZ3ZR472L2RJNLUIQARLBPXQ/action/citation_signature","submit_replication":"https://pith.science/pith/CMIZ3ZR472L2RJNLUIQARLBPXQ/action/replication_record"}},"created_at":"2026-07-05T03:20:48.004941+00:00","updated_at":"2026-07-05T03:20:48.004941+00:00"}