{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AY5QQD5757SFQKK2T2IRICFEUE","short_pith_number":"pith:AY5QQD57","schema_version":"1.0","canonical_sha256":"063b080fbfefe458295a9e911408a4a12addf59333562edca98070117971ddbc","source":{"kind":"arxiv","id":"2101.06686","version":1},"attestation_state":"computed","paper":{"title":"KCP: Kernel Cluster Pruning for Dense Labeling Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Liang-Gee Chen, Po-Hsiang Yu, Sih-Sian Wu","submitted_at":"2021-01-17T14:59:00Z","abstract_excerpt":"Pruning has become a promising technique used to compress and accelerate neural networks. Existing methods are mainly evaluated on spare labeling applications. However, dense labeling applications are those closer to real world problems that require real-time processing on resource-constrained mobile devices. Pruning for dense labeling applications is still a largely unexplored field. The prevailing filter channel pruning method removes the entire filter channel. Accordingly, the interaction between each kernel in one filter channel is ignored.\n  In this study, we proposed kernel cluster pruni"},"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":"2101.06686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-17T14:59:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1857c5ade06ad2919b1ef1ff6e3a8204360666031b37fc977c9cb4c7f9066810","abstract_canon_sha256":"fc17d3a453f9cf56810cc9110048a4c44d81f787c0d6ef2a04b063920d614292"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:36.263063Z","signature_b64":"YhzTxW7KxFW3AVofoC4/g/f/EQY5sZiiQ/ouWP/JYHiF/AKh0dJNB+beZC8YG1hXyF0YJ8SHteB1+/wC9mh0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"063b080fbfefe458295a9e911408a4a12addf59333562edca98070117971ddbc","last_reissued_at":"2026-07-05T02:07:36.262633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:36.262633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KCP: Kernel Cluster Pruning for Dense Labeling Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Liang-Gee Chen, Po-Hsiang Yu, Sih-Sian Wu","submitted_at":"2021-01-17T14:59:00Z","abstract_excerpt":"Pruning has become a promising technique used to compress and accelerate neural networks. Existing methods are mainly evaluated on spare labeling applications. However, dense labeling applications are those closer to real world problems that require real-time processing on resource-constrained mobile devices. Pruning for dense labeling applications is still a largely unexplored field. The prevailing filter channel pruning method removes the entire filter channel. Accordingly, the interaction between each kernel in one filter channel is ignored.\n  In this study, we proposed kernel cluster pruni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06686","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/2101.06686/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":"2101.06686","created_at":"2026-07-05T02:07:36.262687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.06686v1","created_at":"2026-07-05T02:07:36.262687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06686","created_at":"2026-07-05T02:07:36.262687+00:00"},{"alias_kind":"pith_short_12","alias_value":"AY5QQD5757SF","created_at":"2026-07-05T02:07:36.262687+00:00"},{"alias_kind":"pith_short_16","alias_value":"AY5QQD5757SFQKK2","created_at":"2026-07-05T02:07:36.262687+00:00"},{"alias_kind":"pith_short_8","alias_value":"AY5QQD57","created_at":"2026-07-05T02:07:36.262687+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/AY5QQD5757SFQKK2T2IRICFEUE","json":"https://pith.science/pith/AY5QQD5757SFQKK2T2IRICFEUE.json","graph_json":"https://pith.science/api/pith-number/AY5QQD5757SFQKK2T2IRICFEUE/graph.json","events_json":"https://pith.science/api/pith-number/AY5QQD5757SFQKK2T2IRICFEUE/events.json","paper":"https://pith.science/paper/AY5QQD57"},"agent_actions":{"view_html":"https://pith.science/pith/AY5QQD5757SFQKK2T2IRICFEUE","download_json":"https://pith.science/pith/AY5QQD5757SFQKK2T2IRICFEUE.json","view_paper":"https://pith.science/paper/AY5QQD57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.06686&json=true","fetch_graph":"https://pith.science/api/pith-number/AY5QQD5757SFQKK2T2IRICFEUE/graph.json","fetch_events":"https://pith.science/api/pith-number/AY5QQD5757SFQKK2T2IRICFEUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AY5QQD5757SFQKK2T2IRICFEUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AY5QQD5757SFQKK2T2IRICFEUE/action/storage_attestation","attest_author":"https://pith.science/pith/AY5QQD5757SFQKK2T2IRICFEUE/action/author_attestation","sign_citation":"https://pith.science/pith/AY5QQD5757SFQKK2T2IRICFEUE/action/citation_signature","submit_replication":"https://pith.science/pith/AY5QQD5757SFQKK2T2IRICFEUE/action/replication_record"}},"created_at":"2026-07-05T02:07:36.262687+00:00","updated_at":"2026-07-05T02:07:36.262687+00:00"}