{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:553WQC62UWEIITUFDHKO3UAXRO","short_pith_number":"pith:553WQC62","schema_version":"1.0","canonical_sha256":"ef77680bdaa588844e8519d4edd0178b86c54821a40f458b21adf88db1ae4986","source":{"kind":"arxiv","id":"2502.01303","version":1},"attestation_state":"computed","paper":{"title":"Partial Channel Network: Compute Fewer, Perform Better","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiduo Huang, Pengju Ren, Tian Xia, Wenzhe Zhao","submitted_at":"2025-02-03T12:26:55Z","abstract_excerpt":"Designing a module or mechanism that enables a network to maintain low parameters and FLOPs without sacrificing accuracy and throughput remains a challenge. To address this challenge and exploit the redundancy within feature map channels, we propose a new solution: partial channel mechanism (PCM). Specifically, through the split operation, the feature map channels are divided into different parts, with each part corresponding to different operations, such as convolution, attention, pooling, and identity mapping. Based on this assumption, we introduce a novel partial attention convolution (PATC"},"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":"2502.01303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T12:26:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e4f982a4b0267521fc442feba58d89a57e9893685df8d12a403f7518d45be33","abstract_canon_sha256":"9aaa763b9dc4189bd579121d430285a3b477b425ec727dda98d96c9c5ab693ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:45.529911Z","signature_b64":"UUDfV240W6AjR0xdDQmgxOO9YytBjEX7Ci6tWl+1lGcvj81+G56sUC9WMBa9Wf9rSWw3owfNqphUk7u06oobAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef77680bdaa588844e8519d4edd0178b86c54821a40f458b21adf88db1ae4986","last_reissued_at":"2026-07-05T10:08:45.529515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:45.529515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Partial Channel Network: Compute Fewer, Perform Better","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiduo Huang, Pengju Ren, Tian Xia, Wenzhe Zhao","submitted_at":"2025-02-03T12:26:55Z","abstract_excerpt":"Designing a module or mechanism that enables a network to maintain low parameters and FLOPs without sacrificing accuracy and throughput remains a challenge. To address this challenge and exploit the redundancy within feature map channels, we propose a new solution: partial channel mechanism (PCM). Specifically, through the split operation, the feature map channels are divided into different parts, with each part corresponding to different operations, such as convolution, attention, pooling, and identity mapping. Based on this assumption, we introduce a novel partial attention convolution (PATC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01303","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/2502.01303/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":"2502.01303","created_at":"2026-07-05T10:08:45.529575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01303v1","created_at":"2026-07-05T10:08:45.529575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01303","created_at":"2026-07-05T10:08:45.529575+00:00"},{"alias_kind":"pith_short_12","alias_value":"553WQC62UWEI","created_at":"2026-07-05T10:08:45.529575+00:00"},{"alias_kind":"pith_short_16","alias_value":"553WQC62UWEIITUF","created_at":"2026-07-05T10:08:45.529575+00:00"},{"alias_kind":"pith_short_8","alias_value":"553WQC62","created_at":"2026-07-05T10:08:45.529575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05176","citing_title":"FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO","json":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO.json","graph_json":"https://pith.science/api/pith-number/553WQC62UWEIITUFDHKO3UAXRO/graph.json","events_json":"https://pith.science/api/pith-number/553WQC62UWEIITUFDHKO3UAXRO/events.json","paper":"https://pith.science/paper/553WQC62"},"agent_actions":{"view_html":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO","download_json":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO.json","view_paper":"https://pith.science/paper/553WQC62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01303&json=true","fetch_graph":"https://pith.science/api/pith-number/553WQC62UWEIITUFDHKO3UAXRO/graph.json","fetch_events":"https://pith.science/api/pith-number/553WQC62UWEIITUFDHKO3UAXRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO/action/storage_attestation","attest_author":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO/action/author_attestation","sign_citation":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO/action/citation_signature","submit_replication":"https://pith.science/pith/553WQC62UWEIITUFDHKO3UAXRO/action/replication_record"}},"created_at":"2026-07-05T10:08:45.529575+00:00","updated_at":"2026-07-05T10:08:45.529575+00:00"}