{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JFBZJPKA6AOY7R7BAY3P7ZPTBS","short_pith_number":"pith:JFBZJPKA","schema_version":"1.0","canonical_sha256":"494394bd40f01d8fc7e10636ffe5f30ca77bf2628e5f5b819087e29ed2905422","source":{"kind":"arxiv","id":"2506.20152","version":1},"attestation_state":"computed","paper":{"title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Deepak Ghimire, Kilho Lee, Seong-heum Kim","submitted_at":"2025-06-25T06:18:46Z","abstract_excerpt":"Structured pruning is a well-established technique for compressing neural networks, making it suitable for deployment in resource-limited edge devices. This paper presents an efficient Loss-Aware Automatic Selection of Structured Pruning Criteria (LAASP) for slimming and accelerating deep neural networks. The majority of pruning methodologies employ a sequential process consisting of three stages: 1) training, 2) pruning, and 3) fine-tuning, whereas the proposed pruning technique adopts a pruning-while-training approach that eliminates the first stage and integrates the second and third stages"},"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":"2506.20152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T06:18:46Z","cross_cats_sorted":["cs.AI","eess.IV"],"title_canon_sha256":"8bee2a58581d01db7bcf63c101be0be03c9d0a82fbd701aa310c6c0f0df8e7b8","abstract_canon_sha256":"6da8b32f3f59d5bfe09a1991f05cdd4d744b2f03498f700ecaf6998a4559b84c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:01.165663Z","signature_b64":"XjTFKacuEhqKFQJnHHqMl36xD2GsXsTf88FNodbYOLuA5QST2llnq0BoAKcv0it3mx8MYXFMqgdYPExHWHNnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"494394bd40f01d8fc7e10636ffe5f30ca77bf2628e5f5b819087e29ed2905422","last_reissued_at":"2026-07-05T11:27:01.165170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:01.165170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Deepak Ghimire, Kilho Lee, Seong-heum Kim","submitted_at":"2025-06-25T06:18:46Z","abstract_excerpt":"Structured pruning is a well-established technique for compressing neural networks, making it suitable for deployment in resource-limited edge devices. This paper presents an efficient Loss-Aware Automatic Selection of Structured Pruning Criteria (LAASP) for slimming and accelerating deep neural networks. The majority of pruning methodologies employ a sequential process consisting of three stages: 1) training, 2) pruning, and 3) fine-tuning, whereas the proposed pruning technique adopts a pruning-while-training approach that eliminates the first stage and integrates the second and third stages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20152","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/2506.20152/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":"2506.20152","created_at":"2026-07-05T11:27:01.165227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20152v1","created_at":"2026-07-05T11:27:01.165227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20152","created_at":"2026-07-05T11:27:01.165227+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFBZJPKA6AOY","created_at":"2026-07-05T11:27:01.165227+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFBZJPKA6AOY7R7B","created_at":"2026-07-05T11:27:01.165227+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFBZJPKA","created_at":"2026-07-05T11:27:01.165227+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/JFBZJPKA6AOY7R7BAY3P7ZPTBS","json":"https://pith.science/pith/JFBZJPKA6AOY7R7BAY3P7ZPTBS.json","graph_json":"https://pith.science/api/pith-number/JFBZJPKA6AOY7R7BAY3P7ZPTBS/graph.json","events_json":"https://pith.science/api/pith-number/JFBZJPKA6AOY7R7BAY3P7ZPTBS/events.json","paper":"https://pith.science/paper/JFBZJPKA"},"agent_actions":{"view_html":"https://pith.science/pith/JFBZJPKA6AOY7R7BAY3P7ZPTBS","download_json":"https://pith.science/pith/JFBZJPKA6AOY7R7BAY3P7ZPTBS.json","view_paper":"https://pith.science/paper/JFBZJPKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20152&json=true","fetch_graph":"https://pith.science/api/pith-number/JFBZJPKA6AOY7R7BAY3P7ZPTBS/graph.json","fetch_events":"https://pith.science/api/pith-number/JFBZJPKA6AOY7R7BAY3P7ZPTBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFBZJPKA6AOY7R7BAY3P7ZPTBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFBZJPKA6AOY7R7BAY3P7ZPTBS/action/storage_attestation","attest_author":"https://pith.science/pith/JFBZJPKA6AOY7R7BAY3P7ZPTBS/action/author_attestation","sign_citation":"https://pith.science/pith/JFBZJPKA6AOY7R7BAY3P7ZPTBS/action/citation_signature","submit_replication":"https://pith.science/pith/JFBZJPKA6AOY7R7BAY3P7ZPTBS/action/replication_record"}},"created_at":"2026-07-05T11:27:01.165227+00:00","updated_at":"2026-07-05T11:27:01.165227+00:00"}