{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IC76W46O5GCY34BTM2U7ASGL7Q","short_pith_number":"pith:IC76W46O","schema_version":"1.0","canonical_sha256":"40bfeb73cee9858df03366a9f048cbfc3224925f4e05865da6918f5d0426055c","source":{"kind":"arxiv","id":"2204.05566","version":3},"attestation_state":"computed","paper":{"title":"Compact Model Training by Low-Rank Projection with Energy Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Canyang Chen, Fang Liu, Kailing Guo, Xiangmin Xu, Xiaofen Xing, Zhenquan Lin","submitted_at":"2022-04-12T06:53:25Z","abstract_excerpt":"Low-rankness plays an important role in traditional machine learning, but is not so popular in deep learning. Most previous low-rank network compression methods compress networks by approximating pre-trained models and re-training. However, the optimal solution in the Euclidean space may be quite different from the one with low-rank constraint. A well-pre-trained model is not a good initialization for the model with low-rank constraints. Thus, the performance of a low-rank compressed network degrades significantly. Compared with other network compression methods such as pruning, low-rank metho"},"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":"2204.05566","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-12T06:53:25Z","cross_cats_sorted":[],"title_canon_sha256":"67132ba8a770c5cf353a4291b7bbe66d0d72951d2e0985cf6a39f7f831b4f1f8","abstract_canon_sha256":"7b9731e3bd89201a897f8da017ab060cbaccdcfd8265cfa762b412a8c3024a85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:19.231379Z","signature_b64":"8bWewU063dUOqSrmJC/LucRiMZQgihrIjYkuaTU2OR0wR1wlG4l5A+TI51xfmFMUyoig+v3P5FRg5LxQtDTADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40bfeb73cee9858df03366a9f048cbfc3224925f4e05865da6918f5d0426055c","last_reissued_at":"2026-07-05T08:55:19.230972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:19.230972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compact Model Training by Low-Rank Projection with Energy Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Canyang Chen, Fang Liu, Kailing Guo, Xiangmin Xu, Xiaofen Xing, Zhenquan Lin","submitted_at":"2022-04-12T06:53:25Z","abstract_excerpt":"Low-rankness plays an important role in traditional machine learning, but is not so popular in deep learning. Most previous low-rank network compression methods compress networks by approximating pre-trained models and re-training. However, the optimal solution in the Euclidean space may be quite different from the one with low-rank constraint. A well-pre-trained model is not a good initialization for the model with low-rank constraints. Thus, the performance of a low-rank compressed network degrades significantly. Compared with other network compression methods such as pruning, low-rank metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05566","kind":"arxiv","version":3},"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/2204.05566/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":"2204.05566","created_at":"2026-07-05T08:55:19.231026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05566v3","created_at":"2026-07-05T08:55:19.231026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05566","created_at":"2026-07-05T08:55:19.231026+00:00"},{"alias_kind":"pith_short_12","alias_value":"IC76W46O5GCY","created_at":"2026-07-05T08:55:19.231026+00:00"},{"alias_kind":"pith_short_16","alias_value":"IC76W46O5GCY34BT","created_at":"2026-07-05T08:55:19.231026+00:00"},{"alias_kind":"pith_short_8","alias_value":"IC76W46O","created_at":"2026-07-05T08:55:19.231026+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/IC76W46O5GCY34BTM2U7ASGL7Q","json":"https://pith.science/pith/IC76W46O5GCY34BTM2U7ASGL7Q.json","graph_json":"https://pith.science/api/pith-number/IC76W46O5GCY34BTM2U7ASGL7Q/graph.json","events_json":"https://pith.science/api/pith-number/IC76W46O5GCY34BTM2U7ASGL7Q/events.json","paper":"https://pith.science/paper/IC76W46O"},"agent_actions":{"view_html":"https://pith.science/pith/IC76W46O5GCY34BTM2U7ASGL7Q","download_json":"https://pith.science/pith/IC76W46O5GCY34BTM2U7ASGL7Q.json","view_paper":"https://pith.science/paper/IC76W46O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05566&json=true","fetch_graph":"https://pith.science/api/pith-number/IC76W46O5GCY34BTM2U7ASGL7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/IC76W46O5GCY34BTM2U7ASGL7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IC76W46O5GCY34BTM2U7ASGL7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IC76W46O5GCY34BTM2U7ASGL7Q/action/storage_attestation","attest_author":"https://pith.science/pith/IC76W46O5GCY34BTM2U7ASGL7Q/action/author_attestation","sign_citation":"https://pith.science/pith/IC76W46O5GCY34BTM2U7ASGL7Q/action/citation_signature","submit_replication":"https://pith.science/pith/IC76W46O5GCY34BTM2U7ASGL7Q/action/replication_record"}},"created_at":"2026-07-05T08:55:19.231026+00:00","updated_at":"2026-07-05T08:55:19.231026+00:00"}