{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XTFKZN5TMQRDIXLY2FCNDFECRT","short_pith_number":"pith:XTFKZN5T","schema_version":"1.0","canonical_sha256":"bccaacb7b36422345d78d144d194828cede195bc614d3e81c19c92fa99684b9f","source":{"kind":"arxiv","id":"2103.05959","version":1},"attestation_state":"computed","paper":{"title":"Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Cui, Dianhai Yu, Dongliang He, Errui Ding, Fu Li, Jizhou Huang, Qiwen Liu, Ruoyu Guo, Shilei Wen, Xiaoguang Hu, Yanjun Ma, Yuning Du, Zewu Wu","submitted_at":"2021-03-10T09:32:44Z","abstract_excerpt":"Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the community and are proven to be of great potential in obtaining a powerful pre-trained model. However, these models require huge training costs (i.e., hundreds of millions of images or training iterations). In this paper, we propose to improve existing baseline networks via knowledge distillation from off-the-shelf pre-trained big powerful models. Different from exis"},"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":"2103.05959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-10T09:32:44Z","cross_cats_sorted":[],"title_canon_sha256":"67cfe4dd4e1ca480cc64155e2ba4000dec8447cb019087b895036f23dd63f4ee","abstract_canon_sha256":"8f6ca8ebc5e74f351bf16292bf8a4a33513161c2e4d6cd1d1d01c693a30aee55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:00.101224Z","signature_b64":"LsIvGyl8s8+NAJvOz2bN99ZyqLgpxr+ooEVSbYDl98zm9/kI1DxbMjw7rODaWiv3BFt5AoguMLRj+6Soh5meBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bccaacb7b36422345d78d144d194828cede195bc614d3e81c19c92fa99684b9f","last_reissued_at":"2026-07-05T02:22:00.100761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:00.100761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Cui, Dianhai Yu, Dongliang He, Errui Ding, Fu Li, Jizhou Huang, Qiwen Liu, Ruoyu Guo, Shilei Wen, Xiaoguang Hu, Yanjun Ma, Yuning Du, Zewu Wu","submitted_at":"2021-03-10T09:32:44Z","abstract_excerpt":"Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the community and are proven to be of great potential in obtaining a powerful pre-trained model. However, these models require huge training costs (i.e., hundreds of millions of images or training iterations). In this paper, we propose to improve existing baseline networks via knowledge distillation from off-the-shelf pre-trained big powerful models. Different from exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05959","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/2103.05959/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":"2103.05959","created_at":"2026-07-05T02:22:00.100826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05959v1","created_at":"2026-07-05T02:22:00.100826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05959","created_at":"2026-07-05T02:22:00.100826+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTFKZN5TMQRD","created_at":"2026-07-05T02:22:00.100826+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTFKZN5TMQRDIXLY","created_at":"2026-07-05T02:22:00.100826+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTFKZN5T","created_at":"2026-07-05T02:22:00.100826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00734","citing_title":"ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT","json":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT.json","graph_json":"https://pith.science/api/pith-number/XTFKZN5TMQRDIXLY2FCNDFECRT/graph.json","events_json":"https://pith.science/api/pith-number/XTFKZN5TMQRDIXLY2FCNDFECRT/events.json","paper":"https://pith.science/paper/XTFKZN5T"},"agent_actions":{"view_html":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT","download_json":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT.json","view_paper":"https://pith.science/paper/XTFKZN5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05959&json=true","fetch_graph":"https://pith.science/api/pith-number/XTFKZN5TMQRDIXLY2FCNDFECRT/graph.json","fetch_events":"https://pith.science/api/pith-number/XTFKZN5TMQRDIXLY2FCNDFECRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT/action/storage_attestation","attest_author":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT/action/author_attestation","sign_citation":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT/action/citation_signature","submit_replication":"https://pith.science/pith/XTFKZN5TMQRDIXLY2FCNDFECRT/action/replication_record"}},"created_at":"2026-07-05T02:22:00.100826+00:00","updated_at":"2026-07-05T02:22:00.100826+00:00"}