{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UWNT2R3SAHB4REYHDVN45P7TDC","short_pith_number":"pith:UWNT2R3S","schema_version":"1.0","canonical_sha256":"a59b3d477201c3c893071d5bcebff3189b9a610c24a1a42792c1662b536b37e7","source":{"kind":"arxiv","id":"2305.09183","version":1},"attestation_state":"computed","paper":{"title":"Lightweight Self-Knowledge Distillation with Multi-source Information Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Guo, Pengchao Han, Xucong Wang","submitted_at":"2023-05-16T05:46:31Z","abstract_excerpt":"Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a suitable teacher model is not always guaranteed. To address this challenge, Self-Knowledge Distillation (SKD) attempts to construct a teacher model from itself. Existing SKD methods add Auxiliary Classifiers (AC) to intermediate layers of the model or use the history models and models with different input data within the same class. However, these methods are"},"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":"2305.09183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-16T05:46:31Z","cross_cats_sorted":[],"title_canon_sha256":"97230731e0d4f1155cc263215143eb8e181ecb83e50505a5a8ceb50c1e403421","abstract_canon_sha256":"7a25f7f88fef037d47e8f45cc75b303dec4ed79a1f6c24236e04a5e9b67954af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:44.815890Z","signature_b64":"hTKEV+JR7Zi17hKNVMAr3hLJ7kQxg61cim/cSbwcQR/yuO/4rrJI/uMw+ersemZvksDbCwFDFUVIkNwVJCLpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a59b3d477201c3c893071d5bcebff3189b9a610c24a1a42792c1662b536b37e7","last_reissued_at":"2026-07-05T06:10:44.815490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:44.815490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lightweight Self-Knowledge Distillation with Multi-source Information Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Guo, Pengchao Han, Xucong Wang","submitted_at":"2023-05-16T05:46:31Z","abstract_excerpt":"Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a suitable teacher model is not always guaranteed. To address this challenge, Self-Knowledge Distillation (SKD) attempts to construct a teacher model from itself. Existing SKD methods add Auxiliary Classifiers (AC) to intermediate layers of the model or use the history models and models with different input data within the same class. However, these methods are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09183","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/2305.09183/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":"2305.09183","created_at":"2026-07-05T06:10:44.815545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.09183v1","created_at":"2026-07-05T06:10:44.815545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09183","created_at":"2026-07-05T06:10:44.815545+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWNT2R3SAHB4","created_at":"2026-07-05T06:10:44.815545+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWNT2R3SAHB4REYH","created_at":"2026-07-05T06:10:44.815545+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWNT2R3S","created_at":"2026-07-05T06:10:44.815545+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/UWNT2R3SAHB4REYHDVN45P7TDC","json":"https://pith.science/pith/UWNT2R3SAHB4REYHDVN45P7TDC.json","graph_json":"https://pith.science/api/pith-number/UWNT2R3SAHB4REYHDVN45P7TDC/graph.json","events_json":"https://pith.science/api/pith-number/UWNT2R3SAHB4REYHDVN45P7TDC/events.json","paper":"https://pith.science/paper/UWNT2R3S"},"agent_actions":{"view_html":"https://pith.science/pith/UWNT2R3SAHB4REYHDVN45P7TDC","download_json":"https://pith.science/pith/UWNT2R3SAHB4REYHDVN45P7TDC.json","view_paper":"https://pith.science/paper/UWNT2R3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.09183&json=true","fetch_graph":"https://pith.science/api/pith-number/UWNT2R3SAHB4REYHDVN45P7TDC/graph.json","fetch_events":"https://pith.science/api/pith-number/UWNT2R3SAHB4REYHDVN45P7TDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWNT2R3SAHB4REYHDVN45P7TDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWNT2R3SAHB4REYHDVN45P7TDC/action/storage_attestation","attest_author":"https://pith.science/pith/UWNT2R3SAHB4REYHDVN45P7TDC/action/author_attestation","sign_citation":"https://pith.science/pith/UWNT2R3SAHB4REYHDVN45P7TDC/action/citation_signature","submit_replication":"https://pith.science/pith/UWNT2R3SAHB4REYHDVN45P7TDC/action/replication_record"}},"created_at":"2026-07-05T06:10:44.815545+00:00","updated_at":"2026-07-05T06:10:44.815545+00:00"}