{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YY4RM2NJARBW7TRB4NQOJMESQZ","short_pith_number":"pith:YY4RM2NJ","schema_version":"1.0","canonical_sha256":"c6391669a904436fce21e360e4b0928674a0a7e47f26343f008e2ae75e306c94","source":{"kind":"arxiv","id":"2501.13341","version":4},"attestation_state":"computed","paper":{"title":"Multi-aspect Knowledge Distillation with Large Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinsik Bang, Soyeong Kwon, Taegyeong Lee, Taehwan Kim","submitted_at":"2025-01-23T02:45:35Z","abstract_excerpt":"Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy loss on class logits. Since they focus on classifying images with considering class labels, these methods may struggle to learn various \\emph{aspects} of classes (e.g., natural positions and shape changes). Rethinking the previous approach from a novel view, we propose a multi-aspect knowledge distillation method using Multimodal Large Language Models (MLLMs"},"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":"2501.13341","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T02:45:35Z","cross_cats_sorted":[],"title_canon_sha256":"181a4c73a4f32451b6f80152b5ddc37c84ab88d40befe0422eefe3bab7a16457","abstract_canon_sha256":"1d133597633148142a1d818fc03901b6ba1c9602774ece321b66b83cd117fb4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:24.513241Z","signature_b64":"vSIql9UjPLyawMADANMtyN7TBM50we+XOlmmeGgmJWFj6SSypcadjXFu8+El+KR/EQ3PbKxGcb+BKaXapvWcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6391669a904436fce21e360e4b0928674a0a7e47f26343f008e2ae75e306c94","last_reissued_at":"2026-07-05T10:48:24.512701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:24.512701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-aspect Knowledge Distillation with Large Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinsik Bang, Soyeong Kwon, Taegyeong Lee, Taehwan Kim","submitted_at":"2025-01-23T02:45:35Z","abstract_excerpt":"Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy loss on class logits. Since they focus on classifying images with considering class labels, these methods may struggle to learn various \\emph{aspects} of classes (e.g., natural positions and shape changes). Rethinking the previous approach from a novel view, we propose a multi-aspect knowledge distillation method using Multimodal Large Language Models (MLLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13341","kind":"arxiv","version":4},"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/2501.13341/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":"2501.13341","created_at":"2026-07-05T10:48:24.512762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13341v4","created_at":"2026-07-05T10:48:24.512762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13341","created_at":"2026-07-05T10:48:24.512762+00:00"},{"alias_kind":"pith_short_12","alias_value":"YY4RM2NJARBW","created_at":"2026-07-05T10:48:24.512762+00:00"},{"alias_kind":"pith_short_16","alias_value":"YY4RM2NJARBW7TRB","created_at":"2026-07-05T10:48:24.512762+00:00"},{"alias_kind":"pith_short_8","alias_value":"YY4RM2NJ","created_at":"2026-07-05T10:48:24.512762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27527","citing_title":"Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ","json":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ.json","graph_json":"https://pith.science/api/pith-number/YY4RM2NJARBW7TRB4NQOJMESQZ/graph.json","events_json":"https://pith.science/api/pith-number/YY4RM2NJARBW7TRB4NQOJMESQZ/events.json","paper":"https://pith.science/paper/YY4RM2NJ"},"agent_actions":{"view_html":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ","download_json":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ.json","view_paper":"https://pith.science/paper/YY4RM2NJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13341&json=true","fetch_graph":"https://pith.science/api/pith-number/YY4RM2NJARBW7TRB4NQOJMESQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YY4RM2NJARBW7TRB4NQOJMESQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ/action/storage_attestation","attest_author":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ/action/author_attestation","sign_citation":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ/action/citation_signature","submit_replication":"https://pith.science/pith/YY4RM2NJARBW7TRB4NQOJMESQZ/action/replication_record"}},"created_at":"2026-07-05T10:48:24.512762+00:00","updated_at":"2026-07-05T10:48:24.512762+00:00"}