{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R4M7FTVMPKWL64BJI4H4NN5UFA","short_pith_number":"pith:R4M7FTVM","schema_version":"1.0","canonical_sha256":"8f19f2ceac7aacbf7029470fc6b7b42812a047693ee70de5d07ef9468ea0b5ce","source":{"kind":"arxiv","id":"2404.02573","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Jing, Hanting Chen, Jie Hu, Shaohui Lin, Simiao Li, Wei Li, Wenjia Wang, Yun Zhang","submitted_at":"2024-04-03T08:47:40Z","abstract_excerpt":"Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model. Previous methods for image super-resolution (SR) mostly compare the feature maps directly or after standardizing the dimensions with basic algebraic operations (e.g. average, dot-product). However, the intrinsic semantic differences among feature maps are overlooked, which are caused by the disparate expressive capacity between the networks. This work presents MiPKD, a multi-granularit"},"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":"2404.02573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-03T08:47:40Z","cross_cats_sorted":[],"title_canon_sha256":"6f4790a4d51ed0937a7d9e303dc2f579afa4528e73ef53177cad8bffd9d6ca33","abstract_canon_sha256":"753e07c604fc64971ea9ea4fe6021b05d6bdb419ab66e5bfab771cc69a5af58b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:58.396334Z","signature_b64":"pfb5LKd3bSAKEKwWRd3lWVjX2vczL+bNJMoDL2o3AE3Zm4EtDF8w0v8tOBk1Wr2KetTzGZ/FrTzSDq2SItXoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f19f2ceac7aacbf7029470fc6b7b42812a047693ee70de5d07ef9468ea0b5ce","last_reissued_at":"2026-07-05T08:03:58.395880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:58.395880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Jing, Hanting Chen, Jie Hu, Shaohui Lin, Simiao Li, Wei Li, Wenjia Wang, Yun Zhang","submitted_at":"2024-04-03T08:47:40Z","abstract_excerpt":"Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model. Previous methods for image super-resolution (SR) mostly compare the feature maps directly or after standardizing the dimensions with basic algebraic operations (e.g. average, dot-product). However, the intrinsic semantic differences among feature maps are overlooked, which are caused by the disparate expressive capacity between the networks. This work presents MiPKD, a multi-granularit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02573","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/2404.02573/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":"2404.02573","created_at":"2026-07-05T08:03:58.395948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02573v1","created_at":"2026-07-05T08:03:58.395948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02573","created_at":"2026-07-05T08:03:58.395948+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4M7FTVMPKWL","created_at":"2026-07-05T08:03:58.395948+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4M7FTVMPKWL64BJ","created_at":"2026-07-05T08:03:58.395948+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4M7FTVM","created_at":"2026-07-05T08:03:58.395948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08939","citing_title":"Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA","json":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA.json","graph_json":"https://pith.science/api/pith-number/R4M7FTVMPKWL64BJI4H4NN5UFA/graph.json","events_json":"https://pith.science/api/pith-number/R4M7FTVMPKWL64BJI4H4NN5UFA/events.json","paper":"https://pith.science/paper/R4M7FTVM"},"agent_actions":{"view_html":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA","download_json":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA.json","view_paper":"https://pith.science/paper/R4M7FTVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02573&json=true","fetch_graph":"https://pith.science/api/pith-number/R4M7FTVMPKWL64BJI4H4NN5UFA/graph.json","fetch_events":"https://pith.science/api/pith-number/R4M7FTVMPKWL64BJI4H4NN5UFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA/action/storage_attestation","attest_author":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA/action/author_attestation","sign_citation":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA/action/citation_signature","submit_replication":"https://pith.science/pith/R4M7FTVMPKWL64BJI4H4NN5UFA/action/replication_record"}},"created_at":"2026-07-05T08:03:58.395948+00:00","updated_at":"2026-07-05T08:03:58.395948+00:00"}