{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EKQVG4SQFHNB3C5UMC5HWB2OLV","short_pith_number":"pith:EKQVG4SQ","schema_version":"1.0","canonical_sha256":"22a153725029da1d8bb460ba7b074e5d4835e1f1ce8545c2f48b00f3be05f034","source":{"kind":"arxiv","id":"2003.08436","version":2},"attestation_state":"computed","paper":{"title":"Collaborative Distillation for Ultra-Resolution Universal Style Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Haoji Hu, Huan Wang, Ming-Hsuan Yang, Yijun Li, Yuehai Wang","submitted_at":"2020-03-18T18:59:31Z","abstract_excerpt":"Universal style transfer methods typically leverage rich representations from deep Convolutional Neural Network (CNN) models (e.g., VGG-19) pre-trained on large collections of images. Despite the effectiveness, its application is heavily constrained by the large model size to handle ultra-resolution images given limited memory. In this work, we present a new knowledge distillation method (named Collaborative Distillation) for encoder-decoder based neural style transfer to reduce the convolutional filters. The main idea is underpinned by a finding that the encoder-decoder pairs construct an exc"},"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":"2003.08436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-18T18:59:31Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"6f538970739f7e22ea5a4fa16883ce36bbfed664e0aa654db08760b431617dc6","abstract_canon_sha256":"26a8e2b792b285fb785572d51f77b7a3433d2d2f95902d05b66777f9303b1b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:17.286626Z","signature_b64":"tTJTGCkBuzZouiYilcUSSZxSN9wxy9IdY5RIx546qS15uv2nSE9VO1Y1huSH4/xiTHiNUrVPmH+dGKbTbrGBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22a153725029da1d8bb460ba7b074e5d4835e1f1ce8545c2f48b00f3be05f034","last_reissued_at":"2026-07-05T00:50:17.286103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:17.286103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Distillation for Ultra-Resolution Universal Style Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Haoji Hu, Huan Wang, Ming-Hsuan Yang, Yijun Li, Yuehai Wang","submitted_at":"2020-03-18T18:59:31Z","abstract_excerpt":"Universal style transfer methods typically leverage rich representations from deep Convolutional Neural Network (CNN) models (e.g., VGG-19) pre-trained on large collections of images. Despite the effectiveness, its application is heavily constrained by the large model size to handle ultra-resolution images given limited memory. In this work, we present a new knowledge distillation method (named Collaborative Distillation) for encoder-decoder based neural style transfer to reduce the convolutional filters. The main idea is underpinned by a finding that the encoder-decoder pairs construct an exc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08436","kind":"arxiv","version":2},"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/2003.08436/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":"2003.08436","created_at":"2026-07-05T00:50:17.286170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.08436v2","created_at":"2026-07-05T00:50:17.286170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08436","created_at":"2026-07-05T00:50:17.286170+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKQVG4SQFHNB","created_at":"2026-07-05T00:50:17.286170+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKQVG4SQFHNB3C5U","created_at":"2026-07-05T00:50:17.286170+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKQVG4SQ","created_at":"2026-07-05T00:50:17.286170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16056","citing_title":"Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainability","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV","json":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV.json","graph_json":"https://pith.science/api/pith-number/EKQVG4SQFHNB3C5UMC5HWB2OLV/graph.json","events_json":"https://pith.science/api/pith-number/EKQVG4SQFHNB3C5UMC5HWB2OLV/events.json","paper":"https://pith.science/paper/EKQVG4SQ"},"agent_actions":{"view_html":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV","download_json":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV.json","view_paper":"https://pith.science/paper/EKQVG4SQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.08436&json=true","fetch_graph":"https://pith.science/api/pith-number/EKQVG4SQFHNB3C5UMC5HWB2OLV/graph.json","fetch_events":"https://pith.science/api/pith-number/EKQVG4SQFHNB3C5UMC5HWB2OLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV/action/storage_attestation","attest_author":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV/action/author_attestation","sign_citation":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV/action/citation_signature","submit_replication":"https://pith.science/pith/EKQVG4SQFHNB3C5UMC5HWB2OLV/action/replication_record"}},"created_at":"2026-07-05T00:50:17.286170+00:00","updated_at":"2026-07-05T00:50:17.286170+00:00"}