{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NQXFOM36I7Q7DVPRF2NOPKW3S2","short_pith_number":"pith:NQXFOM36","schema_version":"1.0","canonical_sha256":"6c2e57337e47e1f1d5f12e9ae7aadb96811ae9f343cef696167d58cc3fd5860b","source":{"kind":"arxiv","id":"1711.02613","version":4},"attestation_state":"computed","paper":{"title":"Moonshine: Distilling with Cheap Convolutions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Amos Storkey, Elliot J. Crowley, Gavin Gray","submitted_at":"2017-11-07T17:21:06Z","abstract_excerpt":"Many engineers wish to deploy modern neural networks in memory-limited settings; but the development of flexible methods for reducing memory use is in its infancy, and there is little knowledge of the resulting cost-benefit. We propose structural model distillation for memory reduction using a strategy that produces a student architecture that is a simple transformation of the teacher architecture: no redesign is needed, and the same hyperparameters can be used. Using attention transfer, we provide Pareto curves/tables for distillation of residual networks with four benchmark datasets, indicat"},"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":"1711.02613","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2017-11-07T17:21:06Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"f574efe964ed2d17d771aa5580e789032350a084f319276230e07a708aa7d24c","abstract_canon_sha256":"a79f24bbda8832f7625a7f5db9c388c9aa0458522109a42f709d5ff386db3238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:10.441930Z","signature_b64":"KxWnjSpl+c/JHQIEzG5/rFO4z3GO0l6lg7iLlHlNixlIHBTKezpV3TwC11epGB5AGhfpRbuws6xaQC/GRngvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c2e57337e47e1f1d5f12e9ae7aadb96811ae9f343cef696167d58cc3fd5860b","last_reissued_at":"2026-05-17T23:56:10.441330Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:10.441330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moonshine: Distilling with Cheap Convolutions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Amos Storkey, Elliot J. Crowley, Gavin Gray","submitted_at":"2017-11-07T17:21:06Z","abstract_excerpt":"Many engineers wish to deploy modern neural networks in memory-limited settings; but the development of flexible methods for reducing memory use is in its infancy, and there is little knowledge of the resulting cost-benefit. We propose structural model distillation for memory reduction using a strategy that produces a student architecture that is a simple transformation of the teacher architecture: no redesign is needed, and the same hyperparameters can be used. Using attention transfer, we provide Pareto curves/tables for distillation of residual networks with four benchmark datasets, indicat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02613","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":""},"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":"1711.02613","created_at":"2026-05-17T23:56:10.441437+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.02613v4","created_at":"2026-05-17T23:56:10.441437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02613","created_at":"2026-05-17T23:56:10.441437+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQXFOM36I7Q7","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQXFOM36I7Q7DVPR","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQXFOM36","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15014","citing_title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2","json":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2.json","graph_json":"https://pith.science/api/pith-number/NQXFOM36I7Q7DVPRF2NOPKW3S2/graph.json","events_json":"https://pith.science/api/pith-number/NQXFOM36I7Q7DVPRF2NOPKW3S2/events.json","paper":"https://pith.science/paper/NQXFOM36"},"agent_actions":{"view_html":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2","download_json":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2.json","view_paper":"https://pith.science/paper/NQXFOM36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.02613&json=true","fetch_graph":"https://pith.science/api/pith-number/NQXFOM36I7Q7DVPRF2NOPKW3S2/graph.json","fetch_events":"https://pith.science/api/pith-number/NQXFOM36I7Q7DVPRF2NOPKW3S2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2/action/storage_attestation","attest_author":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2/action/author_attestation","sign_citation":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2/action/citation_signature","submit_replication":"https://pith.science/pith/NQXFOM36I7Q7DVPRF2NOPKW3S2/action/replication_record"}},"created_at":"2026-05-17T23:56:10.441437+00:00","updated_at":"2026-05-17T23:56:10.441437+00:00"}