{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZJYHY2MGPCPHFDLVM75NKXJW5B","short_pith_number":"pith:ZJYHY2MG","schema_version":"1.0","canonical_sha256":"ca707c6986789e728d7567fad55d36e85511a48360e23cfd0004742abe1bde53","source":{"kind":"arxiv","id":"1707.04319","version":1},"attestation_state":"computed","paper":{"title":"Model compression as constrained optimization, with application to neural nets. Part II: quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Miguel \\'A. Carreira-Perpi\\~n\\'an, Yerlan Idelbayev","submitted_at":"2017-07-13T20:58:40Z","abstract_excerpt":"We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal. The codebook can be optimally learned jointly with the net, or fixed, as for binarization or ternarization approaches. Previous work has quantized the weights of the reference net, or incorporated rounding operations in the backpropagation algorithm, but this has no guarantee of converging to a loss-optimal, quantized net. We describe a new approach based on "},"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":"1707.04319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-13T20:58:40Z","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"title_canon_sha256":"a26c4743f5c595aff46bfca8e7da5b4e702fcbb6cbeadba789c16de679db31e0","abstract_canon_sha256":"365835af90237c10fd767addfcd51063d8883e2637245b40f26de88520ca0b12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:18.664053Z","signature_b64":"ny61XahZt8vuIFz8IivgrnQAOJTTHASyrzz3hy18mUod38kcoFanw9spAIDkP+qm1H4IBDmaz+pCEKUNwBMzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca707c6986789e728d7567fad55d36e85511a48360e23cfd0004742abe1bde53","last_reissued_at":"2026-05-18T00:40:18.663380Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:18.663380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model compression as constrained optimization, with application to neural nets. Part II: quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Miguel \\'A. Carreira-Perpi\\~n\\'an, Yerlan Idelbayev","submitted_at":"2017-07-13T20:58:40Z","abstract_excerpt":"We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal. The codebook can be optimally learned jointly with the net, or fixed, as for binarization or ternarization approaches. Previous work has quantized the weights of the reference net, or incorporated rounding operations in the backpropagation algorithm, but this has no guarantee of converging to a loss-optimal, quantized net. We describe a new approach based on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04319","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":""},"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":"1707.04319","created_at":"2026-05-18T00:40:18.663474+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.04319v1","created_at":"2026-05-18T00:40:18.663474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04319","created_at":"2026-05-18T00:40:18.663474+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJYHY2MGPCPH","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJYHY2MGPCPHFDLV","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJYHY2MG","created_at":"2026-05-18T12:31:59.375834+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/ZJYHY2MGPCPHFDLVM75NKXJW5B","json":"https://pith.science/pith/ZJYHY2MGPCPHFDLVM75NKXJW5B.json","graph_json":"https://pith.science/api/pith-number/ZJYHY2MGPCPHFDLVM75NKXJW5B/graph.json","events_json":"https://pith.science/api/pith-number/ZJYHY2MGPCPHFDLVM75NKXJW5B/events.json","paper":"https://pith.science/paper/ZJYHY2MG"},"agent_actions":{"view_html":"https://pith.science/pith/ZJYHY2MGPCPHFDLVM75NKXJW5B","download_json":"https://pith.science/pith/ZJYHY2MGPCPHFDLVM75NKXJW5B.json","view_paper":"https://pith.science/paper/ZJYHY2MG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.04319&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJYHY2MGPCPHFDLVM75NKXJW5B/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJYHY2MGPCPHFDLVM75NKXJW5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJYHY2MGPCPHFDLVM75NKXJW5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJYHY2MGPCPHFDLVM75NKXJW5B/action/storage_attestation","attest_author":"https://pith.science/pith/ZJYHY2MGPCPHFDLVM75NKXJW5B/action/author_attestation","sign_citation":"https://pith.science/pith/ZJYHY2MGPCPHFDLVM75NKXJW5B/action/citation_signature","submit_replication":"https://pith.science/pith/ZJYHY2MGPCPHFDLVM75NKXJW5B/action/replication_record"}},"created_at":"2026-05-18T00:40:18.663474+00:00","updated_at":"2026-05-18T00:40:18.663474+00:00"}