{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:K4JORL4MLSL3PB75ZJWI32XLMW","short_pith_number":"pith:K4JORL4M","schema_version":"1.0","canonical_sha256":"5712e8af8c5c97b787fdca6c8deaeb65aad929ccf20bc9ff2bc9dee1bc710e71","source":{"kind":"arxiv","id":"1906.06633","version":1},"attestation_state":"computed","paper":{"title":"Mixture separability loss in a deep convolutional network for image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Bin Jin, Hakil Kim, Trung Dung Do, Van Huan Nguyen","submitted_at":"2019-06-16T01:45:57Z","abstract_excerpt":"In machine learning, the cost function is crucial because it measures how good or bad a system is. In image classification, well-known networks only consider modifying the network structures and applying cross-entropy loss at the end of the network. However, using only cross-entropy loss causes a network to stop updating weights when all training images are correctly classified. This is the problem of the early saturation. This paper proposes a novel cost function, called mixture separability loss (MSL), which updates the weights of the network even when most of the training images are accurat"},"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":"1906.06633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-16T01:45:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e16378cc492ee148abaf9b9091413f7e871a23fbd02294d5204b53e45440cd7f","abstract_canon_sha256":"ff67897fdb6e6c859ed53217018bdbb9479879cacb4f1a2b08ace82647855277"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:13.112616Z","signature_b64":"zcAn+MnotWoaNWxfgS7pjBoYGkSVqenDC5UYh0LA75obVssTN1hrekTSBSxECDMWTgdYvBvQbNDj+NH2qsyADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5712e8af8c5c97b787fdca6c8deaeb65aad929ccf20bc9ff2bc9dee1bc710e71","last_reissued_at":"2026-05-17T23:43:13.112066Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:13.112066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture separability loss in a deep convolutional network for image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Bin Jin, Hakil Kim, Trung Dung Do, Van Huan Nguyen","submitted_at":"2019-06-16T01:45:57Z","abstract_excerpt":"In machine learning, the cost function is crucial because it measures how good or bad a system is. In image classification, well-known networks only consider modifying the network structures and applying cross-entropy loss at the end of the network. However, using only cross-entropy loss causes a network to stop updating weights when all training images are correctly classified. This is the problem of the early saturation. This paper proposes a novel cost function, called mixture separability loss (MSL), which updates the weights of the network even when most of the training images are accurat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06633","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":"1906.06633","created_at":"2026-05-17T23:43:13.112153+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06633v1","created_at":"2026-05-17T23:43:13.112153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06633","created_at":"2026-05-17T23:43:13.112153+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4JORL4MLSL3","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4JORL4MLSL3PB75","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4JORL4M","created_at":"2026-05-18T12:33:21.387695+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/K4JORL4MLSL3PB75ZJWI32XLMW","json":"https://pith.science/pith/K4JORL4MLSL3PB75ZJWI32XLMW.json","graph_json":"https://pith.science/api/pith-number/K4JORL4MLSL3PB75ZJWI32XLMW/graph.json","events_json":"https://pith.science/api/pith-number/K4JORL4MLSL3PB75ZJWI32XLMW/events.json","paper":"https://pith.science/paper/K4JORL4M"},"agent_actions":{"view_html":"https://pith.science/pith/K4JORL4MLSL3PB75ZJWI32XLMW","download_json":"https://pith.science/pith/K4JORL4MLSL3PB75ZJWI32XLMW.json","view_paper":"https://pith.science/paper/K4JORL4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06633&json=true","fetch_graph":"https://pith.science/api/pith-number/K4JORL4MLSL3PB75ZJWI32XLMW/graph.json","fetch_events":"https://pith.science/api/pith-number/K4JORL4MLSL3PB75ZJWI32XLMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4JORL4MLSL3PB75ZJWI32XLMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4JORL4MLSL3PB75ZJWI32XLMW/action/storage_attestation","attest_author":"https://pith.science/pith/K4JORL4MLSL3PB75ZJWI32XLMW/action/author_attestation","sign_citation":"https://pith.science/pith/K4JORL4MLSL3PB75ZJWI32XLMW/action/citation_signature","submit_replication":"https://pith.science/pith/K4JORL4MLSL3PB75ZJWI32XLMW/action/replication_record"}},"created_at":"2026-05-17T23:43:13.112153+00:00","updated_at":"2026-05-17T23:43:13.112153+00:00"}