{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:UXE7A2VVOOOOGYN7THKPFJT6P3","short_pith_number":"pith:UXE7A2VV","schema_version":"1.0","canonical_sha256":"a5c9f06ab5739ce361bf99d4f2a67e7eca6412576618fb4a07c649918b8f34d8","source":{"kind":"arxiv","id":"1511.01574","version":2},"attestation_state":"computed","paper":{"title":"Multinomial Loss on Held-out Data for the Sparse Non-negative Matrix Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ciprian Chelba, Fernando Pereira","submitted_at":"2015-11-05T01:45:29Z","abstract_excerpt":"We describe Sparse Non-negative Matrix (SNM) language model estimation using multinomial loss on held-out data.\n  Being able to train on held-out data is important in practical situations where the training data is usually mismatched from the held-out/test data. It is also less constrained than the previous training algorithm using leave-one-out on training data: it allows the use of richer meta-features in the adjustment model, e.g. the diversity counts used by Kneser-Ney smoothing which would be difficult to deal with correctly in leave-one-out training.\n  In experiments on the one billion w"},"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":"1511.01574","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-05T01:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"c0626740ed780b8bc41969c38187b7d04165597a58dc421503b943a3d7fa3549","abstract_canon_sha256":"c51b5caed5266057c739a9166052b4610d9efb70f034fc9cff110fffde56627d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:16.583218Z","signature_b64":"rzpiWeKkQZEddsUiu6xkLNgUcjRY2yKirGCmJtFxcoAtaqdx1S1KzcE/+fArQ65YqRTfIDoZOL1H6x33cGu2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5c9f06ab5739ce361bf99d4f2a67e7eca6412576618fb4a07c649918b8f34d8","last_reissued_at":"2026-05-18T01:20:16.582586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:16.582586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multinomial Loss on Held-out Data for the Sparse Non-negative Matrix Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ciprian Chelba, Fernando Pereira","submitted_at":"2015-11-05T01:45:29Z","abstract_excerpt":"We describe Sparse Non-negative Matrix (SNM) language model estimation using multinomial loss on held-out data.\n  Being able to train on held-out data is important in practical situations where the training data is usually mismatched from the held-out/test data. It is also less constrained than the previous training algorithm using leave-one-out on training data: it allows the use of richer meta-features in the adjustment model, e.g. the diversity counts used by Kneser-Ney smoothing which would be difficult to deal with correctly in leave-one-out training.\n  In experiments on the one billion w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.01574","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":""},"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":"1511.01574","created_at":"2026-05-18T01:20:16.582685+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.01574v2","created_at":"2026-05-18T01:20:16.582685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01574","created_at":"2026-05-18T01:20:16.582685+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXE7A2VVOOOO","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXE7A2VVOOOOGYN7","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXE7A2VV","created_at":"2026-05-18T12:29:44.643036+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/UXE7A2VVOOOOGYN7THKPFJT6P3","json":"https://pith.science/pith/UXE7A2VVOOOOGYN7THKPFJT6P3.json","graph_json":"https://pith.science/api/pith-number/UXE7A2VVOOOOGYN7THKPFJT6P3/graph.json","events_json":"https://pith.science/api/pith-number/UXE7A2VVOOOOGYN7THKPFJT6P3/events.json","paper":"https://pith.science/paper/UXE7A2VV"},"agent_actions":{"view_html":"https://pith.science/pith/UXE7A2VVOOOOGYN7THKPFJT6P3","download_json":"https://pith.science/pith/UXE7A2VVOOOOGYN7THKPFJT6P3.json","view_paper":"https://pith.science/paper/UXE7A2VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.01574&json=true","fetch_graph":"https://pith.science/api/pith-number/UXE7A2VVOOOOGYN7THKPFJT6P3/graph.json","fetch_events":"https://pith.science/api/pith-number/UXE7A2VVOOOOGYN7THKPFJT6P3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXE7A2VVOOOOGYN7THKPFJT6P3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXE7A2VVOOOOGYN7THKPFJT6P3/action/storage_attestation","attest_author":"https://pith.science/pith/UXE7A2VVOOOOGYN7THKPFJT6P3/action/author_attestation","sign_citation":"https://pith.science/pith/UXE7A2VVOOOOGYN7THKPFJT6P3/action/citation_signature","submit_replication":"https://pith.science/pith/UXE7A2VVOOOOGYN7THKPFJT6P3/action/replication_record"}},"created_at":"2026-05-18T01:20:16.582685+00:00","updated_at":"2026-05-18T01:20:16.582685+00:00"}