{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:OGKHAMQLEO4XAUWI6O4PSKE3EF","short_pith_number":"pith:OGKHAMQL","schema_version":"1.0","canonical_sha256":"719470320b23b97052c8f3b8f9289b2176b6e11d1204949e19fa50a1bc000ff1","source":{"kind":"arxiv","id":"1511.06456","version":4},"attestation_state":"computed","paper":{"title":"Task Loss Estimation for Sequence Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Dmitriy Serdyuk, Dzmitry Bahdanau, Jan Chorowski, Nan Rosemary Ke, Phil\\'emon Brakel, Yoshua Bengio","submitted_at":"2015-11-19T23:51:31Z","abstract_excerpt":"Often, the performance on a supervised machine learning task is evaluated with a emph{task loss} function that cannot be optimized directly. Examples of such loss functions include the classification error, the edit distance and the BLEU score. A common workaround for this problem is to instead optimize a emph{surrogate loss} function, such as for instance cross-entropy or hinge loss. In order for this remedy to be effective, it is important to ensure that minimization of the surrogate loss results in minimization of the task loss, a condition that we call emph{consistency with the task loss}."},"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":"1511.06456","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T23:51:31Z","cross_cats_sorted":[],"title_canon_sha256":"25feab8b5342fdd5881d799dbd87e30ac804122f8ac25ab72e1e7a6d66f91445","abstract_canon_sha256":"ac9bf9ec2dc1bad7b0a82ba3ca13124bb1f377b16dc3911d361b91a860b4065d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:33.011555Z","signature_b64":"iPAdy1oIcHpK9/SzFZhMyJP9J8jLifmS2fcKTwv+Rkz08RAGD/GBlUlZXslpzs4xWs/JoduIvEoxbr/tCCp0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"719470320b23b97052c8f3b8f9289b2176b6e11d1204949e19fa50a1bc000ff1","last_reissued_at":"2026-05-18T01:22:33.011091Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:33.011091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task Loss Estimation for Sequence Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Dmitriy Serdyuk, Dzmitry Bahdanau, Jan Chorowski, Nan Rosemary Ke, Phil\\'emon Brakel, Yoshua Bengio","submitted_at":"2015-11-19T23:51:31Z","abstract_excerpt":"Often, the performance on a supervised machine learning task is evaluated with a emph{task loss} function that cannot be optimized directly. Examples of such loss functions include the classification error, the edit distance and the BLEU score. A common workaround for this problem is to instead optimize a emph{surrogate loss} function, such as for instance cross-entropy or hinge loss. In order for this remedy to be effective, it is important to ensure that minimization of the surrogate loss results in minimization of the task loss, a condition that we call emph{consistency with the task loss}."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06456","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":"1511.06456","created_at":"2026-05-18T01:22:33.011156+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06456v4","created_at":"2026-05-18T01:22:33.011156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06456","created_at":"2026-05-18T01:22:33.011156+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGKHAMQLEO4X","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGKHAMQLEO4XAUWI","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGKHAMQL","created_at":"2026-05-18T12:29:34.919912+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/OGKHAMQLEO4XAUWI6O4PSKE3EF","json":"https://pith.science/pith/OGKHAMQLEO4XAUWI6O4PSKE3EF.json","graph_json":"https://pith.science/api/pith-number/OGKHAMQLEO4XAUWI6O4PSKE3EF/graph.json","events_json":"https://pith.science/api/pith-number/OGKHAMQLEO4XAUWI6O4PSKE3EF/events.json","paper":"https://pith.science/paper/OGKHAMQL"},"agent_actions":{"view_html":"https://pith.science/pith/OGKHAMQLEO4XAUWI6O4PSKE3EF","download_json":"https://pith.science/pith/OGKHAMQLEO4XAUWI6O4PSKE3EF.json","view_paper":"https://pith.science/paper/OGKHAMQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06456&json=true","fetch_graph":"https://pith.science/api/pith-number/OGKHAMQLEO4XAUWI6O4PSKE3EF/graph.json","fetch_events":"https://pith.science/api/pith-number/OGKHAMQLEO4XAUWI6O4PSKE3EF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGKHAMQLEO4XAUWI6O4PSKE3EF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGKHAMQLEO4XAUWI6O4PSKE3EF/action/storage_attestation","attest_author":"https://pith.science/pith/OGKHAMQLEO4XAUWI6O4PSKE3EF/action/author_attestation","sign_citation":"https://pith.science/pith/OGKHAMQLEO4XAUWI6O4PSKE3EF/action/citation_signature","submit_replication":"https://pith.science/pith/OGKHAMQLEO4XAUWI6O4PSKE3EF/action/replication_record"}},"created_at":"2026-05-18T01:22:33.011156+00:00","updated_at":"2026-05-18T01:22:33.011156+00:00"}