{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:O3APHH5MEHYQT2SBMXCCWI7FWM","short_pith_number":"pith:O3APHH5M","schema_version":"1.0","canonical_sha256":"76c0f39fac21f109ea4165c42b23e5b3150b3c98a9841e5cf20b760f14c13727","source":{"kind":"arxiv","id":"1806.04245","version":1},"attestation_state":"computed","paper":{"title":"Learning to Speed Up Structured Output Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Vivek Srikumar, Xingyuan Pan","submitted_at":"2018-06-11T21:06:51Z","abstract_excerpt":"Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier under the learning-to-search approach. As the structured classifier predicts more examples, the speedup classifier will operate as a learned heuristic to guide search to favorable regions of the output space. We present a mistake bound for the speedup classifier and identify infer"},"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":"1806.04245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-11T21:06:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d96368817f36474586134eeb254418c92669e42198889dad34f971e17173f2ef","abstract_canon_sha256":"b2558239c4274f00ba91ecee5391f4f6af45279b19449128982463e251fbef88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:36.129253Z","signature_b64":"wZLr0kZ48l3y1BEpljjiwMuqp5j+7vbZ5f/xrzvYDckYnUTN3109z30IJeOlVMqIfMITurg7kHZtnpnbVaYuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76c0f39fac21f109ea4165c42b23e5b3150b3c98a9841e5cf20b760f14c13727","last_reissued_at":"2026-05-18T00:13:36.128730Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:36.128730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Speed Up Structured Output Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Vivek Srikumar, Xingyuan Pan","submitted_at":"2018-06-11T21:06:51Z","abstract_excerpt":"Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier under the learning-to-search approach. As the structured classifier predicts more examples, the speedup classifier will operate as a learned heuristic to guide search to favorable regions of the output space. We present a mistake bound for the speedup classifier and identify infer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04245","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":"1806.04245","created_at":"2026-05-18T00:13:36.128807+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04245v1","created_at":"2026-05-18T00:13:36.128807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04245","created_at":"2026-05-18T00:13:36.128807+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3APHH5MEHYQ","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3APHH5MEHYQT2SB","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3APHH5M","created_at":"2026-05-18T12:32:40.477152+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/O3APHH5MEHYQT2SBMXCCWI7FWM","json":"https://pith.science/pith/O3APHH5MEHYQT2SBMXCCWI7FWM.json","graph_json":"https://pith.science/api/pith-number/O3APHH5MEHYQT2SBMXCCWI7FWM/graph.json","events_json":"https://pith.science/api/pith-number/O3APHH5MEHYQT2SBMXCCWI7FWM/events.json","paper":"https://pith.science/paper/O3APHH5M"},"agent_actions":{"view_html":"https://pith.science/pith/O3APHH5MEHYQT2SBMXCCWI7FWM","download_json":"https://pith.science/pith/O3APHH5MEHYQT2SBMXCCWI7FWM.json","view_paper":"https://pith.science/paper/O3APHH5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04245&json=true","fetch_graph":"https://pith.science/api/pith-number/O3APHH5MEHYQT2SBMXCCWI7FWM/graph.json","fetch_events":"https://pith.science/api/pith-number/O3APHH5MEHYQT2SBMXCCWI7FWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3APHH5MEHYQT2SBMXCCWI7FWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3APHH5MEHYQT2SBMXCCWI7FWM/action/storage_attestation","attest_author":"https://pith.science/pith/O3APHH5MEHYQT2SBMXCCWI7FWM/action/author_attestation","sign_citation":"https://pith.science/pith/O3APHH5MEHYQT2SBMXCCWI7FWM/action/citation_signature","submit_replication":"https://pith.science/pith/O3APHH5MEHYQT2SBMXCCWI7FWM/action/replication_record"}},"created_at":"2026-05-18T00:13:36.128807+00:00","updated_at":"2026-05-18T00:13:36.128807+00:00"}