{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DTYXTYZWRPNLVX2ZA7LMZYYMJ5","short_pith_number":"pith:DTYXTYZW","schema_version":"1.0","canonical_sha256":"1cf179e3368bdabadf5907d6cce30c4f65fb23f8d57080e72c9dfd5e4c558b49","source":{"kind":"arxiv","id":"2102.07567","version":3},"attestation_state":"computed","paper":{"title":"Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ajaykrishna Karthikeyan, Nagarajan Natarajan, Naman Jain, Prateek Jain","submitted_at":"2021-02-15T14:10:07Z","abstract_excerpt":"Decision trees provide a rich family of highly non-linear but efficient models, due to which they continue to be the go-to family of predictive models by practitioners across domains. But learning trees is challenging due to their discrete decision boundaries. The state-of-the-art (SOTA) techniques resort to (a) learning \\textit{soft} trees thereby losing logarithmic inference time; or (b) using methods tailored to specific supervised learning settings, requiring access to labeled examples and loss function. In this work, by leveraging techniques like overparameterization and straight-through "},"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":"2102.07567","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-15T14:10:07Z","cross_cats_sorted":[],"title_canon_sha256":"16d352f1cbc7416fb08c46477ada46e354fb50e1b60444f27e1bfc43959e5e3e","abstract_canon_sha256":"dc170a837f225b81722c5187adc84c864b8dcf3428909ec20475d8f9aa63f888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:08.597916Z","signature_b64":"HVpRoifUFjgrmawvN8htyPhOo2YTcb3/SGE4RISLAKLXx/GyqKEIV8pDelyhBCLdTYYhDRyozI/1H8R3xLqIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cf179e3368bdabadf5907d6cce30c4f65fb23f8d57080e72c9dfd5e4c558b49","last_reissued_at":"2026-07-05T05:02:08.597409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:08.597409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ajaykrishna Karthikeyan, Nagarajan Natarajan, Naman Jain, Prateek Jain","submitted_at":"2021-02-15T14:10:07Z","abstract_excerpt":"Decision trees provide a rich family of highly non-linear but efficient models, due to which they continue to be the go-to family of predictive models by practitioners across domains. But learning trees is challenging due to their discrete decision boundaries. The state-of-the-art (SOTA) techniques resort to (a) learning \\textit{soft} trees thereby losing logarithmic inference time; or (b) using methods tailored to specific supervised learning settings, requiring access to labeled examples and loss function. In this work, by leveraging techniques like overparameterization and straight-through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07567","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.07567/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2102.07567","created_at":"2026-07-05T05:02:08.597477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07567v3","created_at":"2026-07-05T05:02:08.597477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07567","created_at":"2026-07-05T05:02:08.597477+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTYXTYZWRPNL","created_at":"2026-07-05T05:02:08.597477+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTYXTYZWRPNLVX2Z","created_at":"2026-07-05T05:02:08.597477+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTYXTYZW","created_at":"2026-07-05T05:02:08.597477+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/DTYXTYZWRPNLVX2ZA7LMZYYMJ5","json":"https://pith.science/pith/DTYXTYZWRPNLVX2ZA7LMZYYMJ5.json","graph_json":"https://pith.science/api/pith-number/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/graph.json","events_json":"https://pith.science/api/pith-number/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/events.json","paper":"https://pith.science/paper/DTYXTYZW"},"agent_actions":{"view_html":"https://pith.science/pith/DTYXTYZWRPNLVX2ZA7LMZYYMJ5","download_json":"https://pith.science/pith/DTYXTYZWRPNLVX2ZA7LMZYYMJ5.json","view_paper":"https://pith.science/paper/DTYXTYZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07567&json=true","fetch_graph":"https://pith.science/api/pith-number/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/action/storage_attestation","attest_author":"https://pith.science/pith/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/action/author_attestation","sign_citation":"https://pith.science/pith/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/action/citation_signature","submit_replication":"https://pith.science/pith/DTYXTYZWRPNLVX2ZA7LMZYYMJ5/action/replication_record"}},"created_at":"2026-07-05T05:02:08.597477+00:00","updated_at":"2026-07-05T05:02:08.597477+00:00"}