{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WV7LPTVN6NZGDMUHIMZ3SSR6GH","short_pith_number":"pith:WV7LPTVN","schema_version":"1.0","canonical_sha256":"b57eb7ceadf37261b2874333b94a3e31dc4a24de43420d1d5ea9d9f582881f92","source":{"kind":"arxiv","id":"2506.00252","version":1},"attestation_state":"computed","paper":{"title":"How hard is learning to cut? Trade-offs and sample complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Andrea Lodi, Sammy Khalife","submitted_at":"2025-05-30T21:41:01Z","abstract_excerpt":"In the recent years, branch-and-cut algorithms have been the target of data-driven approaches designed to enhance the decision making in different phases of the algorithm such as branching, or the choice of cutting planes (cuts). In particular, for cutting plane selection two score functions have been proposed in the literature to evaluate the quality of a cut: branch-and-cut tree size and gap closed. In this paper, we present new sample complexity lower bounds, valid for both scores. We show that for a wide family of classes $\\mathcal{F}$ that maps an instance to a cut, learning over an unkno"},"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":"2506.00252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-30T21:41:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d098c883eb9cf5f77ae08b2692a860e4153b5f132b3afe3738631e8c61e08507","abstract_canon_sha256":"89eedb77dd75f6a5f11fc4599f2d2d073005a98245eecf304d3a08a65868401d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:31.567179Z","signature_b64":"D67ueR9By1plpMZNahzRVxRaqJwP7FOff+EQUyFGjw843bVTVF+AKF1bCMzc2y/5lwXVE9ASqQIPVfpW74fSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b57eb7ceadf37261b2874333b94a3e31dc4a24de43420d1d5ea9d9f582881f92","last_reissued_at":"2026-07-05T11:13:31.566679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:31.566679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How hard is learning to cut? Trade-offs and sample complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Andrea Lodi, Sammy Khalife","submitted_at":"2025-05-30T21:41:01Z","abstract_excerpt":"In the recent years, branch-and-cut algorithms have been the target of data-driven approaches designed to enhance the decision making in different phases of the algorithm such as branching, or the choice of cutting planes (cuts). In particular, for cutting plane selection two score functions have been proposed in the literature to evaluate the quality of a cut: branch-and-cut tree size and gap closed. In this paper, we present new sample complexity lower bounds, valid for both scores. We show that for a wide family of classes $\\mathcal{F}$ that maps an instance to a cut, learning over an unkno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00252","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.00252/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":"2506.00252","created_at":"2026-07-05T11:13:31.566759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00252v1","created_at":"2026-07-05T11:13:31.566759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00252","created_at":"2026-07-05T11:13:31.566759+00:00"},{"alias_kind":"pith_short_12","alias_value":"WV7LPTVN6NZG","created_at":"2026-07-05T11:13:31.566759+00:00"},{"alias_kind":"pith_short_16","alias_value":"WV7LPTVN6NZGDMUH","created_at":"2026-07-05T11:13:31.566759+00:00"},{"alias_kind":"pith_short_8","alias_value":"WV7LPTVN","created_at":"2026-07-05T11:13:31.566759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07239","citing_title":"Sample Complexity of Stochastic Optimization with Integer Variables","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH","json":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH.json","graph_json":"https://pith.science/api/pith-number/WV7LPTVN6NZGDMUHIMZ3SSR6GH/graph.json","events_json":"https://pith.science/api/pith-number/WV7LPTVN6NZGDMUHIMZ3SSR6GH/events.json","paper":"https://pith.science/paper/WV7LPTVN"},"agent_actions":{"view_html":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH","download_json":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH.json","view_paper":"https://pith.science/paper/WV7LPTVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00252&json=true","fetch_graph":"https://pith.science/api/pith-number/WV7LPTVN6NZGDMUHIMZ3SSR6GH/graph.json","fetch_events":"https://pith.science/api/pith-number/WV7LPTVN6NZGDMUHIMZ3SSR6GH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH/action/storage_attestation","attest_author":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH/action/author_attestation","sign_citation":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH/action/citation_signature","submit_replication":"https://pith.science/pith/WV7LPTVN6NZGDMUHIMZ3SSR6GH/action/replication_record"}},"created_at":"2026-07-05T11:13:31.566759+00:00","updated_at":"2026-07-05T11:13:31.566759+00:00"}