{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VYINIHFXKBYFQK4NNJF2MXO4Z4","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"52cff8fbb5102c429dc2d2dfdc4ef0d565736a4f9869e87ed4672dc0d4832b75","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-27T05:09:41Z","title_canon_sha256":"e05e27bfefa7438b04423d0e937336ee129d6351f4e0008a2a075059375c7df7"},"schema_version":"1.0","source":{"id":"2607.24007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24007","created_at":"2026-07-28T01:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24007v1","created_at":"2026-07-28T01:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24007","created_at":"2026-07-28T01:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"VYINIHFXKBYF","created_at":"2026-07-28T01:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"VYINIHFXKBYFQK4N","created_at":"2026-07-28T01:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"VYINIHFX","created_at":"2026-07-28T01:23:40Z"}],"graph_snapshots":[{"event_id":"sha256:77dce1951be57a4a311551f458ac62233eae4b45f77ad5d79a5dd7bdb43b9bc3","target":"graph","created_at":"2026-07-28T01:23:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.24007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit contextual optimization from the perspective of policy class design. A desirable policy class should be expressive enough to learn rich context-decision relationships, should enforce hard feasibility constraints rather than soft penalty terms, and should remain smooth enough for gradient-based training on downstream decision losses. Existing approaches usually emphasize only part of these requirements. We propose Legendre-regularized policies, which parameterize decisions as solutions of regularized optimization problems over the original feasible region. This construction yields po","authors_text":"Rui Chen, Yijie Wang, Zikun Lin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24007","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8b08c02a13293ff53f265e5ee48c85f93c127a42e71dff0b08f178242257c972","target":"record","created_at":"2026-07-28T01:23:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"52cff8fbb5102c429dc2d2dfdc4ef0d565736a4f9869e87ed4672dc0d4832b75","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-27T05:09:41Z","title_canon_sha256":"e05e27bfefa7438b04423d0e937336ee129d6351f4e0008a2a075059375c7df7"},"schema_version":"1.0","source":{"id":"2607.24007","kind":"arxiv","version":1}},"canonical_sha256":"ae10d41cb75070582b8d6a4ba65ddccf0819633d38293ea3255ef537add007d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae10d41cb75070582b8d6a4ba65ddccf0819633d38293ea3255ef537add007d2","first_computed_at":"2026-07-28T01:23:40.765309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:40.765309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SFAMef5OZK1ah4kvDd7tkZBRi9HlyU73sRCZK3YGfK2jJwWLtPlL9juDifl1MgCubSIBCujVoyLsZUlvS9AMBA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:40.766127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b08c02a13293ff53f265e5ee48c85f93c127a42e71dff0b08f178242257c972","sha256:77dce1951be57a4a311551f458ac62233eae4b45f77ad5d79a5dd7bdb43b9bc3","sha256:679c432f44f78ee2a66b6a4c02da07fedb82356be7587454d5ca97a9db4543c7"],"state_sha256":"4c2f88a755dbbc2865a3909a55bb3813ad7b98b807e39285a78fb316fca88534"}