{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AVZM7DIVKL2JLLWMCRRKHWR3QT","short_pith_number":"pith:AVZM7DIV","schema_version":"1.0","canonical_sha256":"0572cf8d1552f495aecc1462a3da3b84f35da9d372212fe2fda5c314c3fda2d8","source":{"kind":"arxiv","id":"2606.07088","version":1},"attestation_state":"computed","paper":{"title":"Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Jianchen Hu, Kang Liu, Ziyu Qu","submitted_at":"2026-06-05T09:35:22Z","abstract_excerpt":"Stochastic constrained decision-making requires optimizing performance objectives while enforcing statistical requirements such as safety or fairness. However, standard primal--dual methods struggle to update multipliers robustly under stochastic mini-batch feedback, as the noise of mini-batch gradients and constraint estimates can be directly accumulated into the multiplier memory. To address this issue, we propose Residual-Controlled Multiplier Learning (RCML), which reformulates multiplier updating as projected-pressure feedback. The central idea is to decompose the projected multiplier int"},"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":"2606.07088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T09:35:22Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"5ebb6312d2eec21892596400d136dc2eb429d80ff963f9ea97ea9a867a9437fa","abstract_canon_sha256":"aa95da036413e9a0e47998bd3a1ac96d128fd8424165e77f7f748473ad616d84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:45.544579Z","signature_b64":"vcaJK3/ShC9AaWhUxDUFhejPvtGXgpJKJDqb7t4cYmrDjBTpDOaFoEV5P0/bWdD8fHHEaSRSTGMy8AX0aFSrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0572cf8d1552f495aecc1462a3da3b84f35da9d372212fe2fda5c314c3fda2d8","last_reissued_at":"2026-06-08T01:04:45.543769Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:45.543769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Jianchen Hu, Kang Liu, Ziyu Qu","submitted_at":"2026-06-05T09:35:22Z","abstract_excerpt":"Stochastic constrained decision-making requires optimizing performance objectives while enforcing statistical requirements such as safety or fairness. However, standard primal--dual methods struggle to update multipliers robustly under stochastic mini-batch feedback, as the noise of mini-batch gradients and constraint estimates can be directly accumulated into the multiplier memory. To address this issue, we propose Residual-Controlled Multiplier Learning (RCML), which reformulates multiplier updating as projected-pressure feedback. The central idea is to decompose the projected multiplier int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07088","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/2606.07088/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":"2606.07088","created_at":"2026-06-08T01:04:45.543872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07088v1","created_at":"2026-06-08T01:04:45.543872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07088","created_at":"2026-06-08T01:04:45.543872+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVZM7DIVKL2J","created_at":"2026-06-08T01:04:45.543872+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVZM7DIVKL2JLLWM","created_at":"2026-06-08T01:04:45.543872+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVZM7DIV","created_at":"2026-06-08T01:04:45.543872+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/AVZM7DIVKL2JLLWMCRRKHWR3QT","json":"https://pith.science/pith/AVZM7DIVKL2JLLWMCRRKHWR3QT.json","graph_json":"https://pith.science/api/pith-number/AVZM7DIVKL2JLLWMCRRKHWR3QT/graph.json","events_json":"https://pith.science/api/pith-number/AVZM7DIVKL2JLLWMCRRKHWR3QT/events.json","paper":"https://pith.science/paper/AVZM7DIV"},"agent_actions":{"view_html":"https://pith.science/pith/AVZM7DIVKL2JLLWMCRRKHWR3QT","download_json":"https://pith.science/pith/AVZM7DIVKL2JLLWMCRRKHWR3QT.json","view_paper":"https://pith.science/paper/AVZM7DIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07088&json=true","fetch_graph":"https://pith.science/api/pith-number/AVZM7DIVKL2JLLWMCRRKHWR3QT/graph.json","fetch_events":"https://pith.science/api/pith-number/AVZM7DIVKL2JLLWMCRRKHWR3QT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVZM7DIVKL2JLLWMCRRKHWR3QT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVZM7DIVKL2JLLWMCRRKHWR3QT/action/storage_attestation","attest_author":"https://pith.science/pith/AVZM7DIVKL2JLLWMCRRKHWR3QT/action/author_attestation","sign_citation":"https://pith.science/pith/AVZM7DIVKL2JLLWMCRRKHWR3QT/action/citation_signature","submit_replication":"https://pith.science/pith/AVZM7DIVKL2JLLWMCRRKHWR3QT/action/replication_record"}},"created_at":"2026-06-08T01:04:45.543872+00:00","updated_at":"2026-06-08T01:04:45.543872+00:00"}