{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DQWURHJKUOHFQPN6KRBGISYCNF","short_pith_number":"pith:DQWURHJK","schema_version":"1.0","canonical_sha256":"1c2d489d2aa38e583dbe5442644b02695841cc98021c273af6013d5425b7ac1e","source":{"kind":"arxiv","id":"2607.01846","version":1},"attestation_state":"computed","paper":{"title":"CLAP: Closed-Loop Training, Evaluation, and Release Control for Domain Agent Post-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyang Zhao, Fangfei Li, Feng Tian, Long Wang, Lv Guo, Zhiyue Zheng","submitted_at":"2026-07-02T08:07:56Z","abstract_excerpt":"Domain agents often face noisy business data, uncertain post-training gains, offline/application mismatch, and adapter-release risk. This paper presents CLAP (Closed-Loop Agent Post-training), a closed-loop method that converts business data into structured SFT samples, decision-preference samples, holdout sets, risk diagnostics, and release-gate records. CLAP combines data validation, target/evidence normalization, reward/KL diagnosis, offline gates, and application-chain replay to decide whether an adapter is suitable for the target application chain. On five anonymized manufacturing-scenari"},"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":"2607.01846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T08:07:56Z","cross_cats_sorted":[],"title_canon_sha256":"ab2200601a9b209df64204db5dbf31f6fc79f15ca46e8fa833ce561d0160bef8","abstract_canon_sha256":"437bb105c0768600729f2f91021a9ea5f4680603a4c796a6ed7626b1a78948eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:31.524047Z","signature_b64":"bzdeu4Orh3nWHrkyfQh+wRMN16CKxD5QKe3LQ3ipcUpzGhQc6Sk6a5TJ/U9CrVncBQiVvs3VVmcWpWrcvpe6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c2d489d2aa38e583dbe5442644b02695841cc98021c273af6013d5425b7ac1e","last_reissued_at":"2026-07-03T01:17:31.523662Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:31.523662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLAP: Closed-Loop Training, Evaluation, and Release Control for Domain Agent Post-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyang Zhao, Fangfei Li, Feng Tian, Long Wang, Lv Guo, Zhiyue Zheng","submitted_at":"2026-07-02T08:07:56Z","abstract_excerpt":"Domain agents often face noisy business data, uncertain post-training gains, offline/application mismatch, and adapter-release risk. This paper presents CLAP (Closed-Loop Agent Post-training), a closed-loop method that converts business data into structured SFT samples, decision-preference samples, holdout sets, risk diagnostics, and release-gate records. CLAP combines data validation, target/evidence normalization, reward/KL diagnosis, offline gates, and application-chain replay to decide whether an adapter is suitable for the target application chain. On five anonymized manufacturing-scenari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01846","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/2607.01846/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":"2607.01846","created_at":"2026-07-03T01:17:31.523710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01846v1","created_at":"2026-07-03T01:17:31.523710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01846","created_at":"2026-07-03T01:17:31.523710+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQWURHJKUOHF","created_at":"2026-07-03T01:17:31.523710+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQWURHJKUOHFQPN6","created_at":"2026-07-03T01:17:31.523710+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQWURHJK","created_at":"2026-07-03T01:17:31.523710+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/DQWURHJKUOHFQPN6KRBGISYCNF","json":"https://pith.science/pith/DQWURHJKUOHFQPN6KRBGISYCNF.json","graph_json":"https://pith.science/api/pith-number/DQWURHJKUOHFQPN6KRBGISYCNF/graph.json","events_json":"https://pith.science/api/pith-number/DQWURHJKUOHFQPN6KRBGISYCNF/events.json","paper":"https://pith.science/paper/DQWURHJK"},"agent_actions":{"view_html":"https://pith.science/pith/DQWURHJKUOHFQPN6KRBGISYCNF","download_json":"https://pith.science/pith/DQWURHJKUOHFQPN6KRBGISYCNF.json","view_paper":"https://pith.science/paper/DQWURHJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01846&json=true","fetch_graph":"https://pith.science/api/pith-number/DQWURHJKUOHFQPN6KRBGISYCNF/graph.json","fetch_events":"https://pith.science/api/pith-number/DQWURHJKUOHFQPN6KRBGISYCNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQWURHJKUOHFQPN6KRBGISYCNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQWURHJKUOHFQPN6KRBGISYCNF/action/storage_attestation","attest_author":"https://pith.science/pith/DQWURHJKUOHFQPN6KRBGISYCNF/action/author_attestation","sign_citation":"https://pith.science/pith/DQWURHJKUOHFQPN6KRBGISYCNF/action/citation_signature","submit_replication":"https://pith.science/pith/DQWURHJKUOHFQPN6KRBGISYCNF/action/replication_record"}},"created_at":"2026-07-03T01:17:31.523710+00:00","updated_at":"2026-07-03T01:17:31.523710+00:00"}