{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XH2KGETPNBDECLUA5FCXQ6S7Q6","short_pith_number":"pith:XH2KGETP","schema_version":"1.0","canonical_sha256":"b9f4a3126f6846412e80e945787a5f8790ef72d6c20c37ffb4b5c142fba23a45","source":{"kind":"arxiv","id":"2411.11504","version":1},"attestation_state":"computed","paper":{"title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.AI","authors_text":"Ben He, Bowen Yu, Boxi Cao, Hongyu Lin, Jie Lou, Le Sun, Xianpei Han, Xinyan Guan, Xinyu Lu, Yanjiang Liu, Yaojie Lu","submitted_at":"2024-11-18T12:04:52Z","abstract_excerpt":"The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models presents significant challenges in providing effective supervision signals necessary for further enhancing their capabilities. Consequently, there is an urgent need to explore novel supervision signals and technical approaches. In this paper, we propose verifier engineering, a novel post-training paradigm specifically designed for the era of foundation models. The core of verifier engineering involves leveraging a s"},"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":"2411.11504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-18T12:04:52Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"6ad6a13aaebbe89be4faf04cc4031f60a62a421271f221c5d76d25e5035c30b3","abstract_canon_sha256":"d7f65042e8480050e5669accafc955f7ac1d01adeda99b1ad8ce9f77a8b13879"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:57.232545Z","signature_b64":"5TWqKf9niZV0bzns1xKIBwJmLumFJ1dZwSKisSGqbKeh0mCyf1gHTU0wE451ANjVMc04k/Nl/DUlEk44n7qXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9f4a3126f6846412e80e945787a5f8790ef72d6c20c37ffb4b5c142fba23a45","last_reissued_at":"2026-07-05T09:36:57.232054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:57.232054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.AI","authors_text":"Ben He, Bowen Yu, Boxi Cao, Hongyu Lin, Jie Lou, Le Sun, Xianpei Han, Xinyan Guan, Xinyu Lu, Yanjiang Liu, Yaojie Lu","submitted_at":"2024-11-18T12:04:52Z","abstract_excerpt":"The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models presents significant challenges in providing effective supervision signals necessary for further enhancing their capabilities. Consequently, there is an urgent need to explore novel supervision signals and technical approaches. In this paper, we propose verifier engineering, a novel post-training paradigm specifically designed for the era of foundation models. The core of verifier engineering involves leveraging a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11504","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/2411.11504/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":"2411.11504","created_at":"2026-07-05T09:36:57.232111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11504v1","created_at":"2026-07-05T09:36:57.232111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11504","created_at":"2026-07-05T09:36:57.232111+00:00"},{"alias_kind":"pith_short_12","alias_value":"XH2KGETPNBDE","created_at":"2026-07-05T09:36:57.232111+00:00"},{"alias_kind":"pith_short_16","alias_value":"XH2KGETPNBDECLUA","created_at":"2026-07-05T09:36:57.232111+00:00"},{"alias_kind":"pith_short_8","alias_value":"XH2KGETP","created_at":"2026-07-05T09:36:57.232111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22446","citing_title":"Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12652","citing_title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":224,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07941","citing_title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6","json":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6.json","graph_json":"https://pith.science/api/pith-number/XH2KGETPNBDECLUA5FCXQ6S7Q6/graph.json","events_json":"https://pith.science/api/pith-number/XH2KGETPNBDECLUA5FCXQ6S7Q6/events.json","paper":"https://pith.science/paper/XH2KGETP"},"agent_actions":{"view_html":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6","download_json":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6.json","view_paper":"https://pith.science/paper/XH2KGETP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11504&json=true","fetch_graph":"https://pith.science/api/pith-number/XH2KGETPNBDECLUA5FCXQ6S7Q6/graph.json","fetch_events":"https://pith.science/api/pith-number/XH2KGETPNBDECLUA5FCXQ6S7Q6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6/action/storage_attestation","attest_author":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6/action/author_attestation","sign_citation":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6/action/citation_signature","submit_replication":"https://pith.science/pith/XH2KGETPNBDECLUA5FCXQ6S7Q6/action/replication_record"}},"created_at":"2026-07-05T09:36:57.232111+00:00","updated_at":"2026-07-05T09:36:57.232111+00:00"}