{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5CBMF264YJAFLHWD2JQOBVKMHY","short_pith_number":"pith:5CBMF264","schema_version":"1.0","canonical_sha256":"e882c2ebdcc240559ec3d260e0d54c3e10843ae85f812bccf933cbe132d56bbf","source":{"kind":"arxiv","id":"2312.14878","version":1},"attestation_state":"computed","paper":{"title":"Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Filippos Christianos, Georgios Papoudakis, Haitham Bou-Ammar, James Doran, Jiacheng Liu, Jianye Hao, Jingxuan Chen, Jun Wang, Khyati Khandelwal, Kun Shao, Matthieu Zimmer, Thomas Coste, Xidong Feng, Yicheng Luo, Zheng Xiong, Zhihao Wu","submitted_at":"2023-12-22T17:57:57Z","abstract_excerpt":"A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack of generality across multiple tasks and the need for a large amount of training data. The leading cause is that it cannot effectively integrate prior information into the perception-action cycle when devising the policy. Large language models (LLMs) emerged as a fundamental way to incorporate cross-domain knowledge into AI agents but lack crucial learning and"},"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":"2312.14878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-22T17:57:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb833f30147476dd3c750948d1319f6d8f167898ba3b064b5b9b8ab95a8810e6","abstract_canon_sha256":"022f11a78b9c3dee0cf154e19a508a91edf2ccf32737e7585e3961d55d674d3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:21.444099Z","signature_b64":"foPlgKFZ3k0Dw5t7C+4PgsJ6/BckdiGxDn79rm7VZVmG3lmRw5pwVFyWKHjcQsbzRTiAvACHWemTqmyqp1UBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e882c2ebdcc240559ec3d260e0d54c3e10843ae85f812bccf933cbe132d56bbf","last_reissued_at":"2026-07-05T07:27:21.443586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:21.443586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Filippos Christianos, Georgios Papoudakis, Haitham Bou-Ammar, James Doran, Jiacheng Liu, Jianye Hao, Jingxuan Chen, Jun Wang, Khyati Khandelwal, Kun Shao, Matthieu Zimmer, Thomas Coste, Xidong Feng, Yicheng Luo, Zheng Xiong, Zhihao Wu","submitted_at":"2023-12-22T17:57:57Z","abstract_excerpt":"A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack of generality across multiple tasks and the need for a large amount of training data. The leading cause is that it cannot effectively integrate prior information into the perception-action cycle when devising the policy. Large language models (LLMs) emerged as a fundamental way to incorporate cross-domain knowledge into AI agents but lack crucial learning and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14878","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/2312.14878/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":"2312.14878","created_at":"2026-07-05T07:27:21.443649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14878v1","created_at":"2026-07-05T07:27:21.443649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14878","created_at":"2026-07-05T07:27:21.443649+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CBMF264YJAF","created_at":"2026-07-05T07:27:21.443649+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CBMF264YJAFLHWD","created_at":"2026-07-05T07:27:21.443649+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CBMF264","created_at":"2026-07-05T07:27:21.443649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.02170","citing_title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26041","citing_title":"Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY","json":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY.json","graph_json":"https://pith.science/api/pith-number/5CBMF264YJAFLHWD2JQOBVKMHY/graph.json","events_json":"https://pith.science/api/pith-number/5CBMF264YJAFLHWD2JQOBVKMHY/events.json","paper":"https://pith.science/paper/5CBMF264"},"agent_actions":{"view_html":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY","download_json":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY.json","view_paper":"https://pith.science/paper/5CBMF264","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14878&json=true","fetch_graph":"https://pith.science/api/pith-number/5CBMF264YJAFLHWD2JQOBVKMHY/graph.json","fetch_events":"https://pith.science/api/pith-number/5CBMF264YJAFLHWD2JQOBVKMHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY/action/storage_attestation","attest_author":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY/action/author_attestation","sign_citation":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY/action/citation_signature","submit_replication":"https://pith.science/pith/5CBMF264YJAFLHWD2JQOBVKMHY/action/replication_record"}},"created_at":"2026-07-05T07:27:21.443649+00:00","updated_at":"2026-07-05T07:27:21.443649+00:00"}