{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5MM7G2TETHSVEPL732GXQZ32WS","short_pith_number":"pith:5MM7G2TE","schema_version":"1.0","canonical_sha256":"eb19f36a6499e5523d7fde8d78677ab4b063df19eb2bb8cf92dbde3ef52bb273","source":{"kind":"arxiv","id":"2605.24812","version":1},"attestation_state":"computed","paper":{"title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Qinjian Zhao, Sumon Biswas, Xiaoyu Xia, Zhihao Dou, Zhongwei Wan","submitted_at":"2026-05-24T01:47:30Z","abstract_excerpt":"Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing test cases or inefficient complexity). While recent approaches such as Chain-of-Thought (CoT) and multi-agent systems (MAS) introduce planning, their limited role specialization and coordination hinder performance on complex tasks. To address the challenges of coordination and specialization in multi-agent code generation, we propose Collaborative Reinforceme"},"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":"2605.24812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-24T01:47:30Z","cross_cats_sorted":[],"title_canon_sha256":"770a56af7df1d7bceb2e541516ecfe27b5f64203e7c3b0ed8222251d1ec19e0a","abstract_canon_sha256":"fb1804d6895819b13361bb584e8cd88c304aa8af90abf1d27cb9c87790c1c865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:59.601569Z","signature_b64":"Cuds8+/Ikf8loOaeG2aHcIhWW8XMw/k6EZfGU5JwkpepfxUu2d7OaSnopObo5GDpdmOQJ0BIyyWLvVyW2U2CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb19f36a6499e5523d7fde8d78677ab4b063df19eb2bb8cf92dbde3ef52bb273","last_reissued_at":"2026-05-26T01:03:59.601028Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:59.601028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Qinjian Zhao, Sumon Biswas, Xiaoyu Xia, Zhihao Dou, Zhongwei Wan","submitted_at":"2026-05-24T01:47:30Z","abstract_excerpt":"Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing test cases or inefficient complexity). While recent approaches such as Chain-of-Thought (CoT) and multi-agent systems (MAS) introduce planning, their limited role specialization and coordination hinder performance on complex tasks. To address the challenges of coordination and specialization in multi-agent code generation, we propose Collaborative Reinforceme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24812","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/2605.24812/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":"2605.24812","created_at":"2026-05-26T01:03:59.601109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24812v1","created_at":"2026-05-26T01:03:59.601109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24812","created_at":"2026-05-26T01:03:59.601109+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MM7G2TETHSV","created_at":"2026-05-26T01:03:59.601109+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MM7G2TETHSVEPL7","created_at":"2026-05-26T01:03:59.601109+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MM7G2TE","created_at":"2026-05-26T01:03:59.601109+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/5MM7G2TETHSVEPL732GXQZ32WS","json":"https://pith.science/pith/5MM7G2TETHSVEPL732GXQZ32WS.json","graph_json":"https://pith.science/api/pith-number/5MM7G2TETHSVEPL732GXQZ32WS/graph.json","events_json":"https://pith.science/api/pith-number/5MM7G2TETHSVEPL732GXQZ32WS/events.json","paper":"https://pith.science/paper/5MM7G2TE"},"agent_actions":{"view_html":"https://pith.science/pith/5MM7G2TETHSVEPL732GXQZ32WS","download_json":"https://pith.science/pith/5MM7G2TETHSVEPL732GXQZ32WS.json","view_paper":"https://pith.science/paper/5MM7G2TE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24812&json=true","fetch_graph":"https://pith.science/api/pith-number/5MM7G2TETHSVEPL732GXQZ32WS/graph.json","fetch_events":"https://pith.science/api/pith-number/5MM7G2TETHSVEPL732GXQZ32WS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MM7G2TETHSVEPL732GXQZ32WS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MM7G2TETHSVEPL732GXQZ32WS/action/storage_attestation","attest_author":"https://pith.science/pith/5MM7G2TETHSVEPL732GXQZ32WS/action/author_attestation","sign_citation":"https://pith.science/pith/5MM7G2TETHSVEPL732GXQZ32WS/action/citation_signature","submit_replication":"https://pith.science/pith/5MM7G2TETHSVEPL732GXQZ32WS/action/replication_record"}},"created_at":"2026-05-26T01:03:59.601109+00:00","updated_at":"2026-05-26T01:03:59.601109+00:00"}