{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BDC52R26YFZDFCY6I4PMJPWQLN","short_pith_number":"pith:BDC52R26","schema_version":"1.0","canonical_sha256":"08c5dd475ec172328b1e471ec4bed05b6cc9a040232c63054b7b82de83728d67","source":{"kind":"arxiv","id":"2506.19235","version":1},"attestation_state":"computed","paper":{"title":"RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lianlei Shan, Xingkai Ren, Yao Hu, Ying Qi, Yu Xie","submitted_at":"2025-06-24T01:39:34Z","abstract_excerpt":"Traditional recommendation systems often grapple with \"filter bubbles\", underutilization of external knowledge, and a disconnect between model optimization and business policy iteration. To address these limitations, this paper introduces RecLLM-R1, a novel recommendation framework leveraging Large Language Models (LLMs) and drawing inspiration from the DeepSeek R1 methodology. The framework initiates by transforming user profiles, historical interactions, and multi-faceted item attributes into LLM-interpretable natural language prompts through a carefully engineered data construction process."},"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":"2506.19235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-24T01:39:34Z","cross_cats_sorted":[],"title_canon_sha256":"44b6546d5e579bbd83676aa526513af872a08f25f6b888e4d0a332e7f05b24ec","abstract_canon_sha256":"08bd0ae2baa7dd66816771823fa3ed1f6ca7483b44ddcb5fddf08ee813c3d81d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:11.931342Z","signature_b64":"8ZKkshFzsaIGvYH8oYh+KvehKBQ3Br1QEH7ozGYkixjQg6gBdHP0CuSClSawNuDhnxkdB7ceujiAEHbza7QQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08c5dd475ec172328b1e471ec4bed05b6cc9a040232c63054b7b82de83728d67","last_reissued_at":"2026-07-05T11:26:11.930868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:11.930868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lianlei Shan, Xingkai Ren, Yao Hu, Ying Qi, Yu Xie","submitted_at":"2025-06-24T01:39:34Z","abstract_excerpt":"Traditional recommendation systems often grapple with \"filter bubbles\", underutilization of external knowledge, and a disconnect between model optimization and business policy iteration. To address these limitations, this paper introduces RecLLM-R1, a novel recommendation framework leveraging Large Language Models (LLMs) and drawing inspiration from the DeepSeek R1 methodology. The framework initiates by transforming user profiles, historical interactions, and multi-faceted item attributes into LLM-interpretable natural language prompts through a carefully engineered data construction process."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19235","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/2506.19235/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":"2506.19235","created_at":"2026-07-05T11:26:11.930927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19235v1","created_at":"2026-07-05T11:26:11.930927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19235","created_at":"2026-07-05T11:26:11.930927+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDC52R26YFZD","created_at":"2026-07-05T11:26:11.930927+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDC52R26YFZDFCY6","created_at":"2026-07-05T11:26:11.930927+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDC52R26","created_at":"2026-07-05T11:26:11.930927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27684","citing_title":"Intuition-Guided Latent Reasoning for LLM-Based Recommendation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11874","citing_title":"RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN","json":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN.json","graph_json":"https://pith.science/api/pith-number/BDC52R26YFZDFCY6I4PMJPWQLN/graph.json","events_json":"https://pith.science/api/pith-number/BDC52R26YFZDFCY6I4PMJPWQLN/events.json","paper":"https://pith.science/paper/BDC52R26"},"agent_actions":{"view_html":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN","download_json":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN.json","view_paper":"https://pith.science/paper/BDC52R26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19235&json=true","fetch_graph":"https://pith.science/api/pith-number/BDC52R26YFZDFCY6I4PMJPWQLN/graph.json","fetch_events":"https://pith.science/api/pith-number/BDC52R26YFZDFCY6I4PMJPWQLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN/action/storage_attestation","attest_author":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN/action/author_attestation","sign_citation":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN/action/citation_signature","submit_replication":"https://pith.science/pith/BDC52R26YFZDFCY6I4PMJPWQLN/action/replication_record"}},"created_at":"2026-07-05T11:26:11.930927+00:00","updated_at":"2026-07-05T11:26:11.930927+00:00"}