{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WKTGWA46LL2UADJB4LRKXIJXR7","short_pith_number":"pith:WKTGWA46","schema_version":"1.0","canonical_sha256":"b2a66b039e5af5400d21e2e2aba1378fe41296a25dbe596f6b3f81d0653db5cc","source":{"kind":"arxiv","id":"2405.04324","version":1},"attestation_state":"computed","paper":{"title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.AI","authors_text":"Aanchal Goyal, Aditya Prasad, Adriana Meza Soria, Amith Singhee, Andrew Coleman, Asim Munawar, Bob Calio, Boris Lublinsky, Brian Belgodere, Carlos Fonseca, Chris Johnson, David D. Cox, Gaoyuan Zhang, Heiko Ludwig, Hima Patel, Ibrahim Abdelaziz, Kinjal Basu, Kun-Lung Wu, Manish Sethi, Mark Lewis, Matthew White, Matt Stallone, Maximilien de Bayser, Maxwell Crouse, Mayank Agarwal, Mayank Mishra, Michele Merler, Nirmit Desai, Parameswaran Selvam, Pavan Kapanipathi, Pengyuan Li, Petros Zerfos, Raju Pavuluri, Rameswar Panda, Ruchir Puri, Saptha Surendran, Seetharami Seelam, Shivdeep Singh, Shweta Salaria, Sophia Wen, Syed Zawad, Xuan-Hong Dang, Yan Koyfman, Yikang Shen, Yi Zhou, Yousaf Shah","submitted_at":"2024-05-07T13:50:40Z","abstract_excerpt":"Large Language Models (LLMs) trained on code are revolutionizing the software development process. Increasingly, code LLMs are being integrated into software development environments to improve the productivity of human programmers, and LLM-based agents are beginning to show promise for handling complex tasks autonomously. Realizing the full potential of code LLMs requires a wide range of capabilities, including code generation, fixing bugs, explaining and documenting code, maintaining repositories, and more. In this work, we introduce the Granite series of decoder-only code models for code ge"},"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":"2405.04324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-07T13:50:40Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"a2e70283d7e40e1fe6429040ab9cac89e8d4317cf2dd12945644873376940c09","abstract_canon_sha256":"f5d3288f44bc8dd65b23a61f103563a1bc7392853fe2c9f0b1b00f14f649e3b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:35.497607Z","signature_b64":"1SIByXYx6WzsDw25JHSynlsniSaeb9idrNKhITEMFfxf+GJoy9PxiZilCF5UIatQl6HiMTFaN1U0BuI7jH2PCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2a66b039e5af5400d21e2e2aba1378fe41296a25dbe596f6b3f81d0653db5cc","last_reissued_at":"2026-07-05T08:16:35.496998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:35.496998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.AI","authors_text":"Aanchal Goyal, Aditya Prasad, Adriana Meza Soria, Amith Singhee, Andrew Coleman, Asim Munawar, Bob Calio, Boris Lublinsky, Brian Belgodere, Carlos Fonseca, Chris Johnson, David D. Cox, Gaoyuan Zhang, Heiko Ludwig, Hima Patel, Ibrahim Abdelaziz, Kinjal Basu, Kun-Lung Wu, Manish Sethi, Mark Lewis, Matthew White, Matt Stallone, Maximilien de Bayser, Maxwell Crouse, Mayank Agarwal, Mayank Mishra, Michele Merler, Nirmit Desai, Parameswaran Selvam, Pavan Kapanipathi, Pengyuan Li, Petros Zerfos, Raju Pavuluri, Rameswar Panda, Ruchir Puri, Saptha Surendran, Seetharami Seelam, Shivdeep Singh, Shweta Salaria, Sophia Wen, Syed Zawad, Xuan-Hong Dang, Yan Koyfman, Yikang Shen, Yi Zhou, Yousaf Shah","submitted_at":"2024-05-07T13:50:40Z","abstract_excerpt":"Large Language Models (LLMs) trained on code are revolutionizing the software development process. Increasingly, code LLMs are being integrated into software development environments to improve the productivity of human programmers, and LLM-based agents are beginning to show promise for handling complex tasks autonomously. Realizing the full potential of code LLMs requires a wide range of capabilities, including code generation, fixing bugs, explaining and documenting code, maintaining repositories, and more. In this work, we introduce the Granite series of decoder-only code models for code ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04324","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/2405.04324/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":"2405.04324","created_at":"2026-07-05T08:16:35.497069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04324v1","created_at":"2026-07-05T08:16:35.497069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04324","created_at":"2026-07-05T08:16:35.497069+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKTGWA46LL2U","created_at":"2026-07-05T08:16:35.497069+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKTGWA46LL2UADJB","created_at":"2026-07-05T08:16:35.497069+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKTGWA46","created_at":"2026-07-05T08:16:35.497069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26734","citing_title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07017","citing_title":"The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26734","citing_title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08696","citing_title":"Structured Recurrent Mixers for Massively Parallelized Sequence Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08696","citing_title":"Structured Recurrent Mixers for Massively Parallelized Sequence Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18801","citing_title":"Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04500","citing_title":"\"Don't Do That!\": Guiding Embodied Systems through Large Language Model-based Constraint Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21954","citing_title":"Fine-Tuning Code Language Models to Detect Cross-Language Bugs","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05695","citing_title":"SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.14276","citing_title":"ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14503","citing_title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08696","citing_title":"Structured Recurrent Mixers for Massively Parallelized Sequence Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04894","citing_title":"SynConfRoute: Syntax-Aware Routing for Efficient Code Completion with Small CodeLLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01546","citing_title":"6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7","json":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7.json","graph_json":"https://pith.science/api/pith-number/WKTGWA46LL2UADJB4LRKXIJXR7/graph.json","events_json":"https://pith.science/api/pith-number/WKTGWA46LL2UADJB4LRKXIJXR7/events.json","paper":"https://pith.science/paper/WKTGWA46"},"agent_actions":{"view_html":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7","download_json":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7.json","view_paper":"https://pith.science/paper/WKTGWA46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04324&json=true","fetch_graph":"https://pith.science/api/pith-number/WKTGWA46LL2UADJB4LRKXIJXR7/graph.json","fetch_events":"https://pith.science/api/pith-number/WKTGWA46LL2UADJB4LRKXIJXR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7/action/storage_attestation","attest_author":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7/action/author_attestation","sign_citation":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7/action/citation_signature","submit_replication":"https://pith.science/pith/WKTGWA46LL2UADJB4LRKXIJXR7/action/replication_record"}},"created_at":"2026-07-05T08:16:35.497069+00:00","updated_at":"2026-07-05T08:16:35.497069+00:00"}