{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQUIAG7HS2XEC7IKXDCA7EIAAL","short_pith_number":"pith:DQUIAG7H","schema_version":"1.0","canonical_sha256":"1c28801be796ae417d0ab8c40f910002e81285b1064b650eca4e9b4cb52fd8b2","source":{"kind":"arxiv","id":"2406.11638","version":1},"attestation_state":"computed","paper":{"title":"MASAI: Modular Architecture for Software-engineering AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Abhav Mehrotra, Aditya Kanade, Atharv Sonwane, Daman Arora, Nagarajan Natarajan, Nalin Wadhwa, Ramakrishna Bairi, Saiteja Utpala","submitted_at":"2024-06-17T15:19:51Z","abstract_excerpt":"A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. Inspired by this, we propose a Modular Architecture for Software-engineering AI (MASAI) agents, where different LLM-powered sub-agents are instantiated with well-defined objectives and strategies tuned to achieve those objectives. Our modular architecture offers several advantages: (1) employing and tuning different problem-solving strategies across sub-agents, (2) enabling sub-agents to gather information from different sources scattered throughout a repository, and (3) avoi"},"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":"2406.11638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T15:19:51Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"ced36a0349ffbcbac39b2d2831b7dad783aefe5046d8de59779ab25482a46be3","abstract_canon_sha256":"4cc5e7d8782875b9aa45487ed2c546b408b126196efab4ca0a20118862d2ae7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:55.767367Z","signature_b64":"vTseckPGwhL2NdwLJV2Q9Vr/+yPc4dT+FOIIT8zEmIhngfXt6Umwqv3r40pbHewjgfGpx0E24csHDT65rrqyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c28801be796ae417d0ab8c40f910002e81285b1064b650eca4e9b4cb52fd8b2","last_reissued_at":"2026-07-05T08:32:55.766882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:55.766882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MASAI: Modular Architecture for Software-engineering AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Abhav Mehrotra, Aditya Kanade, Atharv Sonwane, Daman Arora, Nagarajan Natarajan, Nalin Wadhwa, Ramakrishna Bairi, Saiteja Utpala","submitted_at":"2024-06-17T15:19:51Z","abstract_excerpt":"A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. Inspired by this, we propose a Modular Architecture for Software-engineering AI (MASAI) agents, where different LLM-powered sub-agents are instantiated with well-defined objectives and strategies tuned to achieve those objectives. Our modular architecture offers several advantages: (1) employing and tuning different problem-solving strategies across sub-agents, (2) enabling sub-agents to gather information from different sources scattered throughout a repository, and (3) avoi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11638","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/2406.11638/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":"2406.11638","created_at":"2026-07-05T08:32:55.766939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11638v1","created_at":"2026-07-05T08:32:55.766939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11638","created_at":"2026-07-05T08:32:55.766939+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQUIAG7HS2XE","created_at":"2026-07-05T08:32:55.766939+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQUIAG7HS2XEC7IK","created_at":"2026-07-05T08:32:55.766939+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQUIAG7H","created_at":"2026-07-05T08:32:55.766939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00341","citing_title":"ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10106","citing_title":"What makes a harness a harness: necessary and sufficient conditions for an agent harness","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16858","citing_title":"Investigating Test Overfitting on SWE-bench","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18571","citing_title":"Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13872","citing_title":"S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":222,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03515","citing_title":"Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2407.01489","citing_title":"Agentless: Demystifying LLM-based Software Engineering Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13934","citing_title":"Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07320","citing_title":"Splitting User Stories Into Tasks with AI -- A Foe or an Ally?","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL","json":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL.json","graph_json":"https://pith.science/api/pith-number/DQUIAG7HS2XEC7IKXDCA7EIAAL/graph.json","events_json":"https://pith.science/api/pith-number/DQUIAG7HS2XEC7IKXDCA7EIAAL/events.json","paper":"https://pith.science/paper/DQUIAG7H"},"agent_actions":{"view_html":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL","download_json":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL.json","view_paper":"https://pith.science/paper/DQUIAG7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11638&json=true","fetch_graph":"https://pith.science/api/pith-number/DQUIAG7HS2XEC7IKXDCA7EIAAL/graph.json","fetch_events":"https://pith.science/api/pith-number/DQUIAG7HS2XEC7IKXDCA7EIAAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL/action/storage_attestation","attest_author":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL/action/author_attestation","sign_citation":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL/action/citation_signature","submit_replication":"https://pith.science/pith/DQUIAG7HS2XEC7IKXDCA7EIAAL/action/replication_record"}},"created_at":"2026-07-05T08:32:55.766939+00:00","updated_at":"2026-07-05T08:32:55.766939+00:00"}