{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7LY5LLUY7LE6PFPE4QS4KA6ZK3","short_pith_number":"pith:7LY5LLUY","schema_version":"1.0","canonical_sha256":"faf1d5ae98fac9e795e4e425c503d956de4c56c39b736cee9e7810e5205dcee8","source":{"kind":"arxiv","id":"2602.11198","version":2},"attestation_state":"computed","paper":{"title":"Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistability","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Shafiuddin Rehan Ahmed, Sourabh Deshpande","submitted_at":"2026-02-03T01:10:59Z","abstract_excerpt":"Multi-agent frameworks (MAFs) promise to simplify LLM-driven software development, yet no principled metric captures how well AI coding assistants can generate correct, framework-specific code. We introduce \\textit{AI-assistability} ($\\mathcal{AI}$), a composite metric that quantifies a framework's amenability to AI-assisted development by combining structural alignment ($\\bar{\\sigma}$) with functional correctness (pass@1). To evaluate this metric in a controlled setting, we design DDL2PropBank, a novel benchmark task that maps relational database schemas to PropBank semantic rolesets, and imp"},"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":"2602.11198","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-03T01:10:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42e8b64ea27d3328ab04cc0197dc4911a2f936df6308465cf7b3876ca1fe9301","abstract_canon_sha256":"6d3b1f73bd89c004f7768e4c547140a5c44c6f8fb14523ec3a21f03209062bda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T00:21:16.465697Z","signature_b64":"UmzHkiggYdQnPGEWmk3FzM0Omx8F+OhYMio+F1l0+ePuIDzK9IUv+N2+xrS1aiu9Eczp35KTZpVVzlYv0mN4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faf1d5ae98fac9e795e4e425c503d956de4c56c39b736cee9e7810e5205dcee8","last_reissued_at":"2026-07-15T00:21:16.464676Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T00:21:16.464676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistability","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Shafiuddin Rehan Ahmed, Sourabh Deshpande","submitted_at":"2026-02-03T01:10:59Z","abstract_excerpt":"Multi-agent frameworks (MAFs) promise to simplify LLM-driven software development, yet no principled metric captures how well AI coding assistants can generate correct, framework-specific code. We introduce \\textit{AI-assistability} ($\\mathcal{AI}$), a composite metric that quantifies a framework's amenability to AI-assisted development by combining structural alignment ($\\bar{\\sigma}$) with functional correctness (pass@1). To evaluate this metric in a controlled setting, we design DDL2PropBank, a novel benchmark task that maps relational database schemas to PropBank semantic rolesets, and imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11198","kind":"arxiv","version":2},"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/2602.11198/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":"2602.11198","created_at":"2026-07-15T00:21:16.465109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11198v2","created_at":"2026-07-15T00:21:16.465109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11198","created_at":"2026-07-15T00:21:16.465109+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LY5LLUY7LE6","created_at":"2026-07-15T00:21:16.465109+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LY5LLUY7LE6PFPE","created_at":"2026-07-15T00:21:16.465109+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LY5LLUY","created_at":"2026-07-15T00:21:16.465109+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/7LY5LLUY7LE6PFPE4QS4KA6ZK3","json":"https://pith.science/pith/7LY5LLUY7LE6PFPE4QS4KA6ZK3.json","graph_json":"https://pith.science/api/pith-number/7LY5LLUY7LE6PFPE4QS4KA6ZK3/graph.json","events_json":"https://pith.science/api/pith-number/7LY5LLUY7LE6PFPE4QS4KA6ZK3/events.json","paper":"https://pith.science/paper/7LY5LLUY"},"agent_actions":{"view_html":"https://pith.science/pith/7LY5LLUY7LE6PFPE4QS4KA6ZK3","download_json":"https://pith.science/pith/7LY5LLUY7LE6PFPE4QS4KA6ZK3.json","view_paper":"https://pith.science/paper/7LY5LLUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11198&json=true","fetch_graph":"https://pith.science/api/pith-number/7LY5LLUY7LE6PFPE4QS4KA6ZK3/graph.json","fetch_events":"https://pith.science/api/pith-number/7LY5LLUY7LE6PFPE4QS4KA6ZK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LY5LLUY7LE6PFPE4QS4KA6ZK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LY5LLUY7LE6PFPE4QS4KA6ZK3/action/storage_attestation","attest_author":"https://pith.science/pith/7LY5LLUY7LE6PFPE4QS4KA6ZK3/action/author_attestation","sign_citation":"https://pith.science/pith/7LY5LLUY7LE6PFPE4QS4KA6ZK3/action/citation_signature","submit_replication":"https://pith.science/pith/7LY5LLUY7LE6PFPE4QS4KA6ZK3/action/replication_record"}},"created_at":"2026-07-15T00:21:16.465109+00:00","updated_at":"2026-07-15T00:21:16.465109+00:00"}