{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XOUDILWS2WTKSI3BM6CJXDCXUN","short_pith_number":"pith:XOUDILWS","schema_version":"1.0","canonical_sha256":"bba8342ed2d5a6a9236167849b8c57a3450ade4c798d291ce85162822557cbaa","source":{"kind":"arxiv","id":"2506.03011","version":1},"attestation_state":"computed","paper":{"title":"Coding Agents with Multimodal Browsing are Generalist Problem Solvers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Bharat Soni, Boxuan Li, Graham Neubig, Valerie Chen, Xingyao Wang","submitted_at":"2025-06-03T15:50:55Z","abstract_excerpt":"Modern human labor is characterized by specialization; we train for years and develop particular tools that allow us to perform well across a variety of tasks. In addition, AI agents have been specialized for domains such as software engineering, web navigation, and workflow automation. However, this results in agents that are good for one thing but fail to generalize beyond their intended scope. One reason for this is that agent developers provide a highly specialized set of tools or make architectural decisions optimized for a specific use case or benchmark. In this work, we ask the question"},"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":"2506.03011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T15:50:55Z","cross_cats_sorted":[],"title_canon_sha256":"518bff37b30dfd09b76c083503bc56a4962ca28ae11283768b2729b18529f4f7","abstract_canon_sha256":"8d056c41a8434ae8ef092a6b352d1ca1a0b42add923d82fe3b9f18d621ba5440"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:13.313458Z","signature_b64":"oMc54eXlwE4nCzkyupJJAKc7Itdrs5HBT0hclZ8PrJ7OeaH01LXUpF9Bw8tUN+dMcdqp9i39v8krvxqoaNjVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bba8342ed2d5a6a9236167849b8c57a3450ade4c798d291ce85162822557cbaa","last_reissued_at":"2026-07-05T11:15:13.312913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:13.312913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coding Agents with Multimodal Browsing are Generalist Problem Solvers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Bharat Soni, Boxuan Li, Graham Neubig, Valerie Chen, Xingyao Wang","submitted_at":"2025-06-03T15:50:55Z","abstract_excerpt":"Modern human labor is characterized by specialization; we train for years and develop particular tools that allow us to perform well across a variety of tasks. In addition, AI agents have been specialized for domains such as software engineering, web navigation, and workflow automation. However, this results in agents that are good for one thing but fail to generalize beyond their intended scope. One reason for this is that agent developers provide a highly specialized set of tools or make architectural decisions optimized for a specific use case or benchmark. In this work, we ask the question"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03011","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/2506.03011/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":"2506.03011","created_at":"2026-07-05T11:15:13.312976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03011v1","created_at":"2026-07-05T11:15:13.312976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03011","created_at":"2026-07-05T11:15:13.312976+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOUDILWS2WTK","created_at":"2026-07-05T11:15:13.312976+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOUDILWS2WTKSI3B","created_at":"2026-07-05T11:15:13.312976+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOUDILWS","created_at":"2026-07-05T11:15:13.312976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21926","citing_title":"A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19319","citing_title":"Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.14061","citing_title":"LLM Agents Can See Code Repositories","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.13727","citing_title":"From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03690","citing_title":"The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11359","citing_title":"CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN","json":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN.json","graph_json":"https://pith.science/api/pith-number/XOUDILWS2WTKSI3BM6CJXDCXUN/graph.json","events_json":"https://pith.science/api/pith-number/XOUDILWS2WTKSI3BM6CJXDCXUN/events.json","paper":"https://pith.science/paper/XOUDILWS"},"agent_actions":{"view_html":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN","download_json":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN.json","view_paper":"https://pith.science/paper/XOUDILWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03011&json=true","fetch_graph":"https://pith.science/api/pith-number/XOUDILWS2WTKSI3BM6CJXDCXUN/graph.json","fetch_events":"https://pith.science/api/pith-number/XOUDILWS2WTKSI3BM6CJXDCXUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN/action/storage_attestation","attest_author":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN/action/author_attestation","sign_citation":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN/action/citation_signature","submit_replication":"https://pith.science/pith/XOUDILWS2WTKSI3BM6CJXDCXUN/action/replication_record"}},"created_at":"2026-07-05T11:15:13.312976+00:00","updated_at":"2026-07-05T11:15:13.312976+00:00"}