{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AI63BE4SR6OZ53KZWTNMSKBIIC","short_pith_number":"pith:AI63BE4S","schema_version":"1.0","canonical_sha256":"023db093928f9d9eed59b4dac9282840b230f641b4ddcd551a9b9431457e308f","source":{"kind":"arxiv","id":"2506.01520","version":1},"attestation_state":"computed","paper":{"title":"FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bobo Li, Hao Fei, Juncheng Li, Mong-Li Lee, Wei Ji, Wynne Hsu, Yuheng Wang","submitted_at":"2025-06-02T10:34:57Z","abstract_excerpt":"Online form filling is a common yet labor-intensive task involving extensive keyboard and mouse interactions. Despite the long-standing vision of automating this process with \"one click\", existing tools remain largely rule-based and lack generalizable, generative capabilities. Recent advances in Multimodal Large Language Models (MLLMs) have enabled promising agents for GUI-related tasks in general-purpose scenarios. However, they struggle with the unique challenges of form filling, such as flexible layouts and the difficulty of aligning textual instructions with on-screen fields. To bridge thi"},"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":"2506.01520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T10:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"a069fcf3a6fde60ca0699198904c8155e7546e776bb3538bfda2cceddd79813c","abstract_canon_sha256":"c151ef06b4aa367f16fafa412f32fa0cef6bf2ab6fea494a033212b2ade1e6a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:15.041387Z","signature_b64":"XDjFn+Z3B3HzFvNWNIZPNzpoE/TbgbK4UxE7cWsuqQFLP5IH272gySt+ncByVOzelU+VNHPF/Bepq+AFeTY+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"023db093928f9d9eed59b4dac9282840b230f641b4ddcd551a9b9431457e308f","last_reissued_at":"2026-07-05T11:14:15.040936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:15.040936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bobo Li, Hao Fei, Juncheng Li, Mong-Li Lee, Wei Ji, Wynne Hsu, Yuheng Wang","submitted_at":"2025-06-02T10:34:57Z","abstract_excerpt":"Online form filling is a common yet labor-intensive task involving extensive keyboard and mouse interactions. Despite the long-standing vision of automating this process with \"one click\", existing tools remain largely rule-based and lack generalizable, generative capabilities. Recent advances in Multimodal Large Language Models (MLLMs) have enabled promising agents for GUI-related tasks in general-purpose scenarios. However, they struggle with the unique challenges of form filling, such as flexible layouts and the difficulty of aligning textual instructions with on-screen fields. To bridge thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01520","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/2506.01520/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":"2506.01520","created_at":"2026-07-05T11:14:15.040992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01520v1","created_at":"2026-07-05T11:14:15.040992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01520","created_at":"2026-07-05T11:14:15.040992+00:00"},{"alias_kind":"pith_short_12","alias_value":"AI63BE4SR6OZ","created_at":"2026-07-05T11:14:15.040992+00:00"},{"alias_kind":"pith_short_16","alias_value":"AI63BE4SR6OZ53KZ","created_at":"2026-07-05T11:14:15.040992+00:00"},{"alias_kind":"pith_short_8","alias_value":"AI63BE4S","created_at":"2026-07-05T11:14:15.040992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.11724","citing_title":"WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04820","citing_title":"ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01250","citing_title":"EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC","json":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC.json","graph_json":"https://pith.science/api/pith-number/AI63BE4SR6OZ53KZWTNMSKBIIC/graph.json","events_json":"https://pith.science/api/pith-number/AI63BE4SR6OZ53KZWTNMSKBIIC/events.json","paper":"https://pith.science/paper/AI63BE4S"},"agent_actions":{"view_html":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC","download_json":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC.json","view_paper":"https://pith.science/paper/AI63BE4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01520&json=true","fetch_graph":"https://pith.science/api/pith-number/AI63BE4SR6OZ53KZWTNMSKBIIC/graph.json","fetch_events":"https://pith.science/api/pith-number/AI63BE4SR6OZ53KZWTNMSKBIIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC/action/storage_attestation","attest_author":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC/action/author_attestation","sign_citation":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC/action/citation_signature","submit_replication":"https://pith.science/pith/AI63BE4SR6OZ53KZWTNMSKBIIC/action/replication_record"}},"created_at":"2026-07-05T11:14:15.040992+00:00","updated_at":"2026-07-05T11:14:15.040992+00:00"}