{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RZZ7AAYDI6XWL6L5BIONNWYRFA","short_pith_number":"pith:RZZ7AAYD","schema_version":"1.0","canonical_sha256":"8e73f0030347af65f97d0a1cd6db112802112893b0d09a6a0a9400c00214505a","source":{"kind":"arxiv","id":"2411.13451","version":1},"attestation_state":"computed","paper":{"title":"AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Gaurav Verma, Manuela Veloso, Nishan Srishankar, Rachneet Kaur, Tucker Balch, Zhen Zeng","submitted_at":"2024-11-20T16:54:15Z","abstract_excerpt":"State-of-the-art multimodal web agents, powered by Multimodal Large Language Models (MLLMs), can autonomously execute many web tasks by processing user instructions and interacting with graphical user interfaces (GUIs). Current strategies for building web agents rely on (i) the generalizability of underlying MLLMs and their steerability via prompting, and (ii) large-scale fine-tuning of MLLMs on web-related tasks. However, web agents still struggle to automate tasks on unseen websites and domains, limiting their applicability to enterprise-specific and proprietary platforms. Beyond generalizat"},"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":"2411.13451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-20T16:54:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"936e6f23045a22a4e53431a11895032256e13c819e3785bd7771e95e92e44165","abstract_canon_sha256":"e1c902a399e70ffaed6df8a7b9fddb263eea05835787d62888417c1da0d59b51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:17.091102Z","signature_b64":"WZsbyoHcgiP5Y14M6sCfArbsAUOAES1F3as3gnPBzc4XOAjnwueoimnDveVr83Ph3NQ+J/MIjuWxqxRAZwalBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e73f0030347af65f97d0a1cd6db112802112893b0d09a6a0a9400c00214505a","last_reissued_at":"2026-07-05T09:38:17.090586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:17.090586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Gaurav Verma, Manuela Veloso, Nishan Srishankar, Rachneet Kaur, Tucker Balch, Zhen Zeng","submitted_at":"2024-11-20T16:54:15Z","abstract_excerpt":"State-of-the-art multimodal web agents, powered by Multimodal Large Language Models (MLLMs), can autonomously execute many web tasks by processing user instructions and interacting with graphical user interfaces (GUIs). Current strategies for building web agents rely on (i) the generalizability of underlying MLLMs and their steerability via prompting, and (ii) large-scale fine-tuning of MLLMs on web-related tasks. However, web agents still struggle to automate tasks on unseen websites and domains, limiting their applicability to enterprise-specific and proprietary platforms. Beyond generalizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13451","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/2411.13451/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":"2411.13451","created_at":"2026-07-05T09:38:17.090649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13451v1","created_at":"2026-07-05T09:38:17.090649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13451","created_at":"2026-07-05T09:38:17.090649+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZZ7AAYDI6XW","created_at":"2026-07-05T09:38:17.090649+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZZ7AAYDI6XWL6L5","created_at":"2026-07-05T09:38:17.090649+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZZ7AAYD","created_at":"2026-07-05T09:38:17.090649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31365","citing_title":"Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03530","citing_title":"How Far Are We from Generating Missing Modalities with Foundation Models?","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":294,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20148","citing_title":"Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA","json":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA.json","graph_json":"https://pith.science/api/pith-number/RZZ7AAYDI6XWL6L5BIONNWYRFA/graph.json","events_json":"https://pith.science/api/pith-number/RZZ7AAYDI6XWL6L5BIONNWYRFA/events.json","paper":"https://pith.science/paper/RZZ7AAYD"},"agent_actions":{"view_html":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA","download_json":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA.json","view_paper":"https://pith.science/paper/RZZ7AAYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13451&json=true","fetch_graph":"https://pith.science/api/pith-number/RZZ7AAYDI6XWL6L5BIONNWYRFA/graph.json","fetch_events":"https://pith.science/api/pith-number/RZZ7AAYDI6XWL6L5BIONNWYRFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA/action/storage_attestation","attest_author":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA/action/author_attestation","sign_citation":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA/action/citation_signature","submit_replication":"https://pith.science/pith/RZZ7AAYDI6XWL6L5BIONNWYRFA/action/replication_record"}},"created_at":"2026-07-05T09:38:17.090649+00:00","updated_at":"2026-07-05T09:38:17.090649+00:00"}