{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NPTZ7Q5OSLZOSMDSZRIHSB3TK5","short_pith_number":"pith:NPTZ7Q5O","schema_version":"1.0","canonical_sha256":"6be79fc3ae92f2e93072cc50790773574130dfcaad89d9f219be76e3d092765b","source":{"kind":"arxiv","id":"2410.08356","version":1},"attestation_state":"computed","paper":{"title":"SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Andreas Bulling, Guanhua Zhang, Mohamed Ahmed, Zhiming Hu","submitted_at":"2024-10-10T20:23:00Z","abstract_excerpt":"Recent work has highlighted the potential of modelling interactive behaviour analogously to natural language. We propose interactive behaviour summarisation as a novel computational task and demonstrate its usefulness for automatically uncovering latent user intentions while interacting with graphical user interfaces. To tackle this task, we introduce SummAct, a novel hierarchical method to summarise low-level input actions into high-level intentions. SummAct first identifies sub-goals from user actions using a large language model and in-context learning. High-level intentions are then obtain"},"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":"2410.08356","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-10-10T20:23:00Z","cross_cats_sorted":[],"title_canon_sha256":"9eb124618d8ca2b462e6c1f4d7f4f2ba3213d915d4f6e350ecc6bf620b2b8f03","abstract_canon_sha256":"c7d605e1bf6c40c6f0ca5eff154765dd18c4848c43d70b6ef9554e5b8017c6c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:57.107861Z","signature_b64":"Ba0WdO6rsFbMm+oOJeXCPj4Y8d3z4qzJQvaR/jiW2W+gSDKxZxv0B6MJTCmivU6uk56ELfCJLHiUQfIdiAZoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be79fc3ae92f2e93072cc50790773574130dfcaad89d9f219be76e3d092765b","last_reissued_at":"2026-07-05T09:18:57.107396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:57.107396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Andreas Bulling, Guanhua Zhang, Mohamed Ahmed, Zhiming Hu","submitted_at":"2024-10-10T20:23:00Z","abstract_excerpt":"Recent work has highlighted the potential of modelling interactive behaviour analogously to natural language. We propose interactive behaviour summarisation as a novel computational task and demonstrate its usefulness for automatically uncovering latent user intentions while interacting with graphical user interfaces. To tackle this task, we introduce SummAct, a novel hierarchical method to summarise low-level input actions into high-level intentions. SummAct first identifies sub-goals from user actions using a large language model and in-context learning. High-level intentions are then obtain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08356","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/2410.08356/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":"2410.08356","created_at":"2026-07-05T09:18:57.107461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08356v1","created_at":"2026-07-05T09:18:57.107461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08356","created_at":"2026-07-05T09:18:57.107461+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPTZ7Q5OSLZO","created_at":"2026-07-05T09:18:57.107461+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPTZ7Q5OSLZOSMDS","created_at":"2026-07-05T09:18:57.107461+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPTZ7Q5O","created_at":"2026-07-05T09:18:57.107461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.13149","citing_title":"Bi-Fact: A Bidirectional Factorization-based Evaluation of Intent Extraction from UI Trajectories","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5","json":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5.json","graph_json":"https://pith.science/api/pith-number/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/graph.json","events_json":"https://pith.science/api/pith-number/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/events.json","paper":"https://pith.science/paper/NPTZ7Q5O"},"agent_actions":{"view_html":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5","download_json":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5.json","view_paper":"https://pith.science/paper/NPTZ7Q5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08356&json=true","fetch_graph":"https://pith.science/api/pith-number/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/graph.json","fetch_events":"https://pith.science/api/pith-number/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/action/storage_attestation","attest_author":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/action/author_attestation","sign_citation":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/action/citation_signature","submit_replication":"https://pith.science/pith/NPTZ7Q5OSLZOSMDSZRIHSB3TK5/action/replication_record"}},"created_at":"2026-07-05T09:18:57.107461+00:00","updated_at":"2026-07-05T09:18:57.107461+00:00"}