{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EXO2YP63OJBO4L24HMUAOF2XXF","short_pith_number":"pith:EXO2YP63","schema_version":"1.0","canonical_sha256":"25ddac3fdb7242ee2f5c3b28071757b97ca0c427a3e6d04c7a56f8491cef2dee","source":{"kind":"arxiv","id":"2506.13980","version":1},"attestation_state":"computed","paper":{"title":"ProfiLLM: An LLM-Based Framework for Implicit Profiling of Chatbot Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Asaf Shabtai, Daniel Varnovitzky, Dudu Mimran, Ido Hersko, Shahaf David, Yair Meidan, Yuval Elovici","submitted_at":"2025-06-16T20:33:44Z","abstract_excerpt":"Despite significant advancements in conversational AI, large language model (LLM)-powered chatbots often struggle with personalizing their responses according to individual user characteristics, such as technical expertise, learning style, and communication preferences. This lack of personalization is particularly problematic in specialized knowledge-intense domains like IT/cybersecurity (ITSec), where user knowledge levels vary widely. Existing approaches for chatbot personalization primarily rely on static user categories or explicit self-reported information, limiting their adaptability to "},"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":"2506.13980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-16T20:33:44Z","cross_cats_sorted":[],"title_canon_sha256":"0c932158c131d030189d24f401a8a6818187d7ae479b2a45fbe4c2c1a9f803a7","abstract_canon_sha256":"016814fb3cdd3bf8d4faaeb446d41329285ee83e86d887b574fdedb5364f9666"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:46.688519Z","signature_b64":"iFLVnX5jTt4Idaoxf1WDKaOuKZgoFNgx5ehSQtjojaHyMX/CZ2qx18qdU2+uZwoxu+wc3vEcc+zeu3jkfONkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ddac3fdb7242ee2f5c3b28071757b97ca0c427a3e6d04c7a56f8491cef2dee","last_reissued_at":"2026-07-05T11:22:46.688046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:46.688046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProfiLLM: An LLM-Based Framework for Implicit Profiling of Chatbot Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Asaf Shabtai, Daniel Varnovitzky, Dudu Mimran, Ido Hersko, Shahaf David, Yair Meidan, Yuval Elovici","submitted_at":"2025-06-16T20:33:44Z","abstract_excerpt":"Despite significant advancements in conversational AI, large language model (LLM)-powered chatbots often struggle with personalizing their responses according to individual user characteristics, such as technical expertise, learning style, and communication preferences. This lack of personalization is particularly problematic in specialized knowledge-intense domains like IT/cybersecurity (ITSec), where user knowledge levels vary widely. Existing approaches for chatbot personalization primarily rely on static user categories or explicit self-reported information, limiting their adaptability to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13980","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/2506.13980/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":"2506.13980","created_at":"2026-07-05T11:22:46.688104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13980v1","created_at":"2026-07-05T11:22:46.688104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13980","created_at":"2026-07-05T11:22:46.688104+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXO2YP63OJBO","created_at":"2026-07-05T11:22:46.688104+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXO2YP63OJBO4L24","created_at":"2026-07-05T11:22:46.688104+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXO2YP63","created_at":"2026-07-05T11:22:46.688104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02897","citing_title":"Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalities","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26394","citing_title":"SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF","json":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF.json","graph_json":"https://pith.science/api/pith-number/EXO2YP63OJBO4L24HMUAOF2XXF/graph.json","events_json":"https://pith.science/api/pith-number/EXO2YP63OJBO4L24HMUAOF2XXF/events.json","paper":"https://pith.science/paper/EXO2YP63"},"agent_actions":{"view_html":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF","download_json":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF.json","view_paper":"https://pith.science/paper/EXO2YP63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13980&json=true","fetch_graph":"https://pith.science/api/pith-number/EXO2YP63OJBO4L24HMUAOF2XXF/graph.json","fetch_events":"https://pith.science/api/pith-number/EXO2YP63OJBO4L24HMUAOF2XXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF/action/storage_attestation","attest_author":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF/action/author_attestation","sign_citation":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF/action/citation_signature","submit_replication":"https://pith.science/pith/EXO2YP63OJBO4L24HMUAOF2XXF/action/replication_record"}},"created_at":"2026-07-05T11:22:46.688104+00:00","updated_at":"2026-07-05T11:22:46.688104+00:00"}