{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TMFA4PBEOTC37BPKXZHJ2LRAUM","short_pith_number":"pith:TMFA4PBE","schema_version":"1.0","canonical_sha256":"9b0a0e3c2474c5bf85eabe4e9d2e20a3103aa2a5ff16747ef87f04f49cb03278","source":{"kind":"arxiv","id":"2506.23774","version":1},"attestation_state":"computed","paper":{"title":"Leveraging a Multi-Agent LLM-Based System to Educate Teachers in Hate Incidents Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CY","authors_text":"Ewelina Gajewska, Jaros{\\l}aw A. Chudziak, Katarzyna Budzynska, Michal Wawer","submitted_at":"2025-06-30T12:18:13Z","abstract_excerpt":"Computer-aided teacher training is a state-of-the-art method designed to enhance teachers' professional skills effectively while minimising concerns related to costs, time constraints, and geographical limitations. We investigate the potential of large language models (LLMs) in teacher education, using a case of teaching hate incidents management in schools. To this end, we create a multi-agent LLM-based system that mimics realistic situations of hate, using a combination of retrieval-augmented prompting and persona modelling. It is designed to identify and analyse hate speech patterns, predic"},"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":"2506.23774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-06-30T12:18:13Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"6f6e4cc1eceaa1da99d0b343d1d81ada3e67474782ffd3ac1f87436b00497f06","abstract_canon_sha256":"492a86217bb7aa19deceec076de08ed5773f196f06bb3b23c11f92a22138022b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:27.790882Z","signature_b64":"COqsaP6KWeVzwB9i/llSXS9zzZppIf00t7wLfqQnveFJpbY+vLSkr5JUMKBMujUsN2/wlt1ztwNxvIrXNDPhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b0a0e3c2474c5bf85eabe4e9d2e20a3103aa2a5ff16747ef87f04f49cb03278","last_reissued_at":"2026-07-05T11:29:27.790309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:27.790309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging a Multi-Agent LLM-Based System to Educate Teachers in Hate Incidents Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CY","authors_text":"Ewelina Gajewska, Jaros{\\l}aw A. Chudziak, Katarzyna Budzynska, Michal Wawer","submitted_at":"2025-06-30T12:18:13Z","abstract_excerpt":"Computer-aided teacher training is a state-of-the-art method designed to enhance teachers' professional skills effectively while minimising concerns related to costs, time constraints, and geographical limitations. We investigate the potential of large language models (LLMs) in teacher education, using a case of teaching hate incidents management in schools. To this end, we create a multi-agent LLM-based system that mimics realistic situations of hate, using a combination of retrieval-augmented prompting and persona modelling. It is designed to identify and analyse hate speech patterns, predic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23774","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/2506.23774/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":"2506.23774","created_at":"2026-07-05T11:29:27.790404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23774v1","created_at":"2026-07-05T11:29:27.790404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23774","created_at":"2026-07-05T11:29:27.790404+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMFA4PBEOTC3","created_at":"2026-07-05T11:29:27.790404+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMFA4PBEOTC37BPK","created_at":"2026-07-05T11:29:27.790404+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMFA4PBE","created_at":"2026-07-05T11:29:27.790404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.22788","citing_title":"FACET: Multi-Agent AI Supporting Teachers in Scaling Differentiated Learning for Diverse Students","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM","json":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM.json","graph_json":"https://pith.science/api/pith-number/TMFA4PBEOTC37BPKXZHJ2LRAUM/graph.json","events_json":"https://pith.science/api/pith-number/TMFA4PBEOTC37BPKXZHJ2LRAUM/events.json","paper":"https://pith.science/paper/TMFA4PBE"},"agent_actions":{"view_html":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM","download_json":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM.json","view_paper":"https://pith.science/paper/TMFA4PBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23774&json=true","fetch_graph":"https://pith.science/api/pith-number/TMFA4PBEOTC37BPKXZHJ2LRAUM/graph.json","fetch_events":"https://pith.science/api/pith-number/TMFA4PBEOTC37BPKXZHJ2LRAUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM/action/storage_attestation","attest_author":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM/action/author_attestation","sign_citation":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM/action/citation_signature","submit_replication":"https://pith.science/pith/TMFA4PBEOTC37BPKXZHJ2LRAUM/action/replication_record"}},"created_at":"2026-07-05T11:29:27.790404+00:00","updated_at":"2026-07-05T11:29:27.790404+00:00"}