{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:URYMMZPQBKUKGQ7KLQNXYFZISZ","short_pith_number":"pith:URYMMZPQ","schema_version":"1.0","canonical_sha256":"a470c665f00aa8a343ea5c1b7c1728966918a67f3cb86a32e946be62113cd578","source":{"kind":"arxiv","id":"2506.23767","version":2},"attestation_state":"computed","paper":{"title":"Explainable AI for Comprehensive Risk Assessment for Financial Reports: A Lightweight Hierarchical Transformer Network Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-fin.RM","authors_text":"Stanley Kok, Xue Wen Tan","submitted_at":"2025-06-30T12:13:35Z","abstract_excerpt":"Every publicly traded U.S. company files an annual 10-K report containing critical insights into financial health and risk. We propose Tiny eXplainable Risk Assessor (TinyXRA), a lightweight and explainable transformer-based model that automatically assesses company risk from these reports. Unlike prior work that relies solely on the standard deviation of excess returns (adjusted for the Fama-French model), which indiscriminately penalizes both upside and downside risk, TinyXRA incorporates skewness, kurtosis, and the Sortino ratio for more comprehensive risk assessment. We leverage TinyBERT a"},"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":"2506.23767","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.RM","submitted_at":"2025-06-30T12:13:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0722e45ce6afa4c74c8d68e4b2ec9fa2f53186c53ada8479dc96eb0bdd44f97d","abstract_canon_sha256":"45508b3c8f2207c517128ee0ce03f91c3ea6a1d625c1180b8d82288783466f24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:08.640759Z","signature_b64":"CW6dc30pKQKNuE36UiWcQklyWGlCAVzXn152U1qfg7upaxE0HTtI/XFWzkWtZyaN2A6zbz/ohq4VFAVUxpThCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a470c665f00aa8a343ea5c1b7c1728966918a67f3cb86a32e946be62113cd578","last_reissued_at":"2026-07-05T11:31:08.640274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:08.640274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable AI for Comprehensive Risk Assessment for Financial Reports: A Lightweight Hierarchical Transformer Network Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-fin.RM","authors_text":"Stanley Kok, Xue Wen Tan","submitted_at":"2025-06-30T12:13:35Z","abstract_excerpt":"Every publicly traded U.S. company files an annual 10-K report containing critical insights into financial health and risk. We propose Tiny eXplainable Risk Assessor (TinyXRA), a lightweight and explainable transformer-based model that automatically assesses company risk from these reports. Unlike prior work that relies solely on the standard deviation of excess returns (adjusted for the Fama-French model), which indiscriminately penalizes both upside and downside risk, TinyXRA incorporates skewness, kurtosis, and the Sortino ratio for more comprehensive risk assessment. We leverage TinyBERT a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23767","kind":"arxiv","version":2},"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/2506.23767/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":"2506.23767","created_at":"2026-07-05T11:31:08.640338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23767v2","created_at":"2026-07-05T11:31:08.640338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23767","created_at":"2026-07-05T11:31:08.640338+00:00"},{"alias_kind":"pith_short_12","alias_value":"URYMMZPQBKUK","created_at":"2026-07-05T11:31:08.640338+00:00"},{"alias_kind":"pith_short_16","alias_value":"URYMMZPQBKUKGQ7K","created_at":"2026-07-05T11:31:08.640338+00:00"},{"alias_kind":"pith_short_8","alias_value":"URYMMZPQ","created_at":"2026-07-05T11:31:08.640338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ","json":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ.json","graph_json":"https://pith.science/api/pith-number/URYMMZPQBKUKGQ7KLQNXYFZISZ/graph.json","events_json":"https://pith.science/api/pith-number/URYMMZPQBKUKGQ7KLQNXYFZISZ/events.json","paper":"https://pith.science/paper/URYMMZPQ"},"agent_actions":{"view_html":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ","download_json":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ.json","view_paper":"https://pith.science/paper/URYMMZPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23767&json=true","fetch_graph":"https://pith.science/api/pith-number/URYMMZPQBKUKGQ7KLQNXYFZISZ/graph.json","fetch_events":"https://pith.science/api/pith-number/URYMMZPQBKUKGQ7KLQNXYFZISZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ/action/storage_attestation","attest_author":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ/action/author_attestation","sign_citation":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ/action/citation_signature","submit_replication":"https://pith.science/pith/URYMMZPQBKUKGQ7KLQNXYFZISZ/action/replication_record"}},"created_at":"2026-07-05T11:31:08.640338+00:00","updated_at":"2026-07-05T11:31:08.640338+00:00"}