{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K2QW6COO2VK4UW6RXTETEV3MPS","short_pith_number":"pith:K2QW6COO","schema_version":"1.0","canonical_sha256":"56a16f09ced555ca5bd1bcc932576c7caecbcbae6c488d1ecb8733b209064b83","source":{"kind":"arxiv","id":"2605.13407","version":1},"attestation_state":"computed","paper":{"title":"Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PRISM-VQ combines vector-quantized discrete latent factors with financial priors and a mixture-of-experts to improve dynamic cross-sectional stock return predictions.","cross_cats":["cs.CE","q-fin.ST"],"primary_cat":"cs.LG","authors_text":"Jae Wook Song, Namhyoung Kim","submitted_at":"2026-05-13T12:02:53Z","abstract_excerpt":"Predicting cross-sectional stock returns is challenging due to low signal-to-noise ratios and evolving market regimes. Classical factor models offer interpretability but limited flexibility, while deep learning models achieve strong performance yet often underutilize financial priors. We address this gap with PRISM-VQ (PRior-Informed Stock Model with Vector Quantization), a dynamic factor framework that integrates expert prior factors, vector-quantized discrete latent factors learned from cross-sectional structure, and a structure-conditioned Mixture-of-Experts to generate time-varying factor "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:02:53Z","cross_cats_sorted":["cs.CE","q-fin.ST"],"title_canon_sha256":"894bfb691198821fdae3d7f06f5ce87e286e98fc01ef1597f5b6d342848f8d3d","abstract_canon_sha256":"a89973fc992f256639caf4be2a6d2f5a5e0ba9184d9c1483d9a425f63b410ae7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:47.497198Z","signature_b64":"dfsEpUtuH0877VTxGkTV9yi6kWmMgYvvXRZ4onlHL/y0h9H0LqmqMxCM39OSl9X2wRtcB7YGtN3KehLau80RAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56a16f09ced555ca5bd1bcc932576c7caecbcbae6c488d1ecb8733b209064b83","last_reissued_at":"2026-05-18T02:44:47.496754Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:47.496754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PRISM-VQ combines vector-quantized discrete latent factors with financial priors and a mixture-of-experts to improve dynamic cross-sectional stock return predictions.","cross_cats":["cs.CE","q-fin.ST"],"primary_cat":"cs.LG","authors_text":"Jae Wook Song, Namhyoung Kim","submitted_at":"2026-05-13T12:02:53Z","abstract_excerpt":"Predicting cross-sectional stock returns is challenging due to low signal-to-noise ratios and evolving market regimes. Classical factor models offer interpretability but limited flexibility, while deep learning models achieve strong performance yet often underutilize financial priors. We address this gap with PRISM-VQ (PRior-Informed Stock Model with Vector Quantization), a dynamic factor framework that integrates expert prior factors, vector-quantized discrete latent factors learned from cross-sectional structure, and a structure-conditioned Mixture-of-Experts to generate time-varying factor "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on CSI 300 and S&P 500 show consistent improvements in cross-sectional return prediction and portfolio performance over strong baselines while preserving interpretability.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That vector quantization reliably suppresses noise while preserving predictive cross-sectional structure and that the discrete codes provide effective routing signals for the mixture-of-experts without introducing regime misclassification.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PRISM-VQ integrates vector-quantized latent factors with financial priors and a structure-conditioned mixture-of-experts to deliver improved cross-sectional stock return predictions and portfolio performance on CSI 300 and S&P 500.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PRISM-VQ combines vector-quantized discrete latent factors with financial priors and a mixture-of-experts to improve dynamic cross-sectional stock return predictions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ebad94ae3c28dcbc8ca2f9b865907c9a0bf5ade9afd6249478db622affa53a08"},"source":{"id":"2605.13407","kind":"arxiv","version":1},"verdict":{"id":"bb6d3237-9c9e-402c-b8cf-903ccb7e72c9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:50:45.200203Z","strongest_claim":"Experiments on CSI 300 and S&P 500 show consistent improvements in cross-sectional return prediction and portfolio performance over strong baselines while preserving interpretability.","one_line_summary":"PRISM-VQ integrates vector-quantized latent factors with financial priors and a structure-conditioned mixture-of-experts to deliver improved cross-sectional stock return predictions and portfolio performance on CSI 300 and S&P 500.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That vector quantization reliably suppresses noise while preserving predictive cross-sectional structure and that the discrete codes provide effective routing signals for the mixture-of-experts without introducing regime misclassification.","pith_extraction_headline":"PRISM-VQ combines vector-quantized discrete latent factors with financial priors and a mixture-of-experts to improve dynamic cross-sectional stock return predictions."},"references":{"count":37,"sample":[{"doi":"","year":2025,"title":"Hypergraph neural networks to predict stock movements by exploring higher-order relationships","work_id":"8de8d143-6af6-477c-9543-4827fc451ef8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Matcc: A novel approach for ro- bust stock price prediction incorporating market trends and cross-time correlations","work_id":"818e323c-121e-440d-9cec-1e521d0aa97e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Xgboost: A scalable tree boosting system","work_id":"201b380e-e7dc-4ede-8f33-13d407e7bf07","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"A simple framework for contrastive learning of visual representations","work_id":"af318d86-525b-4804-9442-823880d84a5d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Automatic de- biased temporal-relational modeling for stock investment recommendation","work_id":"c47b7cfc-0ce0-4386-a2ce-58190052d9e1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":37,"snapshot_sha256":"d93314e082ba2c6bc4999164cb7c1c1b80ce9a2bcba06ebf397541bd168bbbeb","internal_anchors":3},"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":"2605.13407","created_at":"2026-05-18T02:44:47.496827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13407v1","created_at":"2026-05-18T02:44:47.496827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13407","created_at":"2026-05-18T02:44:47.496827+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2QW6COO2VK4","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2QW6COO2VK4UW6R","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2QW6COO","created_at":"2026-05-18T12:33:37.589309+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/K2QW6COO2VK4UW6RXTETEV3MPS","json":"https://pith.science/pith/K2QW6COO2VK4UW6RXTETEV3MPS.json","graph_json":"https://pith.science/api/pith-number/K2QW6COO2VK4UW6RXTETEV3MPS/graph.json","events_json":"https://pith.science/api/pith-number/K2QW6COO2VK4UW6RXTETEV3MPS/events.json","paper":"https://pith.science/paper/K2QW6COO"},"agent_actions":{"view_html":"https://pith.science/pith/K2QW6COO2VK4UW6RXTETEV3MPS","download_json":"https://pith.science/pith/K2QW6COO2VK4UW6RXTETEV3MPS.json","view_paper":"https://pith.science/paper/K2QW6COO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13407&json=true","fetch_graph":"https://pith.science/api/pith-number/K2QW6COO2VK4UW6RXTETEV3MPS/graph.json","fetch_events":"https://pith.science/api/pith-number/K2QW6COO2VK4UW6RXTETEV3MPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2QW6COO2VK4UW6RXTETEV3MPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2QW6COO2VK4UW6RXTETEV3MPS/action/storage_attestation","attest_author":"https://pith.science/pith/K2QW6COO2VK4UW6RXTETEV3MPS/action/author_attestation","sign_citation":"https://pith.science/pith/K2QW6COO2VK4UW6RXTETEV3MPS/action/citation_signature","submit_replication":"https://pith.science/pith/K2QW6COO2VK4UW6RXTETEV3MPS/action/replication_record"}},"created_at":"2026-05-18T02:44:47.496827+00:00","updated_at":"2026-05-18T02:44:47.496827+00:00"}