{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XURRAWSRHKB2Y7GCXXLEPHZW3F","short_pith_number":"pith:XURRAWSR","schema_version":"1.0","canonical_sha256":"bd23105a513a83ac7cc2bdd6479f36d975699e34f54b58a814b238ec5174f8d4","source":{"kind":"arxiv","id":"2605.30652","version":1},"attestation_state":"computed","paper":{"title":"Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brian Y. C. Leung (Mike), Noelle Jung, Yujin Jeong","submitted_at":"2026-05-28T23:14:45Z","abstract_excerpt":"Traditional multi-modal financial forecasting often relies on scalar sentiment scores, which fail to capture the nuances of financial news. To address this information loss, this paper explores high-dimensional representation learning by replacing discrete polarity ratings with dense FinBERT embeddings within a Transformer-based forecasting architecture. We benchmarked various embedding strategies on the FNSPID dataset, including raw embeddings, attention-weighted aggregation, and a custom Siamese network. While the attention-based mechanism struggled with the low signal-to-noise ratio typical"},"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":"2605.30652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T23:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"ba1409b930a06d0ebd2170bb7f75fd3e90aa940addbac28fd1ad812804b96fa3","abstract_canon_sha256":"e58f857b4bd2b05c4851bb4afed3f7fc076194e400dc3274f733a8a55b489d16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:06.440799Z","signature_b64":"I2vzgLUaSqHjZlyxh1KHRbEPsiULV1PAS5dBa/nwkpOxOMpjsxnN11i9TZoeMNMrAjOPfe+VLU6iDydoP2OICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd23105a513a83ac7cc2bdd6479f36d975699e34f54b58a814b238ec5174f8d4","last_reissued_at":"2026-06-01T01:03:06.439671Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:06.439671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brian Y. C. Leung (Mike), Noelle Jung, Yujin Jeong","submitted_at":"2026-05-28T23:14:45Z","abstract_excerpt":"Traditional multi-modal financial forecasting often relies on scalar sentiment scores, which fail to capture the nuances of financial news. To address this information loss, this paper explores high-dimensional representation learning by replacing discrete polarity ratings with dense FinBERT embeddings within a Transformer-based forecasting architecture. We benchmarked various embedding strategies on the FNSPID dataset, including raw embeddings, attention-weighted aggregation, and a custom Siamese network. While the attention-based mechanism struggled with the low signal-to-noise ratio typical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30652","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/2605.30652/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":"2605.30652","created_at":"2026-06-01T01:03:06.439835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30652v1","created_at":"2026-06-01T01:03:06.439835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30652","created_at":"2026-06-01T01:03:06.439835+00:00"},{"alias_kind":"pith_short_12","alias_value":"XURRAWSRHKB2","created_at":"2026-06-01T01:03:06.439835+00:00"},{"alias_kind":"pith_short_16","alias_value":"XURRAWSRHKB2Y7GC","created_at":"2026-06-01T01:03:06.439835+00:00"},{"alias_kind":"pith_short_8","alias_value":"XURRAWSR","created_at":"2026-06-01T01:03:06.439835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.30652","citing_title":"Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F","json":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F.json","graph_json":"https://pith.science/api/pith-number/XURRAWSRHKB2Y7GCXXLEPHZW3F/graph.json","events_json":"https://pith.science/api/pith-number/XURRAWSRHKB2Y7GCXXLEPHZW3F/events.json","paper":"https://pith.science/paper/XURRAWSR"},"agent_actions":{"view_html":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F","download_json":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F.json","view_paper":"https://pith.science/paper/XURRAWSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30652&json=true","fetch_graph":"https://pith.science/api/pith-number/XURRAWSRHKB2Y7GCXXLEPHZW3F/graph.json","fetch_events":"https://pith.science/api/pith-number/XURRAWSRHKB2Y7GCXXLEPHZW3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F/action/storage_attestation","attest_author":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F/action/author_attestation","sign_citation":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F/action/citation_signature","submit_replication":"https://pith.science/pith/XURRAWSRHKB2Y7GCXXLEPHZW3F/action/replication_record"}},"created_at":"2026-06-01T01:03:06.439835+00:00","updated_at":"2026-06-01T01:03:06.439835+00:00"}