{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:24RP6IDVVAPBV2LE2U3TUBG2YV","short_pith_number":"pith:24RP6IDV","schema_version":"1.0","canonical_sha256":"d722ff2075a81e1ae964d5373a04dac567f6f9939e7f9f1e21c8c921bccfcbb4","source":{"kind":"arxiv","id":"2411.07142","version":1},"attestation_state":"computed","paper":{"title":"Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adapt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charlie Flanagan, Jason He, Mano Vikash Janardhanan, Peter Anderson, Wei Cheng","submitted_at":"2024-11-11T17:13:28Z","abstract_excerpt":"Financial documents are filled with specialized terminology, arcane jargon, and curious acronyms that pose challenges for general-purpose text embeddings. Yet, few text embeddings specialized for finance have been reported in the literature, perhaps in part due to a lack of public datasets and benchmarks. We present BAM embeddings, a set of text embeddings finetuned on a carefully constructed dataset of 14.3M query-passage pairs. Demonstrating the benefits of domain-specific training, BAM embeddings achieve Recall@1 of 62.8% on a held-out test set, vs. only 39.2% for the best general-purpose t"},"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":"2411.07142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T17:13:28Z","cross_cats_sorted":[],"title_canon_sha256":"f5ac85b382df3ec25ade0c5790e119783a768614bcc30ed31738302475a64fdc","abstract_canon_sha256":"16783a92d24d93619ef072134622fe797b656cae9afeaf430e1cd8b32dbf616d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:57.456454Z","signature_b64":"dTkA7HTNwk+ukv8n4456XpbztsdbhrSTsu6yPHnkvsyRyorXa+Zs2rK/bafY4uwAvQV2/oczMONnkA7rP0/LBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d722ff2075a81e1ae964d5373a04dac567f6f9939e7f9f1e21c8c921bccfcbb4","last_reissued_at":"2026-07-05T09:33:57.455882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:57.455882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adapt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charlie Flanagan, Jason He, Mano Vikash Janardhanan, Peter Anderson, Wei Cheng","submitted_at":"2024-11-11T17:13:28Z","abstract_excerpt":"Financial documents are filled with specialized terminology, arcane jargon, and curious acronyms that pose challenges for general-purpose text embeddings. Yet, few text embeddings specialized for finance have been reported in the literature, perhaps in part due to a lack of public datasets and benchmarks. We present BAM embeddings, a set of text embeddings finetuned on a carefully constructed dataset of 14.3M query-passage pairs. Demonstrating the benefits of domain-specific training, BAM embeddings achieve Recall@1 of 62.8% on a held-out test set, vs. only 39.2% for the best general-purpose t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07142","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/2411.07142/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":"2411.07142","created_at":"2026-07-05T09:33:57.455953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07142v1","created_at":"2026-07-05T09:33:57.455953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07142","created_at":"2026-07-05T09:33:57.455953+00:00"},{"alias_kind":"pith_short_12","alias_value":"24RP6IDVVAPB","created_at":"2026-07-05T09:33:57.455953+00:00"},{"alias_kind":"pith_short_16","alias_value":"24RP6IDVVAPBV2LE","created_at":"2026-07-05T09:33:57.455953+00:00"},{"alias_kind":"pith_short_8","alias_value":"24RP6IDV","created_at":"2026-07-05T09:33:57.455953+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/24RP6IDVVAPBV2LE2U3TUBG2YV","json":"https://pith.science/pith/24RP6IDVVAPBV2LE2U3TUBG2YV.json","graph_json":"https://pith.science/api/pith-number/24RP6IDVVAPBV2LE2U3TUBG2YV/graph.json","events_json":"https://pith.science/api/pith-number/24RP6IDVVAPBV2LE2U3TUBG2YV/events.json","paper":"https://pith.science/paper/24RP6IDV"},"agent_actions":{"view_html":"https://pith.science/pith/24RP6IDVVAPBV2LE2U3TUBG2YV","download_json":"https://pith.science/pith/24RP6IDVVAPBV2LE2U3TUBG2YV.json","view_paper":"https://pith.science/paper/24RP6IDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07142&json=true","fetch_graph":"https://pith.science/api/pith-number/24RP6IDVVAPBV2LE2U3TUBG2YV/graph.json","fetch_events":"https://pith.science/api/pith-number/24RP6IDVVAPBV2LE2U3TUBG2YV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24RP6IDVVAPBV2LE2U3TUBG2YV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24RP6IDVVAPBV2LE2U3TUBG2YV/action/storage_attestation","attest_author":"https://pith.science/pith/24RP6IDVVAPBV2LE2U3TUBG2YV/action/author_attestation","sign_citation":"https://pith.science/pith/24RP6IDVVAPBV2LE2U3TUBG2YV/action/citation_signature","submit_replication":"https://pith.science/pith/24RP6IDVVAPBV2LE2U3TUBG2YV/action/replication_record"}},"created_at":"2026-07-05T09:33:57.455953+00:00","updated_at":"2026-07-05T09:33:57.455953+00:00"}