{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:24RP6IDVVAPBV2LE2U3TUBG2YV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"16783a92d24d93619ef072134622fe797b656cae9afeaf430e1cd8b32dbf616d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T17:13:28Z","title_canon_sha256":"f5ac85b382df3ec25ade0c5790e119783a768614bcc30ed31738302475a64fdc"},"schema_version":"1.0","source":{"id":"2411.07142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07142","created_at":"2026-07-05T09:33:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07142v1","created_at":"2026-07-05T09:33:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07142","created_at":"2026-07-05T09:33:57Z"},{"alias_kind":"pith_short_12","alias_value":"24RP6IDVVAPB","created_at":"2026-07-05T09:33:57Z"},{"alias_kind":"pith_short_16","alias_value":"24RP6IDVVAPBV2LE","created_at":"2026-07-05T09:33:57Z"},{"alias_kind":"pith_short_8","alias_value":"24RP6IDV","created_at":"2026-07-05T09:33:57Z"}],"graph_snapshots":[{"event_id":"sha256:6301880a264ecc948b93aa9f3c654bec6a6f75c4df914f3e698bb3f4eca69b25","target":"graph","created_at":"2026-07-05T09:33:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.07142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Charlie Flanagan, Jason He, Mano Vikash Janardhanan, Peter Anderson, Wei Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T17:13:28Z","title":"Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adapt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07142","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f7095abd25553c41bc34ad0abe5f3db54335c631ec3ef09011907b6ed1667ffd","target":"record","created_at":"2026-07-05T09:33:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"16783a92d24d93619ef072134622fe797b656cae9afeaf430e1cd8b32dbf616d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T17:13:28Z","title_canon_sha256":"f5ac85b382df3ec25ade0c5790e119783a768614bcc30ed31738302475a64fdc"},"schema_version":"1.0","source":{"id":"2411.07142","kind":"arxiv","version":1}},"canonical_sha256":"d722ff2075a81e1ae964d5373a04dac567f6f9939e7f9f1e21c8c921bccfcbb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d722ff2075a81e1ae964d5373a04dac567f6f9939e7f9f1e21c8c921bccfcbb4","first_computed_at":"2026-07-05T09:33:57.455882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:57.455882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dTkA7HTNwk+ukv8n4456XpbztsdbhrSTsu6yPHnkvsyRyorXa+Zs2rK/bafY4uwAvQV2/oczMONnkA7rP0/LBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:57.456454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7095abd25553c41bc34ad0abe5f3db54335c631ec3ef09011907b6ed1667ffd","sha256:6301880a264ecc948b93aa9f3c654bec6a6f75c4df914f3e698bb3f4eca69b25"],"state_sha256":"85ad483da91f277b54185829c8cd3d4abf4208552e365b5d0cb926fc71364deb"}