{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5FODSJOKAJN57II24CA4M55QBP","short_pith_number":"pith:5FODSJOK","canonical_record":{"source":{"id":"2502.10990","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T04:23:52Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3b13aab358769f57207b8f14dedd9c81e3f8af97238e65816b8cf6258b261ae5","abstract_canon_sha256":"63a38544c1894070324c2251a422ff14f6cea30b85a74a92528bd6426dbb9666"},"schema_version":"1.0"},"canonical_sha256":"e95c3925ca025bdfa11ae081c677b00be73ea5bdc53d601aaf279b7997ed4eca","source":{"kind":"arxiv","id":"2502.10990","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10990","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10990v3","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10990","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"pith_short_12","alias_value":"5FODSJOKAJN5","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"pith_short_16","alias_value":"5FODSJOKAJN57II2","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"pith_short_8","alias_value":"5FODSJOK","created_at":"2026-07-05T12:09:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5FODSJOKAJN57II24CA4M55QBP","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10990","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T04:23:52Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3b13aab358769f57207b8f14dedd9c81e3f8af97238e65816b8cf6258b261ae5","abstract_canon_sha256":"63a38544c1894070324c2251a422ff14f6cea30b85a74a92528bd6426dbb9666"},"schema_version":"1.0"},"canonical_sha256":"e95c3925ca025bdfa11ae081c677b00be73ea5bdc53d601aaf279b7997ed4eca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:43.585448Z","signature_b64":"JpIyfJzKZ2PqHP91gW61JPeEczi9fa4tmSWHzoeLeEESI/8LyEItG47/jeSA/skaZpysANSSM8bUI4877R4nAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e95c3925ca025bdfa11ae081c677b00be73ea5bdc53d601aaf279b7997ed4eca","last_reissued_at":"2026-07-05T12:09:43.584822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:43.584822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10990","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLcc+p4jyJvV+uSq+Qm1P4La5u2dBBCQsIJoqrc3CIpR0YJD+iPrUjYhTIqalmHkpz09/h/WP3Zz3KU+DzLiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:12:31.482120Z"},"content_sha256":"fedee8d98d35ec632cd51eededc5dd346b0b011c045b90cbce92477df7ab0b48","schema_version":"1.0","event_id":"sha256:fedee8d98d35ec632cd51eededc5dd346b0b011c045b90cbce92477df7ab0b48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5FODSJOKAJN57II24CA4M55QBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FinMTEB: Finance Massive Text Embedding Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Yixuan Tang, Yi Yang","submitted_at":"2025-02-16T04:23:52Z","abstract_excerpt":"Embedding models play a crucial role in representing and retrieving information across various NLP applications. Recent advances in large language models (LLMs) have further enhanced the performance of embedding models. While these models are often benchmarked on general-purpose datasets, real-world applications demand domain-specific evaluation. In this work, we introduce the Finance Massive Text Embedding Benchmark (FinMTEB), a specialized counterpart to MTEB designed for the financial domain. FinMTEB comprises 64 financial domain-specific embedding datasets across 7 tasks that cover diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10990","kind":"arxiv","version":3},"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/2502.10990/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srw82NldNq1+XVMm/KMlVa5EPkJgiKXqZozs532GiTuyRwEfcH4tRX91hLSxl+OYXoBv20QdMm+Ghw9+wMX1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:12:31.483031Z"},"content_sha256":"41f7db9a3fbe58ccb9616f18342a21998f4596ecbae302d4bf6ea84e6a3aec2e","schema_version":"1.0","event_id":"sha256:41f7db9a3fbe58ccb9616f18342a21998f4596ecbae302d4bf6ea84e6a3aec2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FODSJOKAJN57II24CA4M55QBP/bundle.json","state_url":"https://pith.science/pith/5FODSJOKAJN57II24CA4M55QBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FODSJOKAJN57II24CA4M55QBP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T00:12:31Z","links":{"resolver":"https://pith.science/pith/5FODSJOKAJN57II24CA4M55QBP","bundle":"https://pith.science/pith/5FODSJOKAJN57II24CA4M55QBP/bundle.json","state":"https://pith.science/pith/5FODSJOKAJN57II24CA4M55QBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FODSJOKAJN57II24CA4M55QBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5FODSJOKAJN57II24CA4M55QBP","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":"63a38544c1894070324c2251a422ff14f6cea30b85a74a92528bd6426dbb9666","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T04:23:52Z","title_canon_sha256":"3b13aab358769f57207b8f14dedd9c81e3f8af97238e65816b8cf6258b261ae5"},"schema_version":"1.0","source":{"id":"2502.10990","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10990","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10990v3","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10990","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"pith_short_12","alias_value":"5FODSJOKAJN5","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"pith_short_16","alias_value":"5FODSJOKAJN57II2","created_at":"2026-07-05T12:09:43Z"},{"alias_kind":"pith_short_8","alias_value":"5FODSJOK","created_at":"2026-07-05T12:09:43Z"}],"graph_snapshots":[{"event_id":"sha256:41f7db9a3fbe58ccb9616f18342a21998f4596ecbae302d4bf6ea84e6a3aec2e","target":"graph","created_at":"2026-07-05T12:09:43Z","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/2502.10990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embedding models play a crucial role in representing and retrieving information across various NLP applications. Recent advances in large language models (LLMs) have further enhanced the performance of embedding models. While these models are often benchmarked on general-purpose datasets, real-world applications demand domain-specific evaluation. In this work, we introduce the Finance Massive Text Embedding Benchmark (FinMTEB), a specialized counterpart to MTEB designed for the financial domain. FinMTEB comprises 64 financial domain-specific embedding datasets across 7 tasks that cover diverse","authors_text":"Yixuan Tang, Yi Yang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T04:23:52Z","title":"FinMTEB: Finance Massive Text Embedding Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10990","kind":"arxiv","version":3},"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:fedee8d98d35ec632cd51eededc5dd346b0b011c045b90cbce92477df7ab0b48","target":"record","created_at":"2026-07-05T12:09:43Z","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":"63a38544c1894070324c2251a422ff14f6cea30b85a74a92528bd6426dbb9666","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T04:23:52Z","title_canon_sha256":"3b13aab358769f57207b8f14dedd9c81e3f8af97238e65816b8cf6258b261ae5"},"schema_version":"1.0","source":{"id":"2502.10990","kind":"arxiv","version":3}},"canonical_sha256":"e95c3925ca025bdfa11ae081c677b00be73ea5bdc53d601aaf279b7997ed4eca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e95c3925ca025bdfa11ae081c677b00be73ea5bdc53d601aaf279b7997ed4eca","first_computed_at":"2026-07-05T12:09:43.584822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:43.584822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JpIyfJzKZ2PqHP91gW61JPeEczi9fa4tmSWHzoeLeEESI/8LyEItG47/jeSA/skaZpysANSSM8bUI4877R4nAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:43.585448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10990","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fedee8d98d35ec632cd51eededc5dd346b0b011c045b90cbce92477df7ab0b48","sha256:41f7db9a3fbe58ccb9616f18342a21998f4596ecbae302d4bf6ea84e6a3aec2e"],"state_sha256":"d370e28b432d78433739520107fcc93eaddb496e9f675ed3ef37364bdf91c1a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LXTU5Ye6sB7NGKd1Wj3PuWBA14w/aijto4HadznkakrPnX+yXHBpHJ9/bwTgG1LlKlsmmy9nqimhfcHoVv1mAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:12:31.488171Z","bundle_sha256":"6d8a486899d71e13a09aa2fc9659f595acf8ea72a256dc2d4e702af25930fbcd"}}