{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A4VW7TLZFO24LVLCUVO5E2BOPF","short_pith_number":"pith:A4VW7TLZ","canonical_record":{"source":{"id":"2505.20650","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T02:55:53Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"5783f011b5d83f0d53f7e37799cf25d69d3479fe4bfb034acd5ea3ee06e8ffcf","abstract_canon_sha256":"6b84628239a86ca23ccfd163ebd585282b7b2898253f4d26b0eb381019ce5b67"},"schema_version":"1.0"},"canonical_sha256":"072b6fcd792bb5c5d562a55dd2682e795dcf4533a84bfa737ffca29190a7e2de","source":{"kind":"arxiv","id":"2505.20650","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20650","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20650v5","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20650","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"A4VW7TLZFO24","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"A4VW7TLZFO24LVLC","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"A4VW7TLZ","created_at":"2026-05-20T00:04:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A4VW7TLZFO24LVLCUVO5E2BOPF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20650","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T02:55:53Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"5783f011b5d83f0d53f7e37799cf25d69d3479fe4bfb034acd5ea3ee06e8ffcf","abstract_canon_sha256":"6b84628239a86ca23ccfd163ebd585282b7b2898253f4d26b0eb381019ce5b67"},"schema_version":"1.0"},"canonical_sha256":"072b6fcd792bb5c5d562a55dd2682e795dcf4533a84bfa737ffca29190a7e2de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:10.105216Z","signature_b64":"NFgJLcN1AVXT9OXPqpSb3SCY54eFBBtK21QTqG2NuHt29PhrHDrKE4m/NX3rMV46IzMh2DEE/SobeJe1Bzx4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"072b6fcd792bb5c5d562a55dd2682e795dcf4533a84bfa737ffca29190a7e2de","last_reissued_at":"2026-05-20T00:04:10.104426Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:10.104426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20650","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3PiyLU2KPUTngujg4AzgK4gHI+96U87y4D7QeJK2Qzj2uJo4sy+q7cu5T60LjvhH+ddnJ+kPVpFtmIrKgWkUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:13:50.457078Z"},"content_sha256":"eb6a1761ca9f9e5da3298ee488c102601c6b111a2816a27f16a762b334a5e7f7","schema_version":"1.0","event_id":"sha256:eb6a1761ca9f9e5da3298ee488c102601c6b111a2816a27f16a762b334a5e7f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A4VW7TLZFO24LVLCUVO5E2BOPF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.CL","authors_text":"Chenri Luo, Chen Xu, Dongji Feng, Fengran Mo, Guojun Xiong, Jianxing Chen, Jian-Yun Nie, Jimin Huang, Junwei Wu, Kaiwen He, Keyi Wang, Lingfei Qian, Qianqian Xie, Qinchuan Zhang, Shengyuan Lin, Xiao-Yang Liu, Xueqing Peng, Yang Ren, Yan Wang, Yi Han, Ziyang Xu","submitted_at":"2025-05-27T02:55:53Z","abstract_excerpt":"Accurate interpretation of numerical data in financial reports is critical for markets and regulators. Although XBRL (eXtensible Business Reporting Language) provides a standard for tagging financial figures, mapping thousands of facts to over 10k US GAAP concepts remains costly and error prone. Existing benchmarks oversimplify this task as flat, single step classification over small subsets of concepts, ignoring the hierarchical semantics of the taxonomy and the structured nature of financial documents. Consequently, these benchmarks fail to evaluate Large Language Models (LLMs) under realist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20650","kind":"arxiv","version":5},"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/2505.20650/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":"2026-05-20T00:04:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8dTv3G3yOtgmhMItJhE2zkBA3L+fGPrpaaIH7ytHbZYW+ehbmKT7/rH6wjOp8+z4PXmsPxF5GY8aISEZLFhVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:13:50.457803Z"},"content_sha256":"7f30d3990f1c61f5cbc9ee28fbf45847b28c6320766332f774ee81ab4375ed9d","schema_version":"1.0","event_id":"sha256:7f30d3990f1c61f5cbc9ee28fbf45847b28c6320766332f774ee81ab4375ed9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4VW7TLZFO24LVLCUVO5E2BOPF/bundle.json","state_url":"https://pith.science/pith/A4VW7TLZFO24LVLCUVO5E2BOPF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4VW7TLZFO24LVLCUVO5E2BOPF/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":"2026-05-26T17:13:50Z","links":{"resolver":"https://pith.science/pith/A4VW7TLZFO24LVLCUVO5E2BOPF","bundle":"https://pith.science/pith/A4VW7TLZFO24LVLCUVO5E2BOPF/bundle.json","state":"https://pith.science/pith/A4VW7TLZFO24LVLCUVO5E2BOPF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4VW7TLZFO24LVLCUVO5E2BOPF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A4VW7TLZFO24LVLCUVO5E2BOPF","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":"6b84628239a86ca23ccfd163ebd585282b7b2898253f4d26b0eb381019ce5b67","cross_cats_sorted":["cs.AI","cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T02:55:53Z","title_canon_sha256":"5783f011b5d83f0d53f7e37799cf25d69d3479fe4bfb034acd5ea3ee06e8ffcf"},"schema_version":"1.0","source":{"id":"2505.20650","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20650","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20650v5","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20650","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"A4VW7TLZFO24","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"A4VW7TLZFO24LVLC","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"A4VW7TLZ","created_at":"2026-05-20T00:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:7f30d3990f1c61f5cbc9ee28fbf45847b28c6320766332f774ee81ab4375ed9d","target":"graph","created_at":"2026-05-20T00:04:10Z","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/2505.20650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate interpretation of numerical data in financial reports is critical for markets and regulators. Although XBRL (eXtensible Business Reporting Language) provides a standard for tagging financial figures, mapping thousands of facts to over 10k US GAAP concepts remains costly and error prone. Existing benchmarks oversimplify this task as flat, single step classification over small subsets of concepts, ignoring the hierarchical semantics of the taxonomy and the structured nature of financial documents. Consequently, these benchmarks fail to evaluate Large Language Models (LLMs) under realist","authors_text":"Chenri Luo, Chen Xu, Dongji Feng, Fengran Mo, Guojun Xiong, Jianxing Chen, Jian-Yun Nie, Jimin Huang, Junwei Wu, Kaiwen He, Keyi Wang, Lingfei Qian, Qianqian Xie, Qinchuan Zhang, Shengyuan Lin, Xiao-Yang Liu, Xueqing Peng, Yang Ren, Yan Wang, Yi Han, Ziyang Xu","cross_cats":["cs.AI","cs.CE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T02:55:53Z","title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20650","kind":"arxiv","version":5},"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:eb6a1761ca9f9e5da3298ee488c102601c6b111a2816a27f16a762b334a5e7f7","target":"record","created_at":"2026-05-20T00:04:10Z","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":"6b84628239a86ca23ccfd163ebd585282b7b2898253f4d26b0eb381019ce5b67","cross_cats_sorted":["cs.AI","cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T02:55:53Z","title_canon_sha256":"5783f011b5d83f0d53f7e37799cf25d69d3479fe4bfb034acd5ea3ee06e8ffcf"},"schema_version":"1.0","source":{"id":"2505.20650","kind":"arxiv","version":5}},"canonical_sha256":"072b6fcd792bb5c5d562a55dd2682e795dcf4533a84bfa737ffca29190a7e2de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"072b6fcd792bb5c5d562a55dd2682e795dcf4533a84bfa737ffca29190a7e2de","first_computed_at":"2026-05-20T00:04:10.104426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:10.104426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NFgJLcN1AVXT9OXPqpSb3SCY54eFBBtK21QTqG2NuHt29PhrHDrKE4m/NX3rMV46IzMh2DEE/SobeJe1Bzx4DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:10.105216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20650","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb6a1761ca9f9e5da3298ee488c102601c6b111a2816a27f16a762b334a5e7f7","sha256:7f30d3990f1c61f5cbc9ee28fbf45847b28c6320766332f774ee81ab4375ed9d"],"state_sha256":"c1a416e87f895b13e3dee877cd5cb06f030165983db574cb7887ba0cf1ac8887"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pz2LkYqUfQY8fJpRM6CKCJ717GHCs6JzBskHeosoaXrQTSRZRew8x5fPqIjQfa3f9lLc/6Epkohqc3vSbaOpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:13:50.460656Z","bundle_sha256":"084ed91d3a7d580d335afc76a6fd1011b8ada82e4255a56708519b764eb2d3ea"}}