{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C6SY63RM5244JY7RUHJEPDEQBF","short_pith_number":"pith:C6SY63RM","schema_version":"1.0","canonical_sha256":"17a58f6e2ceeb9c4e3f1a1d2478c900942bffa25bf3caec4cab9c80daa1c3d3c","source":{"kind":"arxiv","id":"2605.28714","version":1},"attestation_state":"computed","paper":{"title":"IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aman Patel, Arnav Hiray, Liqin Ye, Michael Galarnyk, Prasun Banerjee, Rutwik Routu, Sagnik Nandi, Siddhartha Somani, Siddharth Lohani, Sudheer Chava, Vidhyakshaya Kannan","submitted_at":"2026-05-27T16:36:39Z","abstract_excerpt":"An Initial Public Offering (IPO) filing is a document released when a private firm goes public, allowing individual (retail) investors to purchase its shares. These filings describe a firm's business, financials, and risks and are long, multimodal documents with narrative text and images. Despite their importance to financial markets, there is no large-scale, standardized dataset or benchmark for studying IPO filings with modern language and multimodal models. These documents pose significant challenges: filings frequently exceed 500,000 tokens and lack consistent structural organization. We i"},"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":"2605.28714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T16:36:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a23209cf415331640879efae8883e03ef04853401a4516484f234503a33ce71","abstract_canon_sha256":"70764d33508d5c9681f0332293b9bd76170fdcdd823cf970134416a554e90f29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:00.859393Z","signature_b64":"9YaogDUL9qIAurlQCUAdTO/a+ZEQf7TqvutMD9ibTHVg/F1SDAIR6QfvdPJwQazrCeW1jTcq546W4ps5dcSoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17a58f6e2ceeb9c4e3f1a1d2478c900942bffa25bf3caec4cab9c80daa1c3d3c","last_reissued_at":"2026-05-28T02:05:00.858908Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:00.858908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aman Patel, Arnav Hiray, Liqin Ye, Michael Galarnyk, Prasun Banerjee, Rutwik Routu, Sagnik Nandi, Siddhartha Somani, Siddharth Lohani, Sudheer Chava, Vidhyakshaya Kannan","submitted_at":"2026-05-27T16:36:39Z","abstract_excerpt":"An Initial Public Offering (IPO) filing is a document released when a private firm goes public, allowing individual (retail) investors to purchase its shares. These filings describe a firm's business, financials, and risks and are long, multimodal documents with narrative text and images. Despite their importance to financial markets, there is no large-scale, standardized dataset or benchmark for studying IPO filings with modern language and multimodal models. These documents pose significant challenges: filings frequently exceed 500,000 tokens and lack consistent structural organization. We i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28714","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/2605.28714/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":"2605.28714","created_at":"2026-05-28T02:05:00.858986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28714v1","created_at":"2026-05-28T02:05:00.858986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28714","created_at":"2026-05-28T02:05:00.858986+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6SY63RM5244","created_at":"2026-05-28T02:05:00.858986+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6SY63RM5244JY7R","created_at":"2026-05-28T02:05:00.858986+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6SY63RM","created_at":"2026-05-28T02:05:00.858986+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/C6SY63RM5244JY7RUHJEPDEQBF","json":"https://pith.science/pith/C6SY63RM5244JY7RUHJEPDEQBF.json","graph_json":"https://pith.science/api/pith-number/C6SY63RM5244JY7RUHJEPDEQBF/graph.json","events_json":"https://pith.science/api/pith-number/C6SY63RM5244JY7RUHJEPDEQBF/events.json","paper":"https://pith.science/paper/C6SY63RM"},"agent_actions":{"view_html":"https://pith.science/pith/C6SY63RM5244JY7RUHJEPDEQBF","download_json":"https://pith.science/pith/C6SY63RM5244JY7RUHJEPDEQBF.json","view_paper":"https://pith.science/paper/C6SY63RM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28714&json=true","fetch_graph":"https://pith.science/api/pith-number/C6SY63RM5244JY7RUHJEPDEQBF/graph.json","fetch_events":"https://pith.science/api/pith-number/C6SY63RM5244JY7RUHJEPDEQBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6SY63RM5244JY7RUHJEPDEQBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6SY63RM5244JY7RUHJEPDEQBF/action/storage_attestation","attest_author":"https://pith.science/pith/C6SY63RM5244JY7RUHJEPDEQBF/action/author_attestation","sign_citation":"https://pith.science/pith/C6SY63RM5244JY7RUHJEPDEQBF/action/citation_signature","submit_replication":"https://pith.science/pith/C6SY63RM5244JY7RUHJEPDEQBF/action/replication_record"}},"created_at":"2026-05-28T02:05:00.858986+00:00","updated_at":"2026-05-28T02:05:00.858986+00:00"}