{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VKQLWRM5N55SH354HLGISZG746","short_pith_number":"pith:VKQLWRM5","schema_version":"1.0","canonical_sha256":"aaa0bb459d6f7b23efbc3acc8964dfe7bace6ba3fbe94ca3f1251161e9c23b14","source":{"kind":"arxiv","id":"2507.00041","version":1},"attestation_state":"computed","paper":{"title":"TalentMine: LLM-Based Extraction and Question-Answering from Multimodal Talent Tables","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.AI","authors_text":"ChaoChun Liu, Fang Wang, Varun Mannam, Xin Chen","submitted_at":"2025-06-22T22:17:42Z","abstract_excerpt":"In talent management systems, critical information often resides in complex tabular formats, presenting significant retrieval challenges for conventional language models. These challenges are pronounced when processing Talent documentation that requires precise interpretation of tabular relationships for accurate information retrieval and downstream decision-making. Current table extraction methods struggle with semantic understanding, resulting in poor performance when integrated into retrieval-augmented chat applications. This paper identifies a key bottleneck - while structural table inform"},"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":"2507.00041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-22T22:17:42Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"5a0f8d0d1e70bb827af135cf6bec3e61cb30a58dbadec7d3124d8984e67574ce","abstract_canon_sha256":"a765b5d3f68b3db52c033747296a1f993cae462bdaaaf3e8a85f5eafcdd05648"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:35.520750Z","signature_b64":"IEyTpJMUqRIGf8KJBz+NZJCtmVqDvJ1WSZO55GZUl9XU+S8D3POzjc8LA/tfo+GqPDAQJMBO9srXc9k1ULopCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aaa0bb459d6f7b23efbc3acc8964dfe7bace6ba3fbe94ca3f1251161e9c23b14","last_reissued_at":"2026-07-05T11:29:35.520170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:35.520170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TalentMine: LLM-Based Extraction and Question-Answering from Multimodal Talent Tables","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.AI","authors_text":"ChaoChun Liu, Fang Wang, Varun Mannam, Xin Chen","submitted_at":"2025-06-22T22:17:42Z","abstract_excerpt":"In talent management systems, critical information often resides in complex tabular formats, presenting significant retrieval challenges for conventional language models. These challenges are pronounced when processing Talent documentation that requires precise interpretation of tabular relationships for accurate information retrieval and downstream decision-making. Current table extraction methods struggle with semantic understanding, resulting in poor performance when integrated into retrieval-augmented chat applications. This paper identifies a key bottleneck - while structural table inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00041","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/2507.00041/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":"2507.00041","created_at":"2026-07-05T11:29:35.520237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00041v1","created_at":"2026-07-05T11:29:35.520237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00041","created_at":"2026-07-05T11:29:35.520237+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKQLWRM5N55S","created_at":"2026-07-05T11:29:35.520237+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKQLWRM5N55SH354","created_at":"2026-07-05T11:29:35.520237+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKQLWRM5","created_at":"2026-07-05T11:29:35.520237+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/VKQLWRM5N55SH354HLGISZG746","json":"https://pith.science/pith/VKQLWRM5N55SH354HLGISZG746.json","graph_json":"https://pith.science/api/pith-number/VKQLWRM5N55SH354HLGISZG746/graph.json","events_json":"https://pith.science/api/pith-number/VKQLWRM5N55SH354HLGISZG746/events.json","paper":"https://pith.science/paper/VKQLWRM5"},"agent_actions":{"view_html":"https://pith.science/pith/VKQLWRM5N55SH354HLGISZG746","download_json":"https://pith.science/pith/VKQLWRM5N55SH354HLGISZG746.json","view_paper":"https://pith.science/paper/VKQLWRM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00041&json=true","fetch_graph":"https://pith.science/api/pith-number/VKQLWRM5N55SH354HLGISZG746/graph.json","fetch_events":"https://pith.science/api/pith-number/VKQLWRM5N55SH354HLGISZG746/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKQLWRM5N55SH354HLGISZG746/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKQLWRM5N55SH354HLGISZG746/action/storage_attestation","attest_author":"https://pith.science/pith/VKQLWRM5N55SH354HLGISZG746/action/author_attestation","sign_citation":"https://pith.science/pith/VKQLWRM5N55SH354HLGISZG746/action/citation_signature","submit_replication":"https://pith.science/pith/VKQLWRM5N55SH354HLGISZG746/action/replication_record"}},"created_at":"2026-07-05T11:29:35.520237+00:00","updated_at":"2026-07-05T11:29:35.520237+00:00"}