{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:73KJMSUCITWPYYORYSZ4N7OGIR","short_pith_number":"pith:73KJMSUC","schema_version":"1.0","canonical_sha256":"fed4964a8244ecfc61d1c4b3c6fdc64463bfb1de5bbcc07034d694c6b3c6ec94","source":{"kind":"arxiv","id":"2606.07534","version":1},"attestation_state":"computed","paper":{"title":"PulseBench-Tab: A Multilingual Benchmark for Table Extraction with Graph-Based Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Dushyanth Sekhar, Mohammed Hadi, Mohammed Wazir Adain, Ritvik Pandey, Sid Manchkanti","submitted_at":"2026-04-21T18:19:44Z","abstract_excerpt":"We introduce PulseBench-Tab, an open multilingual benchmark for evaluating table extraction from document images. The benchmark comprises 1,820 human-annotated tables spanning 9 languages and 4 scripts (Latin, CJK, Arabic, Cyrillic), drawn from 380 real-world source documents including financial filings, government reports, and regulatory disclosures. Tables range from 2 to 1,183 cells, with 48.1% containing merged or spanning cells. Alongside the dataset, we propose T-LAG (Table Logical Adjacency Graph), a novel evaluation metric that models tables as directed graphs over cell adjacencies and"},"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":"2606.07534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-21T18:19:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2a5f135b29739779fb5d002486dfe5ddb1eca4a6b1d77ad3051c1cd197d5e7ce","abstract_canon_sha256":"28884f369f1834624e4c05b4e8efed6ca7d2538ad01a24690755da03a2bd5204"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:41.920376Z","signature_b64":"bsKXX55zFWaot4I1jawwPl10QJpBy+nhYhgmL9IRrHcJPwvW8damj5TWloLHxTIJIsxxNHu5wpCxGerKkB2ZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fed4964a8244ecfc61d1c4b3c6fdc64463bfb1de5bbcc07034d694c6b3c6ec94","last_reissued_at":"2026-06-09T00:04:41.919678Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:41.919678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PulseBench-Tab: A Multilingual Benchmark for Table Extraction with Graph-Based Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Dushyanth Sekhar, Mohammed Hadi, Mohammed Wazir Adain, Ritvik Pandey, Sid Manchkanti","submitted_at":"2026-04-21T18:19:44Z","abstract_excerpt":"We introduce PulseBench-Tab, an open multilingual benchmark for evaluating table extraction from document images. The benchmark comprises 1,820 human-annotated tables spanning 9 languages and 4 scripts (Latin, CJK, Arabic, Cyrillic), drawn from 380 real-world source documents including financial filings, government reports, and regulatory disclosures. Tables range from 2 to 1,183 cells, with 48.1% containing merged or spanning cells. Alongside the dataset, we propose T-LAG (Table Logical Adjacency Graph), a novel evaluation metric that models tables as directed graphs over cell adjacencies and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07534","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/2606.07534/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":"2606.07534","created_at":"2026-06-09T00:04:41.919787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07534v1","created_at":"2026-06-09T00:04:41.919787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07534","created_at":"2026-06-09T00:04:41.919787+00:00"},{"alias_kind":"pith_short_12","alias_value":"73KJMSUCITWP","created_at":"2026-06-09T00:04:41.919787+00:00"},{"alias_kind":"pith_short_16","alias_value":"73KJMSUCITWPYYOR","created_at":"2026-06-09T00:04:41.919787+00:00"},{"alias_kind":"pith_short_8","alias_value":"73KJMSUC","created_at":"2026-06-09T00:04:41.919787+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/73KJMSUCITWPYYORYSZ4N7OGIR","json":"https://pith.science/pith/73KJMSUCITWPYYORYSZ4N7OGIR.json","graph_json":"https://pith.science/api/pith-number/73KJMSUCITWPYYORYSZ4N7OGIR/graph.json","events_json":"https://pith.science/api/pith-number/73KJMSUCITWPYYORYSZ4N7OGIR/events.json","paper":"https://pith.science/paper/73KJMSUC"},"agent_actions":{"view_html":"https://pith.science/pith/73KJMSUCITWPYYORYSZ4N7OGIR","download_json":"https://pith.science/pith/73KJMSUCITWPYYORYSZ4N7OGIR.json","view_paper":"https://pith.science/paper/73KJMSUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07534&json=true","fetch_graph":"https://pith.science/api/pith-number/73KJMSUCITWPYYORYSZ4N7OGIR/graph.json","fetch_events":"https://pith.science/api/pith-number/73KJMSUCITWPYYORYSZ4N7OGIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73KJMSUCITWPYYORYSZ4N7OGIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73KJMSUCITWPYYORYSZ4N7OGIR/action/storage_attestation","attest_author":"https://pith.science/pith/73KJMSUCITWPYYORYSZ4N7OGIR/action/author_attestation","sign_citation":"https://pith.science/pith/73KJMSUCITWPYYORYSZ4N7OGIR/action/citation_signature","submit_replication":"https://pith.science/pith/73KJMSUCITWPYYORYSZ4N7OGIR/action/replication_record"}},"created_at":"2026-06-09T00:04:41.919787+00:00","updated_at":"2026-06-09T00:04:41.919787+00:00"}