{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XUZUROJALGESJ544LW7PLUU46E","short_pith_number":"pith:XUZUROJA","schema_version":"1.0","canonical_sha256":"bd3348b920598924f79c5dbef5d29cf119e466c09207033baa90e4432f2c0626","source":{"kind":"arxiv","id":"2607.21780","version":1},"attestation_state":"computed","paper":{"title":"Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Abu Tyeb Azad, AKM Mahbubur Rahman, Aman Chadha, Amin Ahsan Ali, Armun Alam, Ezharuddin Jubaer, Fahim Ahmed, Ishita Sur Apan, Md Mofijul Islam, Sumaiya Karim Katha","submitted_at":"2026-07-23T19:52:58Z","abstract_excerpt":"Document packets, multiple documents concatenated into a single file, are common in government and administrative workflows, yet splitting them into their constituent documents is difficult, especially for low-resource languages. We introduce Khondo (Bangla for split/segment), the first benchmark for document packet splitting on Bangladeshi government forms. Unlike prior English and OCR-text-based datasets, Khondo is bilingual (Bangla--English) and vision-native; where models operate directly on page images. It spans five concatenation schemes, from sequential to fully shuffled, across 14 admi"},"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":"2607.21780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T19:52:58Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"262ee1fc17df8c67872d3072e423ee94b8397248e8bd7b16c33d20c1286c875c","abstract_canon_sha256":"098b47d8ea08f2f91d368084c0974db5853e1861a13d434e6e654540080da0c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:20.597825Z","signature_b64":"OJdEKfPIDwty/4jDsmi8vr/ag7KoYCchoK4kkoNVQw67QD+GG/h1nRi5k+UdnTgY0NBOgpldIALqyZ/3st3mBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd3348b920598924f79c5dbef5d29cf119e466c09207033baa90e4432f2c0626","last_reissued_at":"2026-07-27T00:20:20.596969Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:20.596969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Abu Tyeb Azad, AKM Mahbubur Rahman, Aman Chadha, Amin Ahsan Ali, Armun Alam, Ezharuddin Jubaer, Fahim Ahmed, Ishita Sur Apan, Md Mofijul Islam, Sumaiya Karim Katha","submitted_at":"2026-07-23T19:52:58Z","abstract_excerpt":"Document packets, multiple documents concatenated into a single file, are common in government and administrative workflows, yet splitting them into their constituent documents is difficult, especially for low-resource languages. We introduce Khondo (Bangla for split/segment), the first benchmark for document packet splitting on Bangladeshi government forms. Unlike prior English and OCR-text-based datasets, Khondo is bilingual (Bangla--English) and vision-native; where models operate directly on page images. It spans five concatenation schemes, from sequential to fully shuffled, across 14 admi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21780","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/2607.21780/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":"2607.21780","created_at":"2026-07-27T00:20:20.597413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21780v1","created_at":"2026-07-27T00:20:20.597413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21780","created_at":"2026-07-27T00:20:20.597413+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUZUROJALGES","created_at":"2026-07-27T00:20:20.597413+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUZUROJALGESJ544","created_at":"2026-07-27T00:20:20.597413+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUZUROJA","created_at":"2026-07-27T00:20:20.597413+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/XUZUROJALGESJ544LW7PLUU46E","json":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E.json","graph_json":"https://pith.science/api/pith-number/XUZUROJALGESJ544LW7PLUU46E/graph.json","events_json":"https://pith.science/api/pith-number/XUZUROJALGESJ544LW7PLUU46E/events.json","paper":"https://pith.science/paper/XUZUROJA"},"agent_actions":{"view_html":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E","download_json":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E.json","view_paper":"https://pith.science/paper/XUZUROJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21780&json=true","fetch_graph":"https://pith.science/api/pith-number/XUZUROJALGESJ544LW7PLUU46E/graph.json","fetch_events":"https://pith.science/api/pith-number/XUZUROJALGESJ544LW7PLUU46E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/action/storage_attestation","attest_author":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/action/author_attestation","sign_citation":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/action/citation_signature","submit_replication":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/action/replication_record"}},"created_at":"2026-07-27T00:20:20.597413+00:00","updated_at":"2026-07-27T00:20:20.597413+00:00"}