{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XUZUROJALGESJ544LW7PLUU46E","short_pith_number":"pith:XUZUROJA","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"},"canonical_sha256":"bd3348b920598924f79c5dbef5d29cf119e466c09207033baa90e4432f2c0626","source":{"kind":"arxiv","id":"2607.21780","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21780","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21780v1","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21780","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"XUZUROJALGES","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"XUZUROJALGESJ544","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"XUZUROJA","created_at":"2026-07-27T00:20:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XUZUROJALGESJ544LW7PLUU46E","target":"record","payload":{"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"},"canonical_sha256":"bd3348b920598924f79c5dbef5d29cf119e466c09207033baa90e4432f2c0626","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"},"source_kind":"arxiv","source_id":"2607.21780","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-27T00:20:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fFcK2GH9BNkGmWDZx2m0dxJ14tZeeAHZ2eJd9fzOZV06tC3ekJWsW5zJuq1Dl8cM1CqEdIGycOCIuqDh2tidCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:30:25.632791Z"},"content_sha256":"b72091be09bad7c859820a5ca97e6ff61c68f94f3d1aaa5a80e6af1509e0447d","schema_version":"1.0","event_id":"sha256:b72091be09bad7c859820a5ca97e6ff61c68f94f3d1aaa5a80e6af1509e0447d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XUZUROJALGESJ544LW7PLUU46E","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-27T00:20:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgUHi9RhA/PPE34EOEt9B7fkExe5UnTUYh5GaDVBKOjn2OejNPZgrZybTs1tqPdVla6jKutnk6VNPLBOuNd8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:30:25.633276Z"},"content_sha256":"000ca6b18d126c20679f145aae0d93dad05e8ff1f048e5a4e480046f6bb394a5","schema_version":"1.0","event_id":"sha256:000ca6b18d126c20679f145aae0d93dad05e8ff1f048e5a4e480046f6bb394a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/bundle.json","state_url":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUZUROJALGESJ544LW7PLUU46E/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":"2026-08-06T13:30:25Z","links":{"resolver":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E","bundle":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/bundle.json","state":"https://pith.science/pith/XUZUROJALGESJ544LW7PLUU46E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUZUROJALGESJ544LW7PLUU46E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XUZUROJALGESJ544LW7PLUU46E","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":"098b47d8ea08f2f91d368084c0974db5853e1861a13d434e6e654540080da0c5","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T19:52:58Z","title_canon_sha256":"262ee1fc17df8c67872d3072e423ee94b8397248e8bd7b16c33d20c1286c875c"},"schema_version":"1.0","source":{"id":"2607.21780","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21780","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21780v1","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21780","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"XUZUROJALGES","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"XUZUROJALGESJ544","created_at":"2026-07-27T00:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"XUZUROJA","created_at":"2026-07-27T00:20:20Z"}],"graph_snapshots":[{"event_id":"sha256:000ca6b18d126c20679f145aae0d93dad05e8ff1f048e5a4e480046f6bb394a5","target":"graph","created_at":"2026-07-27T00:20:20Z","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/2607.21780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T19:52:58Z","title":"Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21780","kind":"arxiv","version":1},"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:b72091be09bad7c859820a5ca97e6ff61c68f94f3d1aaa5a80e6af1509e0447d","target":"record","created_at":"2026-07-27T00:20:20Z","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":"098b47d8ea08f2f91d368084c0974db5853e1861a13d434e6e654540080da0c5","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T19:52:58Z","title_canon_sha256":"262ee1fc17df8c67872d3072e423ee94b8397248e8bd7b16c33d20c1286c875c"},"schema_version":"1.0","source":{"id":"2607.21780","kind":"arxiv","version":1}},"canonical_sha256":"bd3348b920598924f79c5dbef5d29cf119e466c09207033baa90e4432f2c0626","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd3348b920598924f79c5dbef5d29cf119e466c09207033baa90e4432f2c0626","first_computed_at":"2026-07-27T00:20:20.596969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T00:20:20.596969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OJdEKfPIDwty/4jDsmi8vr/ag7KoYCchoK4kkoNVQw67QD+GG/h1nRi5k+UdnTgY0NBOgpldIALqyZ/3st3mBw==","signature_status":"signed_v1","signed_at":"2026-07-27T00:20:20.597825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21780","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b72091be09bad7c859820a5ca97e6ff61c68f94f3d1aaa5a80e6af1509e0447d","sha256:000ca6b18d126c20679f145aae0d93dad05e8ff1f048e5a4e480046f6bb394a5"],"state_sha256":"2579624e501ebdeb0b3690ba98f1a0f118883d4aab4eb750e0e50bba21c93472"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/2XSxUTI/tZBCZWYfxaO2nf38TB33GZn+rvDqNjKGjyGlcAJ5mgAnJcLIJySFNVlJ3x95xD3SOc4DeZKuANCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:30:25.637355Z","bundle_sha256":"886f191e9ef89ec163dfe7acc48f062467b2379a36f33d58b6e3a4622d55032a"}}