{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CZVOMDLREBMYSS3HAUA4IZ42YB","short_pith_number":"pith:CZVOMDLR","canonical_record":{"source":{"id":"1701.08706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-27T12:54:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7c46a911d8b89c348f1794b7355063ea1a674310513214fb0455ffc960444d77","abstract_canon_sha256":"318b8c9800d391063d97ff615923ef9d7e9e49d1a59a379c8f459b63eee2c15d"},"schema_version":"1.0"},"canonical_sha256":"166ae60d712059894b670501c4679ac04531ecb34c8b526bf10646769035d74b","source":{"kind":"arxiv","id":"1701.08706","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.08706","created_at":"2026-05-18T00:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1701.08706v1","created_at":"2026-05-18T00:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.08706","created_at":"2026-05-18T00:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"CZVOMDLREBMY","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CZVOMDLREBMYSS3H","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CZVOMDLR","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CZVOMDLREBMYSS3HAUA4IZ42YB","target":"record","payload":{"canonical_record":{"source":{"id":"1701.08706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-27T12:54:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7c46a911d8b89c348f1794b7355063ea1a674310513214fb0455ffc960444d77","abstract_canon_sha256":"318b8c9800d391063d97ff615923ef9d7e9e49d1a59a379c8f459b63eee2c15d"},"schema_version":"1.0"},"canonical_sha256":"166ae60d712059894b670501c4679ac04531ecb34c8b526bf10646769035d74b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:52.907918Z","signature_b64":"Wi6I9WhwE+Nm5y7AHLxrUZ2zkqM6HrIUZqM6cUYgi0qoGID2YBB5tueIftscLIQ9Jn2QaUSE+wyOksec4RV9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"166ae60d712059894b670501c4679ac04531ecb34c8b526bf10646769035d74b","last_reissued_at":"2026-05-18T00:51:52.907394Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:52.907394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.08706","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":"2026-05-18T00:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Y9s6oBcJo7LTGcto2qgCPYLsJqODvkGdelSRrB52ttozL9pOnoZTB89p0faZyZ+QGt1v2uM9KJyUFa6CA2vDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T20:11:18.363486Z"},"content_sha256":"c060c9baedee3fc48827b8c843b5cc7bfbfe52cd7bd5ce24a4f4dcf580c5dc02","schema_version":"1.0","event_id":"sha256:c060c9baedee3fc48827b8c843b5cc7bfbfe52cd7bd5ce24a4f4dcf580c5dc02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CZVOMDLREBMYSS3HAUA4IZ42YB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Document Decomposition of Bangla Printed Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Md. Fahad Hasan, Md. Saiful Islam, Sabir Ismail, Tasmin Afroz","submitted_at":"2017-01-27T12:54:52Z","abstract_excerpt":"Today all kind of information is getting digitized and along with all this digitization, the huge archive of various kinds of documents is being digitized too. We know that, Optical Character Recognition is the method through which, newspapers and other paper documents convert into digital resources. But, it is a fact that this method works on texts only. As a result, if we try to process any document which contains non-textual zones, then we will get garbage texts as output. That is why; in order to digitize documents properly they should be prepossessed carefully. And while preprocessing, se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.08706","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":""},"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":"2026-05-18T00:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IWWLjCWwVZi6mQCLsbR65k9OdNbxg5r8w6d69VMT9qyNm6XITG93lgJMBHVBJHMMmfCJHJ1acM8IURxqnODJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T20:11:18.363836Z"},"content_sha256":"4bbe4f254939ef6fc01a5f20304f61e754549362fe7c4fe625248931504ee075","schema_version":"1.0","event_id":"sha256:4bbe4f254939ef6fc01a5f20304f61e754549362fe7c4fe625248931504ee075"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZVOMDLREBMYSS3HAUA4IZ42YB/bundle.json","state_url":"https://pith.science/pith/CZVOMDLREBMYSS3HAUA4IZ42YB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZVOMDLREBMYSS3HAUA4IZ42YB/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":"2026-06-25T20:11:18Z","links":{"resolver":"https://pith.science/pith/CZVOMDLREBMYSS3HAUA4IZ42YB","bundle":"https://pith.science/pith/CZVOMDLREBMYSS3HAUA4IZ42YB/bundle.json","state":"https://pith.science/pith/CZVOMDLREBMYSS3HAUA4IZ42YB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZVOMDLREBMYSS3HAUA4IZ42YB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CZVOMDLREBMYSS3HAUA4IZ42YB","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":"318b8c9800d391063d97ff615923ef9d7e9e49d1a59a379c8f459b63eee2c15d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-27T12:54:52Z","title_canon_sha256":"7c46a911d8b89c348f1794b7355063ea1a674310513214fb0455ffc960444d77"},"schema_version":"1.0","source":{"id":"1701.08706","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.08706","created_at":"2026-05-18T00:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1701.08706v1","created_at":"2026-05-18T00:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.08706","created_at":"2026-05-18T00:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"CZVOMDLREBMY","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CZVOMDLREBMYSS3H","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CZVOMDLR","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:4bbe4f254939ef6fc01a5f20304f61e754549362fe7c4fe625248931504ee075","target":"graph","created_at":"2026-05-18T00:51:52Z","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"},"paper":{"abstract_excerpt":"Today all kind of information is getting digitized and along with all this digitization, the huge archive of various kinds of documents is being digitized too. We know that, Optical Character Recognition is the method through which, newspapers and other paper documents convert into digital resources. But, it is a fact that this method works on texts only. As a result, if we try to process any document which contains non-textual zones, then we will get garbage texts as output. That is why; in order to digitize documents properly they should be prepossessed carefully. And while preprocessing, se","authors_text":"Md. Fahad Hasan, Md. Saiful Islam, Sabir Ismail, Tasmin Afroz","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-27T12:54:52Z","title":"Document Decomposition of Bangla Printed Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.08706","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:c060c9baedee3fc48827b8c843b5cc7bfbfe52cd7bd5ce24a4f4dcf580c5dc02","target":"record","created_at":"2026-05-18T00:51:52Z","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":"318b8c9800d391063d97ff615923ef9d7e9e49d1a59a379c8f459b63eee2c15d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-27T12:54:52Z","title_canon_sha256":"7c46a911d8b89c348f1794b7355063ea1a674310513214fb0455ffc960444d77"},"schema_version":"1.0","source":{"id":"1701.08706","kind":"arxiv","version":1}},"canonical_sha256":"166ae60d712059894b670501c4679ac04531ecb34c8b526bf10646769035d74b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"166ae60d712059894b670501c4679ac04531ecb34c8b526bf10646769035d74b","first_computed_at":"2026-05-18T00:51:52.907394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:52.907394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wi6I9WhwE+Nm5y7AHLxrUZ2zkqM6HrIUZqM6cUYgi0qoGID2YBB5tueIftscLIQ9Jn2QaUSE+wyOksec4RV9CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:52.907918Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.08706","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c060c9baedee3fc48827b8c843b5cc7bfbfe52cd7bd5ce24a4f4dcf580c5dc02","sha256:4bbe4f254939ef6fc01a5f20304f61e754549362fe7c4fe625248931504ee075"],"state_sha256":"b78257a158ace44cdc8b312efb6905eaeade0a6f0f018c28881ce5bf622dd4b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BbGKgbPB82CaeddrSzpwp5FYFpJhqMHT+JO37X0uMfDUOIOr0Nsg+CFvcroVuiJNT4bjOCgEvIrtyifXZSERDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T20:11:18.365782Z","bundle_sha256":"aef681331b6670a2a89280c559b23286dd3d623ea1f7b1ec348da4c16ef425c7"}}