{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UN67UCCAAHPPFQULUA7NSRCKUI","short_pith_number":"pith:UN67UCCA","canonical_record":{"source":{"id":"2506.05061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:03:18Z","cross_cats_sorted":[],"title_canon_sha256":"a7e1625de32924404be092d9de5b2a93717d9f06a7f72f090ad1e75ace7f75c0","abstract_canon_sha256":"312972c069ce4a7129955181bb48f8b549c71a6f8b396bdb310f14c0472db037"},"schema_version":"1.0"},"canonical_sha256":"a37dfa084001def2c28ba03ed9444aa216d860a6b50bf134321d13ee574585a8","source":{"kind":"arxiv","id":"2506.05061","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05061","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05061v1","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05061","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"UN67UCCAAHPP","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"UN67UCCAAHPPFQUL","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"UN67UCCA","created_at":"2026-07-05T11:16:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UN67UCCAAHPPFQULUA7NSRCKUI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:03:18Z","cross_cats_sorted":[],"title_canon_sha256":"a7e1625de32924404be092d9de5b2a93717d9f06a7f72f090ad1e75ace7f75c0","abstract_canon_sha256":"312972c069ce4a7129955181bb48f8b549c71a6f8b396bdb310f14c0472db037"},"schema_version":"1.0"},"canonical_sha256":"a37dfa084001def2c28ba03ed9444aa216d860a6b50bf134321d13ee574585a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:41.696670Z","signature_b64":"oKkeh4oXgEuDXD9IY2b23hdZdvVJDAKJNib5flWpE8Hm/8F8Eg9M9/AiyZH6IQVloVsAZTJ+6uK+WVATVMrLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a37dfa084001def2c28ba03ed9444aa216d860a6b50bf134321d13ee574585a8","last_reissued_at":"2026-07-05T11:16:41.696139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:41.696139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05061","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":"2026-07-05T11:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dFuaIC7A+BqllvtVxg1uxP1h2sb8ZEei3uSIWc+/qBnxu8NJXIUCo2+7FgYaMNLmh1w4AoP8p7IHVQv2x3T5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:54:30.680470Z"},"content_sha256":"79add3cacc4b9304e2f7fbd95208ab576a0e21456428561b18d994ab97da2912","schema_version":"1.0","event_id":"sha256:79add3cacc4b9304e2f7fbd95208ab576a0e21456428561b18d994ab97da2912"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UN67UCCAAHPPFQULUA7NSRCKUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Le, Dung Nguyen, Thanh Lam","submitted_at":"2025-06-05T14:03:18Z","abstract_excerpt":"Vietnamese document analysis and recognition (DAR) is a crucial field with applications in digitization, information retrieval, and automation. Despite advancements in OCR and NLP, Vietnamese text recognition faces unique challenges due to its complex diacritics, tonal variations, and lack of large-scale annotated datasets. Traditional OCR methods often struggle with real-world document variations, while deep learning approaches have shown promise but remain limited by data scarcity and generalization issues. Recently, large language models (LLMs) and vision-language models have demonstrated r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05061","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/2506.05061/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":"2026-07-05T11:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPJWcqrVwtCzPujYoMuPRrARkoC8OmnyozQ1UIcckMXnOolbSJT0VPVFZAPzjngf0kuOiAB4/Wn8ySHBMBN0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:54:30.681130Z"},"content_sha256":"0c6ecf7419fdae3beb2a9789276045edf53183cd143ca4532da547e3b029f0d0","schema_version":"1.0","event_id":"sha256:0c6ecf7419fdae3beb2a9789276045edf53183cd143ca4532da547e3b029f0d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UN67UCCAAHPPFQULUA7NSRCKUI/bundle.json","state_url":"https://pith.science/pith/UN67UCCAAHPPFQULUA7NSRCKUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UN67UCCAAHPPFQULUA7NSRCKUI/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":"2026-08-07T23:54:30Z","links":{"resolver":"https://pith.science/pith/UN67UCCAAHPPFQULUA7NSRCKUI","bundle":"https://pith.science/pith/UN67UCCAAHPPFQULUA7NSRCKUI/bundle.json","state":"https://pith.science/pith/UN67UCCAAHPPFQULUA7NSRCKUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UN67UCCAAHPPFQULUA7NSRCKUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UN67UCCAAHPPFQULUA7NSRCKUI","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":"312972c069ce4a7129955181bb48f8b549c71a6f8b396bdb310f14c0472db037","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:03:18Z","title_canon_sha256":"a7e1625de32924404be092d9de5b2a93717d9f06a7f72f090ad1e75ace7f75c0"},"schema_version":"1.0","source":{"id":"2506.05061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05061","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05061v1","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05061","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"UN67UCCAAHPP","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"UN67UCCAAHPPFQUL","created_at":"2026-07-05T11:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"UN67UCCA","created_at":"2026-07-05T11:16:41Z"}],"graph_snapshots":[{"event_id":"sha256:0c6ecf7419fdae3beb2a9789276045edf53183cd143ca4532da547e3b029f0d0","target":"graph","created_at":"2026-07-05T11:16:41Z","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/2506.05061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vietnamese document analysis and recognition (DAR) is a crucial field with applications in digitization, information retrieval, and automation. Despite advancements in OCR and NLP, Vietnamese text recognition faces unique challenges due to its complex diacritics, tonal variations, and lack of large-scale annotated datasets. Traditional OCR methods often struggle with real-world document variations, while deep learning approaches have shown promise but remain limited by data scarcity and generalization issues. Recently, large language models (LLMs) and vision-language models have demonstrated r","authors_text":"Anh Le, Dung Nguyen, Thanh Lam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:03:18Z","title":"A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05061","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":"sha256:79add3cacc4b9304e2f7fbd95208ab576a0e21456428561b18d994ab97da2912","target":"record","created_at":"2026-07-05T11:16:41Z","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":"312972c069ce4a7129955181bb48f8b549c71a6f8b396bdb310f14c0472db037","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:03:18Z","title_canon_sha256":"a7e1625de32924404be092d9de5b2a93717d9f06a7f72f090ad1e75ace7f75c0"},"schema_version":"1.0","source":{"id":"2506.05061","kind":"arxiv","version":1}},"canonical_sha256":"a37dfa084001def2c28ba03ed9444aa216d860a6b50bf134321d13ee574585a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a37dfa084001def2c28ba03ed9444aa216d860a6b50bf134321d13ee574585a8","first_computed_at":"2026-07-05T11:16:41.696139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:41.696139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oKkeh4oXgEuDXD9IY2b23hdZdvVJDAKJNib5flWpE8Hm/8F8Eg9M9/AiyZH6IQVloVsAZTJ+6uK+WVATVMrLBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:41.696670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79add3cacc4b9304e2f7fbd95208ab576a0e21456428561b18d994ab97da2912","sha256:0c6ecf7419fdae3beb2a9789276045edf53183cd143ca4532da547e3b029f0d0"],"state_sha256":"5fdfd886f8e5be10e5b29ce5fc34ee37a9e141e7c371bd6d7b84a1bc7e305c38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KMs152EQDdiOVtIy1eeUL/i/EBA+ATw3hYL1mKvTbPHqxvQdy1JQ0LxvnJCTI5NAsluCziPlu81EJbOFv2AXCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:54:30.686834Z","bundle_sha256":"f28a7d3262f1f7bcc09b34476388d407e9fdc3de8986256d8ce4ccda26250c94"}}