{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QQAPIQD72JZKWOCNPEFT5F2MKO","short_pith_number":"pith:QQAPIQD7","canonical_record":{"source":{"id":"2608.01389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T17:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"ea49a85e0b92b7e733d2297612c2f6e3a8116e7714e9562b2baf9df8ec9649a2","abstract_canon_sha256":"2f2c4f90b5336d0cb657e0303f77122342fadfcfd3c1469c693bec37d540ee6e"},"schema_version":"1.0"},"canonical_sha256":"8400f4407fd272ab384d790b3e974c53816c023f3c74f617a6325656fa544ad8","source":{"kind":"arxiv","id":"2608.01389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01389","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01389v1","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01389","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"QQAPIQD72JZK","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"QQAPIQD72JZKWOCN","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"QQAPIQD7","created_at":"2026-08-04T02:04:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QQAPIQD72JZKWOCNPEFT5F2MKO","target":"record","payload":{"canonical_record":{"source":{"id":"2608.01389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T17:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"ea49a85e0b92b7e733d2297612c2f6e3a8116e7714e9562b2baf9df8ec9649a2","abstract_canon_sha256":"2f2c4f90b5336d0cb657e0303f77122342fadfcfd3c1469c693bec37d540ee6e"},"schema_version":"1.0"},"canonical_sha256":"8400f4407fd272ab384d790b3e974c53816c023f3c74f617a6325656fa544ad8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:04:55.889881Z","signature_b64":"Fzbw/UxgD7V1p6tISb9cliGt0J8VMFKP8/u7pF3eGtSHe5EgTGrO+Y4SnE+/H8up/NDmW8a8UTeh6JcR12GQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8400f4407fd272ab384d790b3e974c53816c023f3c74f617a6325656fa544ad8","last_reissued_at":"2026-08-04T02:04:55.888352Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:04:55.888352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.01389","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":"2026-08-04T02:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qVLMWvCauBkozYV0RgmLIRUJI6CTpKNJ0aUoWmitcb0Ff/GgIa9tCsp029Mlk5h/gyYOBrDHgAclaSLHe5GvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:45:47.685966Z"},"content_sha256":"c6a49812a07160821d5efbc5cb98e55e8d10a937200e6db59fcfe7d818f5e8fc","schema_version":"1.0","event_id":"sha256:c6a49812a07160821d5efbc5cb98e55e8d10a937200e6db59fcfe7d818f5e8fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QQAPIQD72JZKWOCNPEFT5F2MKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gyuho Shim, Yongbin Choi, Youngjoon Jang","submitted_at":"2026-08-02T17:11:09Z","abstract_excerpt":"Visual Document Retrieval (VDR) directly matches text queries against document images, preserving visual and structural information that may be lost during text extraction. However, existing VDR models and training resources remain predominantly English-centric, while many high-performing systems rely on massive backbones or storage-intensive multi-vector representations. To address these limitations, we introduce KoVRE: Korean Visual Document Retrieval Embedding, a single-vector retriever for Korean visual documents, alongside a comprehensive training recipe. We train the model on 708,729 Kor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01389","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/2608.01389/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":"2026-08-04T02:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j7kIc6CSvgJ/76yVjejjcTk1dN9oAARNnNB6XnzdUDtrGBaLnFAalnt62qsobuEQvwLHb9q8fs4KbNdeoFpCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:45:47.686467Z"},"content_sha256":"37dfc5c25fc3499d9a224ebc16fd23f46695c65d0275129bb514cb6e9d5dba0b","schema_version":"1.0","event_id":"sha256:37dfc5c25fc3499d9a224ebc16fd23f46695c65d0275129bb514cb6e9d5dba0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQAPIQD72JZKWOCNPEFT5F2MKO/bundle.json","state_url":"https://pith.science/pith/QQAPIQD72JZKWOCNPEFT5F2MKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQAPIQD72JZKWOCNPEFT5F2MKO/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":"2026-08-08T08:45:47Z","links":{"resolver":"https://pith.science/pith/QQAPIQD72JZKWOCNPEFT5F2MKO","bundle":"https://pith.science/pith/QQAPIQD72JZKWOCNPEFT5F2MKO/bundle.json","state":"https://pith.science/pith/QQAPIQD72JZKWOCNPEFT5F2MKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQAPIQD72JZKWOCNPEFT5F2MKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QQAPIQD72JZKWOCNPEFT5F2MKO","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":"2f2c4f90b5336d0cb657e0303f77122342fadfcfd3c1469c693bec37d540ee6e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T17:11:09Z","title_canon_sha256":"ea49a85e0b92b7e733d2297612c2f6e3a8116e7714e9562b2baf9df8ec9649a2"},"schema_version":"1.0","source":{"id":"2608.01389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01389","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01389v1","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01389","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"QQAPIQD72JZK","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"QQAPIQD72JZKWOCN","created_at":"2026-08-04T02:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"QQAPIQD7","created_at":"2026-08-04T02:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:37dfc5c25fc3499d9a224ebc16fd23f46695c65d0275129bb514cb6e9d5dba0b","target":"graph","created_at":"2026-08-04T02:04:55Z","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/2608.01389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Document Retrieval (VDR) directly matches text queries against document images, preserving visual and structural information that may be lost during text extraction. However, existing VDR models and training resources remain predominantly English-centric, while many high-performing systems rely on massive backbones or storage-intensive multi-vector representations. To address these limitations, we introduce KoVRE: Korean Visual Document Retrieval Embedding, a single-vector retriever for Korean visual documents, alongside a comprehensive training recipe. We train the model on 708,729 Kor","authors_text":"Gyuho Shim, Yongbin Choi, Youngjoon Jang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T17:11:09Z","title":"KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01389","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:c6a49812a07160821d5efbc5cb98e55e8d10a937200e6db59fcfe7d818f5e8fc","target":"record","created_at":"2026-08-04T02:04:55Z","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":"2f2c4f90b5336d0cb657e0303f77122342fadfcfd3c1469c693bec37d540ee6e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T17:11:09Z","title_canon_sha256":"ea49a85e0b92b7e733d2297612c2f6e3a8116e7714e9562b2baf9df8ec9649a2"},"schema_version":"1.0","source":{"id":"2608.01389","kind":"arxiv","version":1}},"canonical_sha256":"8400f4407fd272ab384d790b3e974c53816c023f3c74f617a6325656fa544ad8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8400f4407fd272ab384d790b3e974c53816c023f3c74f617a6325656fa544ad8","first_computed_at":"2026-08-04T02:04:55.888352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:04:55.888352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fzbw/UxgD7V1p6tISb9cliGt0J8VMFKP8/u7pF3eGtSHe5EgTGrO+Y4SnE+/H8up/NDmW8a8UTeh6JcR12GQCQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:04:55.889881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6a49812a07160821d5efbc5cb98e55e8d10a937200e6db59fcfe7d818f5e8fc","sha256:37dfc5c25fc3499d9a224ebc16fd23f46695c65d0275129bb514cb6e9d5dba0b"],"state_sha256":"9ec881d1c8ebc131f63d2c360121c7894276f3ea85ab6c34c3f7457fdb6d1e14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YC8yGCY18WSOuEozAED6EYMPtSxj/o8H3vLiFgQUHbYbNQ8xo44yMNWgRD2mmk6N8mOibTCzirbcmTP1lbHGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:45:47.690499Z","bundle_sha256":"0bcf219d394d6dc7964e9299c8014bba4f4b4ebc48cb91b6ac1b1dd5904ea0d8"}}