{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AF67DNJGCEHSBOD5GJR6ET24XH","short_pith_number":"pith:AF67DNJG","canonical_record":{"source":{"id":"2607.24760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-30T06:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"b91b3db451a69c60ae46397704ca92c5b48915944a65a2aef25fec99e1277d08","abstract_canon_sha256":"6d0052cd3deda31823d7314372da5030f67f482f22d69bc739ea522d0c0cfe43"},"schema_version":"1.0"},"canonical_sha256":"017df1b526110f20b87d3263e24f5cb9d3ad5fb7d3072b3a18507e106c548ea3","source":{"kind":"arxiv","id":"2607.24760","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24760","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24760v1","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24760","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"pith_short_12","alias_value":"AF67DNJGCEHS","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"pith_short_16","alias_value":"AF67DNJGCEHSBOD5","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"pith_short_8","alias_value":"AF67DNJG","created_at":"2026-07-29T00:24:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AF67DNJGCEHSBOD5GJR6ET24XH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-30T06:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"b91b3db451a69c60ae46397704ca92c5b48915944a65a2aef25fec99e1277d08","abstract_canon_sha256":"6d0052cd3deda31823d7314372da5030f67f482f22d69bc739ea522d0c0cfe43"},"schema_version":"1.0"},"canonical_sha256":"017df1b526110f20b87d3263e24f5cb9d3ad5fb7d3072b3a18507e106c548ea3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:42.386114Z","signature_b64":"53QhKKsQMv28jPIobA90wkcWeAltGYG+8MFm4B3TNmRWKaJikSyaeyDJcGB6/U020LiNvQVftlGrC4OcNCCdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"017df1b526110f20b87d3263e24f5cb9d3ad5fb7d3072b3a18507e106c548ea3","last_reissued_at":"2026-07-29T00:24:42.385139Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:42.385139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24760","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":"2026-07-29T00:24:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BVkEJC7bt5jCSNzcG6UzhPUsD0SAyzDfpI6/cF1KxDE4qhSiUD0RALr0XdvAdxTL3qQ6fkQkPDpEdVXkhseDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:41:06.745750Z"},"content_sha256":"014c7b77eedb67ccc996a8eb9f36c2e1788838bf515bdb5b4df5272af8c5626b","schema_version":"1.0","event_id":"sha256:014c7b77eedb67ccc996a8eb9f36c2e1788838bf515bdb5b4df5272af8c5626b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AF67DNJGCEHSBOD5GJR6ET24XH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CHaystack: Benchmarking Chinese Document Retrieval and VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hanxi Li","submitted_at":"2026-05-30T06:59:33Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has made substantial progress in extending the memory of large language models (LLMs), and recent advances have further pushed RAG from pure text settings toward multimodal scenarios. In the document understanding domain, document visual question answering (DocumentVQA) has evolved from question answering over a single document to retrieval-and-generation pipelines over large-scale document collections. However, a benchmark specifically designed for Chinese large-scale document retrieval and question answering is still lacking. To bridge this gap, we introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24760","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/2607.24760/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":"2026-07-29T00:24:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5TVkfX9rEi0dQ3DCRkJekhFu8boPSHplVPaXpiyxtZxSWAZrubG1tnFKpMDG/Y5R0AIfTY9L9vxVW92cHiuSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:41:06.746337Z"},"content_sha256":"3d55e122b264a36e5cda93ef6f23237becbf5fe011ffb709ba32e6795010402d","schema_version":"1.0","event_id":"sha256:3d55e122b264a36e5cda93ef6f23237becbf5fe011ffb709ba32e6795010402d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AF67DNJGCEHSBOD5GJR6ET24XH/bundle.json","state_url":"https://pith.science/pith/AF67DNJGCEHSBOD5GJR6ET24XH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AF67DNJGCEHSBOD5GJR6ET24XH/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":"2026-08-06T02:41:06Z","links":{"resolver":"https://pith.science/pith/AF67DNJGCEHSBOD5GJR6ET24XH","bundle":"https://pith.science/pith/AF67DNJGCEHSBOD5GJR6ET24XH/bundle.json","state":"https://pith.science/pith/AF67DNJGCEHSBOD5GJR6ET24XH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AF67DNJGCEHSBOD5GJR6ET24XH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AF67DNJGCEHSBOD5GJR6ET24XH","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":"6d0052cd3deda31823d7314372da5030f67f482f22d69bc739ea522d0c0cfe43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-30T06:59:33Z","title_canon_sha256":"b91b3db451a69c60ae46397704ca92c5b48915944a65a2aef25fec99e1277d08"},"schema_version":"1.0","source":{"id":"2607.24760","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24760","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24760v1","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24760","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"pith_short_12","alias_value":"AF67DNJGCEHS","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"pith_short_16","alias_value":"AF67DNJGCEHSBOD5","created_at":"2026-07-29T00:24:42Z"},{"alias_kind":"pith_short_8","alias_value":"AF67DNJG","created_at":"2026-07-29T00:24:42Z"}],"graph_snapshots":[{"event_id":"sha256:3d55e122b264a36e5cda93ef6f23237becbf5fe011ffb709ba32e6795010402d","target":"graph","created_at":"2026-07-29T00:24:42Z","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/2607.24760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) has made substantial progress in extending the memory of large language models (LLMs), and recent advances have further pushed RAG from pure text settings toward multimodal scenarios. In the document understanding domain, document visual question answering (DocumentVQA) has evolved from question answering over a single document to retrieval-and-generation pipelines over large-scale document collections. However, a benchmark specifically designed for Chinese large-scale document retrieval and question answering is still lacking. To bridge this gap, we introd","authors_text":"Hanxi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-30T06:59:33Z","title":"CHaystack: Benchmarking Chinese Document Retrieval and VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24760","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":"sha256:014c7b77eedb67ccc996a8eb9f36c2e1788838bf515bdb5b4df5272af8c5626b","target":"record","created_at":"2026-07-29T00:24:42Z","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":"6d0052cd3deda31823d7314372da5030f67f482f22d69bc739ea522d0c0cfe43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-30T06:59:33Z","title_canon_sha256":"b91b3db451a69c60ae46397704ca92c5b48915944a65a2aef25fec99e1277d08"},"schema_version":"1.0","source":{"id":"2607.24760","kind":"arxiv","version":1}},"canonical_sha256":"017df1b526110f20b87d3263e24f5cb9d3ad5fb7d3072b3a18507e106c548ea3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"017df1b526110f20b87d3263e24f5cb9d3ad5fb7d3072b3a18507e106c548ea3","first_computed_at":"2026-07-29T00:24:42.385139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:24:42.385139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"53QhKKsQMv28jPIobA90wkcWeAltGYG+8MFm4B3TNmRWKaJikSyaeyDJcGB6/U020LiNvQVftlGrC4OcNCCdDw==","signature_status":"signed_v1","signed_at":"2026-07-29T00:24:42.386114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24760","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:014c7b77eedb67ccc996a8eb9f36c2e1788838bf515bdb5b4df5272af8c5626b","sha256:3d55e122b264a36e5cda93ef6f23237becbf5fe011ffb709ba32e6795010402d"],"state_sha256":"b772af05d51a0f5964e33cc4fe955df1dc8a5cac54cde38c537d01f8b29ef71a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IRGZWThHdAhztEoD0JvERNAFNpupfIrQHmOtkCDoRQTr1WphwEsKbQToBeWr1gB0DMTfZzy45W0EVvFBY0doCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:41:06.750453Z","bundle_sha256":"dfb53cef830cc86d3c63be701f91fe250ff93b107ebec92af5a5c17f3796c776"}}