{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:57XSARXIRNLEOIOSU2CZFJ2PSU","short_pith_number":"pith:57XSARXI","canonical_record":{"source":{"id":"2608.13384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-13T15:46:20Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"cca489e5a46aa491cab6c1a66f02b7cdaaa57b9b07ba2e551f238911e7b4cf64","abstract_canon_sha256":"1f9d12b5eb6e6f8aa5314fbd6aab170b5fb790940aadb21d2448488db6a35e7d"},"schema_version":"1.0"},"canonical_sha256":"efef2046e88b564721d2a68592a74f951bceb64e46c53a306a911ed51a5144d9","source":{"kind":"arxiv","id":"2608.13384","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13384","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13384v1","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13384","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"57XSARXIRNLE","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"57XSARXIRNLEOIOS","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"57XSARXI","created_at":"2026-08-14T01:04:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:57XSARXIRNLEOIOSU2CZFJ2PSU","target":"record","payload":{"canonical_record":{"source":{"id":"2608.13384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-13T15:46:20Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"cca489e5a46aa491cab6c1a66f02b7cdaaa57b9b07ba2e551f238911e7b4cf64","abstract_canon_sha256":"1f9d12b5eb6e6f8aa5314fbd6aab170b5fb790940aadb21d2448488db6a35e7d"},"schema_version":"1.0"},"canonical_sha256":"efef2046e88b564721d2a68592a74f951bceb64e46c53a306a911ed51a5144d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:04:20.122959Z","signature_b64":"xR0TusZGkLtlAWRWDqPdwwiTDpyOBY3OvYZsbb7b2owvh5hoF5jARpmy3f4GXnsZsQbsv18OubkJMrjBBXTpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efef2046e88b564721d2a68592a74f951bceb64e46c53a306a911ed51a5144d9","last_reissued_at":"2026-08-14T01:04:20.120964Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:04:20.120964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.13384","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":"2026-08-14T01:04:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J3egLd39pJ/6ivWuiZL+RZHSC2p1mKPNOVfDxi02wnpqHwEZYAUmslaKTXcDdlNf4A7b0W0lYcEXfcdBQip0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:28:17.927547Z"},"content_sha256":"f36c21accfac3d2167b6d46a58052b311adf4f32a726ef3be598742becaa4349","schema_version":"1.0","event_id":"sha256:f36c21accfac3d2167b6d46a58052b311adf4f32a726ef3be598742becaa4349"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:57XSARXIRNLEOIOSU2CZFJ2PSU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structure then Query: Enabling Precise Analytical Queries over Unstructured Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"Nan Tang, Teng Lin, Yuyu Luo","submitted_at":"2026-08-13T15:46:20Z","abstract_excerpt":"Unstructured documents constitute the majority of enterprise and web data. With the rapid development of large language models(LLMs), researchers have started to build data systems that analyze unstructured textual documents like operating on databases. However, because mainstream retrieval methods still relies on fuzzy matching based on vector similarity, accurately obtaining information and performing structured analysis and reasoning remains a major challenge. To address these limitations, AnnoIndex introduces two core fundamental components. The first is Annotation Index. The system uses a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13384","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/2608.13384/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":"2026-08-14T01:04:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nafBlmzTXxhClbO8SjhTfE9EZoNYsdpzq5SzrkYCnmEafiOglEvEbH9tAwIEKXUNQ8lqhdxmQhnEkDhB4h8uDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:28:17.928086Z"},"content_sha256":"bbce9c0a54fd0352bfddbac2f74f3b8db3558082ec73df0950aa2186eefcf472","schema_version":"1.0","event_id":"sha256:bbce9c0a54fd0352bfddbac2f74f3b8db3558082ec73df0950aa2186eefcf472"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57XSARXIRNLEOIOSU2CZFJ2PSU/bundle.json","state_url":"https://pith.science/pith/57XSARXIRNLEOIOSU2CZFJ2PSU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57XSARXIRNLEOIOSU2CZFJ2PSU/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":"2026-08-17T07:28:17Z","links":{"resolver":"https://pith.science/pith/57XSARXIRNLEOIOSU2CZFJ2PSU","bundle":"https://pith.science/pith/57XSARXIRNLEOIOSU2CZFJ2PSU/bundle.json","state":"https://pith.science/pith/57XSARXIRNLEOIOSU2CZFJ2PSU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57XSARXIRNLEOIOSU2CZFJ2PSU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:57XSARXIRNLEOIOSU2CZFJ2PSU","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":"1f9d12b5eb6e6f8aa5314fbd6aab170b5fb790940aadb21d2448488db6a35e7d","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-13T15:46:20Z","title_canon_sha256":"cca489e5a46aa491cab6c1a66f02b7cdaaa57b9b07ba2e551f238911e7b4cf64"},"schema_version":"1.0","source":{"id":"2608.13384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13384","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13384v1","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13384","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"57XSARXIRNLE","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"57XSARXIRNLEOIOS","created_at":"2026-08-14T01:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"57XSARXI","created_at":"2026-08-14T01:04:20Z"}],"graph_snapshots":[{"event_id":"sha256:bbce9c0a54fd0352bfddbac2f74f3b8db3558082ec73df0950aa2186eefcf472","target":"graph","created_at":"2026-08-14T01:04:20Z","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/2608.13384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unstructured documents constitute the majority of enterprise and web data. With the rapid development of large language models(LLMs), researchers have started to build data systems that analyze unstructured textual documents like operating on databases. However, because mainstream retrieval methods still relies on fuzzy matching based on vector similarity, accurately obtaining information and performing structured analysis and reasoning remains a major challenge. To address these limitations, AnnoIndex introduces two core fundamental components. The first is Annotation Index. The system uses a","authors_text":"Nan Tang, Teng Lin, Yuyu Luo","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-13T15:46:20Z","title":"Structure then Query: Enabling Precise Analytical Queries over Unstructured Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13384","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:f36c21accfac3d2167b6d46a58052b311adf4f32a726ef3be598742becaa4349","target":"record","created_at":"2026-08-14T01:04:20Z","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":"1f9d12b5eb6e6f8aa5314fbd6aab170b5fb790940aadb21d2448488db6a35e7d","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-13T15:46:20Z","title_canon_sha256":"cca489e5a46aa491cab6c1a66f02b7cdaaa57b9b07ba2e551f238911e7b4cf64"},"schema_version":"1.0","source":{"id":"2608.13384","kind":"arxiv","version":1}},"canonical_sha256":"efef2046e88b564721d2a68592a74f951bceb64e46c53a306a911ed51a5144d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efef2046e88b564721d2a68592a74f951bceb64e46c53a306a911ed51a5144d9","first_computed_at":"2026-08-14T01:04:20.120964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:04:20.120964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xR0TusZGkLtlAWRWDqPdwwiTDpyOBY3OvYZsbb7b2owvh5hoF5jARpmy3f4GXnsZsQbsv18OubkJMrjBBXTpCA==","signature_status":"signed_v1","signed_at":"2026-08-14T01:04:20.122959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f36c21accfac3d2167b6d46a58052b311adf4f32a726ef3be598742becaa4349","sha256:bbce9c0a54fd0352bfddbac2f74f3b8db3558082ec73df0950aa2186eefcf472"],"state_sha256":"180e7bc8e56283aaf67ac3d1c8963b7ae81f2fdaedb3114e8961ce0ba6e25457"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLBCmlfq4aXd1n91HCoWKr3anafjmEHy8OyIQFSy/Ptyy8BijCk9FOtJ2XTxOnItAx3p3otueGfowZGv2z2vAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:28:17.931930Z","bundle_sha256":"c6067ea1a6b0d91ce42de4cb74fd31907ae1f37450eb58457652639abad6fb57"}}