{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KHV2KD2CIQXANFE3FZIFTO53KO","short_pith_number":"pith:KHV2KD2C","canonical_record":{"source":{"id":"2508.12536","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-18T00:14:24Z","cross_cats_sorted":["cs.DS","cs.IR"],"title_canon_sha256":"3ee5ea2289bd4d523ad92bd6145f2cd392bb09faa7ebc75eeb0c5e653f710657","abstract_canon_sha256":"5afdb1b1bfd0baa86a3ac5fefe937c372b79fa7b4fad2b46a2b5f93259d50365"},"schema_version":"1.0"},"canonical_sha256":"51eba50f42442e06949b2e5059bbbb53923d6089260562bd5b7dd91c291d06fb","source":{"kind":"arxiv","id":"2508.12536","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12536","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12536v3","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12536","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"KHV2KD2CIQXA","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"KHV2KD2CIQXANFE3","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"KHV2KD2C","created_at":"2026-06-09T02:07:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KHV2KD2CIQXANFE3FZIFTO53KO","target":"record","payload":{"canonical_record":{"source":{"id":"2508.12536","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-18T00:14:24Z","cross_cats_sorted":["cs.DS","cs.IR"],"title_canon_sha256":"3ee5ea2289bd4d523ad92bd6145f2cd392bb09faa7ebc75eeb0c5e653f710657","abstract_canon_sha256":"5afdb1b1bfd0baa86a3ac5fefe937c372b79fa7b4fad2b46a2b5f93259d50365"},"schema_version":"1.0"},"canonical_sha256":"51eba50f42442e06949b2e5059bbbb53923d6089260562bd5b7dd91c291d06fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:06.620186Z","signature_b64":"i+sD1e8rvLl3ZEH6yJd47cNIKBjRxwaa7W87mj6yOZrHfjDrXmscs8PKnazPlN8dZIa9ZGGt4ddokIRJ0PL/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51eba50f42442e06949b2e5059bbbb53923d6089260562bd5b7dd91c291d06fb","last_reissued_at":"2026-06-09T02:07:06.619149Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:06.619149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.12536","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xAeT9GrzHw1805KduPD6VQnIFMotMXGzXqgVUXnYAF0K+ipSVm5oRR7LwPvWQRRxg39zPrs+EJVnCS2gP8xiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T00:28:19.068775Z"},"content_sha256":"dd48c8c04e5b16268496452088fce15b3ee3914cde4a33f9aeb9dea2ac3eea73","schema_version":"1.0","event_id":"sha256:dd48c8c04e5b16268496452088fce15b3ee3914cde4a33f9aeb9dea2ac3eea73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KHV2KD2CIQXANFE3FZIFTO53KO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"jXBW: A Compressed Index for Structure-Aware JSONL Retrieval in Structured RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.IR"],"primary_cat":"cs.DB","authors_text":"Yasuo Tabei","submitted_at":"2025-08-18T00:14:24Z","abstract_excerpt":"Providing \\textit{structured} information to large language models (LLMs) improves multi-step reasoning and factual grounding, and recent retrieval-augmented generation (RAG) systems therefore reconstruct structure from retrieved text on every query. When the corpus is \\emph{already} structured -- as in JSON Lines (JSONL), a popular format for LLM prompts, chemical compounds, and geospatial records -- this per-query rebuilding can be replaced by direct \\emph{structural retrieval}. The core primitive is \\textit{substructure search}: finding all JSON objects in a collection that contain a given "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12536","kind":"arxiv","version":3},"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/2508.12536/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":"2026-06-09T02:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BBvNhLTXI+n0qsUCBd4Y5dDROwv+h3UG4oUvRrIeK3//BuzVtnacTN+uBZgKiEpIZd578765iToGQE1i7O9nAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T00:28:19.069147Z"},"content_sha256":"e3ec90ae721a58d525eda52f2190755ea484e3dee49db6629776d30697a6637c","schema_version":"1.0","event_id":"sha256:e3ec90ae721a58d525eda52f2190755ea484e3dee49db6629776d30697a6637c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHV2KD2CIQXANFE3FZIFTO53KO/bundle.json","state_url":"https://pith.science/pith/KHV2KD2CIQXANFE3FZIFTO53KO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHV2KD2CIQXANFE3FZIFTO53KO/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":"2026-06-27T00:28:19Z","links":{"resolver":"https://pith.science/pith/KHV2KD2CIQXANFE3FZIFTO53KO","bundle":"https://pith.science/pith/KHV2KD2CIQXANFE3FZIFTO53KO/bundle.json","state":"https://pith.science/pith/KHV2KD2CIQXANFE3FZIFTO53KO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHV2KD2CIQXANFE3FZIFTO53KO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KHV2KD2CIQXANFE3FZIFTO53KO","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":"5afdb1b1bfd0baa86a3ac5fefe937c372b79fa7b4fad2b46a2b5f93259d50365","cross_cats_sorted":["cs.DS","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-18T00:14:24Z","title_canon_sha256":"3ee5ea2289bd4d523ad92bd6145f2cd392bb09faa7ebc75eeb0c5e653f710657"},"schema_version":"1.0","source":{"id":"2508.12536","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12536","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12536v3","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12536","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"KHV2KD2CIQXA","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"KHV2KD2CIQXANFE3","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"KHV2KD2C","created_at":"2026-06-09T02:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:e3ec90ae721a58d525eda52f2190755ea484e3dee49db6629776d30697a6637c","target":"graph","created_at":"2026-06-09T02:07:06Z","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/2508.12536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Providing \\textit{structured} information to large language models (LLMs) improves multi-step reasoning and factual grounding, and recent retrieval-augmented generation (RAG) systems therefore reconstruct structure from retrieved text on every query. When the corpus is \\emph{already} structured -- as in JSON Lines (JSONL), a popular format for LLM prompts, chemical compounds, and geospatial records -- this per-query rebuilding can be replaced by direct \\emph{structural retrieval}. The core primitive is \\textit{substructure search}: finding all JSON objects in a collection that contain a given ","authors_text":"Yasuo Tabei","cross_cats":["cs.DS","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-18T00:14:24Z","title":"jXBW: A Compressed Index for Structure-Aware JSONL Retrieval in Structured RAG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12536","kind":"arxiv","version":3},"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:dd48c8c04e5b16268496452088fce15b3ee3914cde4a33f9aeb9dea2ac3eea73","target":"record","created_at":"2026-06-09T02:07:06Z","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":"5afdb1b1bfd0baa86a3ac5fefe937c372b79fa7b4fad2b46a2b5f93259d50365","cross_cats_sorted":["cs.DS","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-18T00:14:24Z","title_canon_sha256":"3ee5ea2289bd4d523ad92bd6145f2cd392bb09faa7ebc75eeb0c5e653f710657"},"schema_version":"1.0","source":{"id":"2508.12536","kind":"arxiv","version":3}},"canonical_sha256":"51eba50f42442e06949b2e5059bbbb53923d6089260562bd5b7dd91c291d06fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51eba50f42442e06949b2e5059bbbb53923d6089260562bd5b7dd91c291d06fb","first_computed_at":"2026-06-09T02:07:06.619149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:06.619149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i+sD1e8rvLl3ZEH6yJd47cNIKBjRxwaa7W87mj6yOZrHfjDrXmscs8PKnazPlN8dZIa9ZGGt4ddokIRJ0PL/Aw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:06.620186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12536","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd48c8c04e5b16268496452088fce15b3ee3914cde4a33f9aeb9dea2ac3eea73","sha256:e3ec90ae721a58d525eda52f2190755ea484e3dee49db6629776d30697a6637c"],"state_sha256":"030cb8353cd22577b642f92484a579a4c08094ce06af38c4833ee5cef763e5b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j5OX29Ok9QI5XUM49tlhVNQPzzuCdj41u0wcHDcJnMsXy/rklYhVVxwHTL3sCoGAaiKrNpFq4o1eZO3+QriGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T00:28:19.071132Z","bundle_sha256":"0724d3dad7242287d1399ceb5ebea39bf0dc22db3c5f5018c5c595351ad311dc"}}