{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LKU7MH5WJYGKTYBEB2TS2YFILR","short_pith_number":"pith:LKU7MH5W","canonical_record":{"source":{"id":"2607.20517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"e2174a6b6ccbdd654cebdc2d9954ac52ad43325415580b72992166f1a92d02f6","abstract_canon_sha256":"3e2f9c57a7e017b9381b1f30b4e6e6a9f9d621a68a3c02477bf3cfc4828a9607"},"schema_version":"1.0"},"canonical_sha256":"5aa9f61fb64e0ca9e0240ea72d60a85c7f1d4d7f205d9409736e60a59cf1836f","source":{"kind":"arxiv","id":"2607.20517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20517","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20517v1","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20517","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"LKU7MH5WJYGK","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"LKU7MH5WJYGKTYBE","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"LKU7MH5W","created_at":"2026-07-24T00:23:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LKU7MH5WJYGKTYBEB2TS2YFILR","target":"record","payload":{"canonical_record":{"source":{"id":"2607.20517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"e2174a6b6ccbdd654cebdc2d9954ac52ad43325415580b72992166f1a92d02f6","abstract_canon_sha256":"3e2f9c57a7e017b9381b1f30b4e6e6a9f9d621a68a3c02477bf3cfc4828a9607"},"schema_version":"1.0"},"canonical_sha256":"5aa9f61fb64e0ca9e0240ea72d60a85c7f1d4d7f205d9409736e60a59cf1836f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:19.951917Z","signature_b64":"M2YpoAFJWe0gdqS9zScORRCQQa1wlIPxhrLiHH7quhraprMQMvq+6RJ8EDWzgtIaUJa4GzYCYSaR0uHxihOKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aa9f61fb64e0ca9e0240ea72d60a85c7f1d4d7f205d9409736e60a59cf1836f","last_reissued_at":"2026-07-24T00:23:19.951043Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:19.951043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.20517","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":"2026-07-24T00:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K1EDsNNAQ46cQ0QdeWSK5ZLxFJvaDJeo+Ov6bmzjF/Sy9qeY/6APKwERRjCFRf0EJOkKJfORtmxlMDQBrlW5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:13:41.738808Z"},"content_sha256":"97c208da0144cfc280b40b5869be615f41564255ffc1f0fbe325f6af203da2b1","schema_version":"1.0","event_id":"sha256:97c208da0144cfc280b40b5869be615f41564255ffc1f0fbe325f6af203da2b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LKU7MH5WJYGKTYBEB2TS2YFILR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Takato Yasuno","submitted_at":"2026-07-07T23:00:52Z","abstract_excerpt":"Retrieval-augmented generation (RAG) over heterogeneous PDF collections remains challenging due to multimodal content, domain-specific terminology, and the need for multi-hop reasoning across dispersed evidence. We present Multimodal CoLRAG-TF, a four-axis fusion architecture that integrates dense text embeddings, BM25 keyword matching, knowledge-graph triple filtering, and image-based similarity for robust retrieval over complex documents. Our system constructs a multimodal index of 2,403 blocks extracted from 43 Japanese disaster lesson PDFs, supported by a hybrid OCR pipeline and LLM-based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20517","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/2607.20517/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":"2026-07-24T00:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2jt84RomROEMm7IqzmxsFCcZ/TNgWKOMh4wl6oxQfKX/ACYAklmZ3IpJxDrTqd8bcj73jtOaPSHqRqwsdkqvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:13:41.739296Z"},"content_sha256":"8235980276769d3ec14ca53bbf79fadae42ddabbb43a4e6faa5412d6d6c3055d","schema_version":"1.0","event_id":"sha256:8235980276769d3ec14ca53bbf79fadae42ddabbb43a4e6faa5412d6d6c3055d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKU7MH5WJYGKTYBEB2TS2YFILR/bundle.json","state_url":"https://pith.science/pith/LKU7MH5WJYGKTYBEB2TS2YFILR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKU7MH5WJYGKTYBEB2TS2YFILR/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":"2026-08-08T05:13:41Z","links":{"resolver":"https://pith.science/pith/LKU7MH5WJYGKTYBEB2TS2YFILR","bundle":"https://pith.science/pith/LKU7MH5WJYGKTYBEB2TS2YFILR/bundle.json","state":"https://pith.science/pith/LKU7MH5WJYGKTYBEB2TS2YFILR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKU7MH5WJYGKTYBEB2TS2YFILR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LKU7MH5WJYGKTYBEB2TS2YFILR","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":"3e2f9c57a7e017b9381b1f30b4e6e6a9f9d621a68a3c02477bf3cfc4828a9607","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:00:52Z","title_canon_sha256":"e2174a6b6ccbdd654cebdc2d9954ac52ad43325415580b72992166f1a92d02f6"},"schema_version":"1.0","source":{"id":"2607.20517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20517","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20517v1","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20517","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"LKU7MH5WJYGK","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"LKU7MH5WJYGKTYBE","created_at":"2026-07-24T00:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"LKU7MH5W","created_at":"2026-07-24T00:23:19Z"}],"graph_snapshots":[{"event_id":"sha256:8235980276769d3ec14ca53bbf79fadae42ddabbb43a4e6faa5412d6d6c3055d","target":"graph","created_at":"2026-07-24T00:23:19Z","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/2607.20517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) over heterogeneous PDF collections remains challenging due to multimodal content, domain-specific terminology, and the need for multi-hop reasoning across dispersed evidence. We present Multimodal CoLRAG-TF, a four-axis fusion architecture that integrates dense text embeddings, BM25 keyword matching, knowledge-graph triple filtering, and image-based similarity for robust retrieval over complex documents. Our system constructs a multimodal index of 2,403 blocks extracted from 43 Japanese disaster lesson PDFs, supported by a hybrid OCR pipeline and LLM-based ","authors_text":"Takato Yasuno","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:00:52Z","title":"Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20517","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":"sha256:97c208da0144cfc280b40b5869be615f41564255ffc1f0fbe325f6af203da2b1","target":"record","created_at":"2026-07-24T00:23:19Z","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":"3e2f9c57a7e017b9381b1f30b4e6e6a9f9d621a68a3c02477bf3cfc4828a9607","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T23:00:52Z","title_canon_sha256":"e2174a6b6ccbdd654cebdc2d9954ac52ad43325415580b72992166f1a92d02f6"},"schema_version":"1.0","source":{"id":"2607.20517","kind":"arxiv","version":1}},"canonical_sha256":"5aa9f61fb64e0ca9e0240ea72d60a85c7f1d4d7f205d9409736e60a59cf1836f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5aa9f61fb64e0ca9e0240ea72d60a85c7f1d4d7f205d9409736e60a59cf1836f","first_computed_at":"2026-07-24T00:23:19.951043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:19.951043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M2YpoAFJWe0gdqS9zScORRCQQa1wlIPxhrLiHH7quhraprMQMvq+6RJ8EDWzgtIaUJa4GzYCYSaR0uHxihOKCg==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:19.951917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97c208da0144cfc280b40b5869be615f41564255ffc1f0fbe325f6af203da2b1","sha256:8235980276769d3ec14ca53bbf79fadae42ddabbb43a4e6faa5412d6d6c3055d"],"state_sha256":"b210187e914fc2a2967e6af688712ddb5f2cd3a46d45ed0434dc81111b5cee9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DBSQg9l3wagS5+bxg5GPPC6jcnQS1f3yUND49edN1T+UUKACcbsR+4M+qjhZRozwl7ByhXR92FYY89ieZmocDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:13:41.742622Z","bundle_sha256":"6572166a08040e06ad4a26f2de4198662f9b72049e2a9a0a7bee32b34bb5976d"}}