{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FHWHZML6FV7RRY5W26MPAWXB52","short_pith_number":"pith:FHWHZML6","canonical_record":{"source":{"id":"2605.14626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:39:53Z","cross_cats_sorted":[],"title_canon_sha256":"ebafd982cd26bee767dc5be0b95b2e45ab935b1bbd0b7a960eb10d1d2ee37ca6","abstract_canon_sha256":"6237492e6b519623a95c253ad308914b6a7e7f91d2b5bfc1c25d46347b1a437f"},"schema_version":"1.0"},"canonical_sha256":"29ec7cb17e2d7f18e3b6d798f05ae1eeb407eb8ef040d9b723378d5275e82028","source":{"kind":"arxiv","id":"2605.14626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14626","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14626v1","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14626","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"FHWHZML6FV7R","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FHWHZML6FV7RRY5W","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FHWHZML6","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FHWHZML6FV7RRY5W26MPAWXB52","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:39:53Z","cross_cats_sorted":[],"title_canon_sha256":"ebafd982cd26bee767dc5be0b95b2e45ab935b1bbd0b7a960eb10d1d2ee37ca6","abstract_canon_sha256":"6237492e6b519623a95c253ad308914b6a7e7f91d2b5bfc1c25d46347b1a437f"},"schema_version":"1.0"},"canonical_sha256":"29ec7cb17e2d7f18e3b6d798f05ae1eeb407eb8ef040d9b723378d5275e82028","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:04.016282Z","signature_b64":"FkoDXjDIvQvnjPZNQ7xBB1ppxnPZuBlLQWmOVzoIX5C4XWq/LPsufy8rOg8XZmMrGKUVgot7+N0bXOATpR1oDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29ec7cb17e2d7f18e3b6d798f05ae1eeb407eb8ef040d9b723378d5275e82028","last_reissued_at":"2026-05-17T23:39:04.015768Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:04.015768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14626","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":"2026-05-17T23:39:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ody1Z54Vv3RNLuoFjLtm+Lj03QVS+hciX6sJGEYEnkr7RBU69y0SELKObOGc8dZMzZ5xTML+0x1E2dFCJeFwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:28:30.759540Z"},"content_sha256":"d4ba5c99516dc117a6a4b44886765e2e4744d2e479e26e98c73d1467286887ed","schema_version":"1.0","event_id":"sha256:d4ba5c99516dc117a6a4b44886765e2e4744d2e479e26e98c73d1467286887ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FHWHZML6FV7RRY5W26MPAWXB52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Ding, Fei Zhou, Haoyu Wang, Lei Zhang, Mengmeng Zheng, Ping Zhou, Wei Wei","submitted_at":"2026-05-14T09:39:53Z","abstract_excerpt":"RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms, decomposing joint triplet generation into local conditional processes. As a result, consistency among VIS, IR, and Label in spatial structure, semantic content, and cross-modal details cannot be reliably maintained. To address this issue, we propose UniTriGen, a unified triplet generation framework that directly generates spatially aligned, semantically cons"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That jointly encoding VIS, IR, and Label into a shared latent space and modeling them with a single diffusion process will reliably enforce global cross-modal consistency in spatial structure and semantics without introducing artifacts or biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T semantic segmentation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4e517537d8938a00cc87bf6cea41b9a19a121b1d1e455ac11684427deb6299a1"},"source":{"id":"2605.14626","kind":"arxiv","version":1},"verdict":{"id":"12c7f69d-df97-4026-8a7f-6b958af13a7e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:48:18.792752Z","strongest_claim":"UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models.","one_line_summary":"UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T semantic segmentation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That jointly encoding VIS, IR, and Label into a shared latent space and modeling them with a single diffusion process will reliably enforce global cross-modal consistency in spatial structure and semantics without introducing artifacts or biases.","pith_extraction_headline":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs."},"references":{"count":41,"sample":[{"doi":"","year":2025,"title":"Textssr: diffusion-based data synthesis for scene text recognition","work_id":"de692509-a80e-4288-ad60-f9e89cda767d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Text2earth: Unlocking text-driven remote sensing image generation with a global-scale dataset and a foundation model.IEEE Geoscience and Remote Sensing Magazine, 2025","work_id":"2c950442-15ce-4a7e-9547-c6f9d501133a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Datasetdm: Synthesizing data with perception annotations using diffusion models","work_id":"dc70158c-0417-4ab1-ab20-51d2e8a692dc","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation.Advances in Neural Information Processing Systems, 36: 76872–76892, 2023","work_id":"6759a602-891f-4a74-9230-805709de97dd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Pseudo-sd: pseudo controlled stable diffusion for semi-supervised and cross-domain semantic segmentation","work_id":"3f0a6b02-fe47-4e83-9d37-a87d58217680","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"c2499e326175543b92985379b7b1a1a7d237b9d128ffb66b40fa5ce9d0b50181","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ee08563d8c4a3bde856216414d8683a8bc8ebc302843fc4e9427bb59d00ad500"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"12c7f69d-df97-4026-8a7f-6b958af13a7e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nccXSitzUeTB6EbgoauRntEOMNLLtPzkricuFWgoIcoPWyZO77s2wp5SeEhUSVCPFv4EHXCy5Y1jlmtNIHaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:28:30.760680Z"},"content_sha256":"34bacd87cbb96aa00d3342ded2959fab10487cceac2be53c1f4ec3bc3c456734","schema_version":"1.0","event_id":"sha256:34bacd87cbb96aa00d3342ded2959fab10487cceac2be53c1f4ec3bc3c456734"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/bundle.json","state_url":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHWHZML6FV7RRY5W26MPAWXB52/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":"2026-05-25T20:28:30Z","links":{"resolver":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52","bundle":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/bundle.json","state":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHWHZML6FV7RRY5W26MPAWXB52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FHWHZML6FV7RRY5W26MPAWXB52","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":"6237492e6b519623a95c253ad308914b6a7e7f91d2b5bfc1c25d46347b1a437f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:39:53Z","title_canon_sha256":"ebafd982cd26bee767dc5be0b95b2e45ab935b1bbd0b7a960eb10d1d2ee37ca6"},"schema_version":"1.0","source":{"id":"2605.14626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14626","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14626v1","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14626","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"FHWHZML6FV7R","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FHWHZML6FV7RRY5W","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FHWHZML6","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:34bacd87cbb96aa00d3342ded2959fab10487cceac2be53c1f4ec3bc3c456734","target":"graph","created_at":"2026-05-17T23:39:04Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That jointly encoding VIS, IR, and Label into a shared latent space and modeling them with a single diffusion process will reliably enforce global cross-modal consistency in spatial structure and semantics without introducing artifacts or biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T semantic segmentation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs."}],"snapshot_sha256":"4e517537d8938a00cc87bf6cea41b9a19a121b1d1e455ac11684427deb6299a1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ee08563d8c4a3bde856216414d8683a8bc8ebc302843fc4e9427bb59d00ad500"},"paper":{"abstract_excerpt":"RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms, decomposing joint triplet generation into local conditional processes. As a result, consistency among VIS, IR, and Label in spatial structure, semantic content, and cross-modal details cannot be reliably maintained. To address this issue, we propose UniTriGen, a unified triplet generation framework that directly generates spatially aligned, semantically cons","authors_text":"Chen Ding, Fei Zhou, Haoyu Wang, Lei Zhang, Mengmeng Zheng, Ping Zhou, Wei Wei","cross_cats":[],"headline":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:39:53Z","title":"UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation"},"references":{"count":41,"internal_anchors":4,"resolved_work":41,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Textssr: diffusion-based data synthesis for scene text recognition","work_id":"de692509-a80e-4288-ad60-f9e89cda767d","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Text2earth: Unlocking text-driven remote sensing image generation with a global-scale dataset and a foundation model.IEEE Geoscience and Remote Sensing Magazine, 2025","work_id":"2c950442-15ce-4a7e-9547-c6f9d501133a","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Datasetdm: Synthesizing data with perception annotations using diffusion models","work_id":"dc70158c-0417-4ab1-ab20-51d2e8a692dc","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation.Advances in Neural Information Processing Systems, 36: 76872–76892, 2023","work_id":"6759a602-891f-4a74-9230-805709de97dd","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Pseudo-sd: pseudo controlled stable diffusion for semi-supervised and cross-domain semantic segmentation","work_id":"3f0a6b02-fe47-4e83-9d37-a87d58217680","year":2025}],"snapshot_sha256":"c2499e326175543b92985379b7b1a1a7d237b9d128ffb66b40fa5ce9d0b50181"},"source":{"id":"2605.14626","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:48:18.792752Z","id":"12c7f69d-df97-4026-8a7f-6b958af13a7e","model_set":{"reader":"grok-4.3"},"one_line_summary":"UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T semantic segmentation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs.","strongest_claim":"UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models.","weakest_assumption":"That jointly encoding VIS, IR, and Label into a shared latent space and modeling them with a single diffusion process will reliably enforce global cross-modal consistency in spatial structure and semantics without introducing artifacts or biases."}},"verdict_id":"12c7f69d-df97-4026-8a7f-6b958af13a7e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d4ba5c99516dc117a6a4b44886765e2e4744d2e479e26e98c73d1467286887ed","target":"record","created_at":"2026-05-17T23:39:04Z","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":"6237492e6b519623a95c253ad308914b6a7e7f91d2b5bfc1c25d46347b1a437f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:39:53Z","title_canon_sha256":"ebafd982cd26bee767dc5be0b95b2e45ab935b1bbd0b7a960eb10d1d2ee37ca6"},"schema_version":"1.0","source":{"id":"2605.14626","kind":"arxiv","version":1}},"canonical_sha256":"29ec7cb17e2d7f18e3b6d798f05ae1eeb407eb8ef040d9b723378d5275e82028","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29ec7cb17e2d7f18e3b6d798f05ae1eeb407eb8ef040d9b723378d5275e82028","first_computed_at":"2026-05-17T23:39:04.015768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:04.015768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FkoDXjDIvQvnjPZNQ7xBB1ppxnPZuBlLQWmOVzoIX5C4XWq/LPsufy8rOg8XZmMrGKUVgot7+N0bXOATpR1oDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:04.016282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4ba5c99516dc117a6a4b44886765e2e4744d2e479e26e98c73d1467286887ed","sha256:34bacd87cbb96aa00d3342ded2959fab10487cceac2be53c1f4ec3bc3c456734"],"state_sha256":"dcfd7525b8b3702cdfbf48e3ad384978414d3f30ab49f19dd62f1860c4388d51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Tryly0gj6yJQI0S0DL/JcWq+NQXGniKbL7e8qgoOYw9EaCQ605f/my0KlKBy/14VMzQvO1ZKhXeyLgu7heEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:28:30.765231Z","bundle_sha256":"5ae4d72fbce3e7fae537d6bc69ca016f69b939829bfe347b78a0e9655048d310"}}