{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TXQVCDGDU5XNKGAJFHRL5YFFOO","short_pith_number":"pith:TXQVCDGD","canonical_record":{"source":{"id":"2605.12975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T04:14:13Z","cross_cats_sorted":[],"title_canon_sha256":"1d97c7f21586a0542518b277b13610e8eca1507d01b4dc4e6eb54a3a3817b6dd","abstract_canon_sha256":"edd89fe4071ca30b1c3f0974ea426bf6988c50805ef42fad2f4913521ce95e34"},"schema_version":"1.0"},"canonical_sha256":"9de1510cc3a76ed5180929e2bee0a5738cae4cd717624087ade232a72852cc07","source":{"kind":"arxiv","id":"2605.12975","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12975","created_at":"2026-05-18T03:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12975v1","created_at":"2026-05-18T03:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12975","created_at":"2026-05-18T03:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"TXQVCDGDU5XN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TXQVCDGDU5XNKGAJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TXQVCDGD","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TXQVCDGDU5XNKGAJFHRL5YFFOO","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T04:14:13Z","cross_cats_sorted":[],"title_canon_sha256":"1d97c7f21586a0542518b277b13610e8eca1507d01b4dc4e6eb54a3a3817b6dd","abstract_canon_sha256":"edd89fe4071ca30b1c3f0974ea426bf6988c50805ef42fad2f4913521ce95e34"},"schema_version":"1.0"},"canonical_sha256":"9de1510cc3a76ed5180929e2bee0a5738cae4cd717624087ade232a72852cc07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:08.764742Z","signature_b64":"TMkC/6L0TYhuiB1mKHExE9OkcNaqNs+/Uco6zN7IfVorT/vE3a17cKuXz40HtUGUAiDnslQ8PHWRk20ykd6qCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9de1510cc3a76ed5180929e2bee0a5738cae4cd717624087ade232a72852cc07","last_reissued_at":"2026-05-18T03:09:08.763960Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:08.763960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12975","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":"2026-05-18T03:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gen4BuprYYLRzoSfhPCa7jSbKtRhnGvX0We9AdqaVsdx4Io9fP/U4C1v0ZjrT62D5xybH33PiGOlDdboLdQuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T03:40:55.610161Z"},"content_sha256":"c1ea910ad0054adf7b7d90a1dbfb18bf5d2ea1a75ddf916a61ed440dba808374","schema_version":"1.0","event_id":"sha256:c1ea910ad0054adf7b7d90a1dbfb18bf5d2ea1a75ddf916a61ed440dba808374"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TXQVCDGDU5XNKGAJFHRL5YFFOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PyRAG reformulates multi-hop RAG as synthesis and execution of Python programs over retrieval tools.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ge Liu, Jash Rajesh Parekh, Jiajun Fan, Jiashuo Sun, Jiawei Han, Jimeng Shi, Peiran Li, Pengcheng Jiang, Qinglong Zheng, Saizhuo Wang, Shaowen Wang, Yixuan Xie, Zhiyi Shi","submitted_at":"2026-05-13T04:14:13Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on multi-hop questions, where solving the task requires chaining multiple retrieval and reasoning steps. Key challenges are that current methods represent reasoning through free-form natural language, where intermediate states are implicit, retrieval queries can drift from intended entities, and errors are detected by the same model that produces them making self-reflection an unreliable, ungrounded signal.\n  We observe that multi-hop question answ"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PyRAG reformulates multi-hop RAG as program synthesis and execution, enabling compiler-grounded self-repair and execution-driven adaptive retrieval without any additional training, and consistently outperforms strong baselines on five QA benchmarks with large gains on compositional multi-hop datasets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That code-specialized language models can reliably synthesize correct executable programs for multi-hop reasoning and that execution feedback alone suffices for self-repair without additional training or human oversight.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PyRAG turns multi-hop reasoning into executable Python code over retrieval tools for explicit, verifiable step-by-step RAG.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PyRAG reformulates multi-hop RAG as synthesis and execution of Python programs over retrieval tools.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6b567fa34c9b29c699e967492ebebbdc3b88ea368fcf26988fb8075d3eaf7c6b"},"source":{"id":"2605.12975","kind":"arxiv","version":1},"verdict":{"id":"39d37e6d-7d48-41cb-a11b-8896600d4507","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:59:18.013477Z","strongest_claim":"PyRAG reformulates multi-hop RAG as program synthesis and execution, enabling compiler-grounded self-repair and execution-driven adaptive retrieval without any additional training, and consistently outperforms strong baselines on five QA benchmarks with large gains on compositional multi-hop datasets.","one_line_summary":"PyRAG turns multi-hop reasoning into executable Python code over retrieval tools for explicit, verifiable step-by-step RAG.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That code-specialized language models can reliably synthesize correct executable programs for multi-hop reasoning and that execution feedback alone suffices for self-repair without additional training or human oversight.","pith_extraction_headline":"PyRAG reformulates multi-hop RAG as synthesis and execution of Python programs over retrieval tools."},"references":{"count":51,"sample":[{"doi":"","year":2026,"title":"Pathrag: Pruning graph-based retrieval augmented generation with relational paths","work_id":"cd70c5f3-52f2-4dd8-8e03-f154e0c5499d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","work_id":"cc9775d9-2fbd-4690-a641-2b50ae4a59dc","ref_index":2,"cited_arxiv_id":"2503.19470","is_internal_anchor":true},{"doi":"","year":2022,"title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","work_id":"618aa44c-a6c6-425c-abce-8aa8aa842921","ref_index":3,"cited_arxiv_id":"2211.12588","is_internal_anchor":true},{"doi":"","year":2022,"title":"Binding language models in symbolic languages.arXiv preprint arXiv:2210.02875","work_id":"f8fe6642-904b-44b0-a533-ae63c3a213e1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","ref_index":5,"cited_arxiv_id":"2404.16130","is_internal_anchor":true}],"resolved_work":51,"snapshot_sha256":"623aa3942647c3c84ce1b82dd39849253305f391dfcfb130f4d96e437d2e6bc8","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"db6ce467eafda4bb230b655df36ffccf128fe248380b1cd95565d260e65d3f0c"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"39d37e6d-7d48-41cb-a11b-8896600d4507"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zw+P8FkzW4w+ddGsGeoYJ5jqzpUAtyFj9UrsHR4juay6BYNwjHbgsnhUXgO5IfH+YKk2DqFlk1s7oVzT65sHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T03:40:55.611220Z"},"content_sha256":"5a52dae5b46e192c2aee4e30ae236037fcdf1ea01e20d1a70c8f823ee7547c2d","schema_version":"1.0","event_id":"sha256:5a52dae5b46e192c2aee4e30ae236037fcdf1ea01e20d1a70c8f823ee7547c2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXQVCDGDU5XNKGAJFHRL5YFFOO/bundle.json","state_url":"https://pith.science/pith/TXQVCDGDU5XNKGAJFHRL5YFFOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXQVCDGDU5XNKGAJFHRL5YFFOO/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":"2026-06-09T03:40:55Z","links":{"resolver":"https://pith.science/pith/TXQVCDGDU5XNKGAJFHRL5YFFOO","bundle":"https://pith.science/pith/TXQVCDGDU5XNKGAJFHRL5YFFOO/bundle.json","state":"https://pith.science/pith/TXQVCDGDU5XNKGAJFHRL5YFFOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXQVCDGDU5XNKGAJFHRL5YFFOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TXQVCDGDU5XNKGAJFHRL5YFFOO","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":"edd89fe4071ca30b1c3f0974ea426bf6988c50805ef42fad2f4913521ce95e34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T04:14:13Z","title_canon_sha256":"1d97c7f21586a0542518b277b13610e8eca1507d01b4dc4e6eb54a3a3817b6dd"},"schema_version":"1.0","source":{"id":"2605.12975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12975","created_at":"2026-05-18T03:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12975v1","created_at":"2026-05-18T03:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12975","created_at":"2026-05-18T03:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"TXQVCDGDU5XN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TXQVCDGDU5XNKGAJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TXQVCDGD","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5a52dae5b46e192c2aee4e30ae236037fcdf1ea01e20d1a70c8f823ee7547c2d","target":"graph","created_at":"2026-05-18T03:09:08Z","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":"PyRAG reformulates multi-hop RAG as program synthesis and execution, enabling compiler-grounded self-repair and execution-driven adaptive retrieval without any additional training, and consistently outperforms strong baselines on five QA benchmarks with large gains on compositional multi-hop datasets."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That code-specialized language models can reliably synthesize correct executable programs for multi-hop reasoning and that execution feedback alone suffices for self-repair without additional training or human oversight."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PyRAG turns multi-hop reasoning into executable Python code over retrieval tools for explicit, verifiable step-by-step RAG."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PyRAG reformulates multi-hop RAG as synthesis and execution of Python programs over retrieval tools."}],"snapshot_sha256":"6b567fa34c9b29c699e967492ebebbdc3b88ea368fcf26988fb8075d3eaf7c6b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"db6ce467eafda4bb230b655df36ffccf128fe248380b1cd95565d260e65d3f0c"},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on multi-hop questions, where solving the task requires chaining multiple retrieval and reasoning steps. Key challenges are that current methods represent reasoning through free-form natural language, where intermediate states are implicit, retrieval queries can drift from intended entities, and errors are detected by the same model that produces them making self-reflection an unreliable, ungrounded signal.\n  We observe that multi-hop question answ","authors_text":"Ge Liu, Jash Rajesh Parekh, Jiajun Fan, Jiashuo Sun, Jiawei Han, Jimeng Shi, Peiran Li, Pengcheng Jiang, Qinglong Zheng, Saizhuo Wang, Shaowen Wang, Yixuan Xie, Zhiyi Shi","cross_cats":[],"headline":"PyRAG reformulates multi-hop RAG as synthesis and execution of Python programs over retrieval tools.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T04:14:13Z","title":"Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation"},"references":{"count":51,"internal_anchors":13,"resolved_work":51,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Pathrag: Pruning graph-based retrieval augmented generation with relational paths","work_id":"cd70c5f3-52f2-4dd8-8e03-f154e0c5499d","year":2026},{"cited_arxiv_id":"2503.19470","doi":"","is_internal_anchor":true,"ref_index":2,"title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","work_id":"cc9775d9-2fbd-4690-a641-2b50ae4a59dc","year":2025},{"cited_arxiv_id":"2211.12588","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","work_id":"618aa44c-a6c6-425c-abce-8aa8aa842921","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Binding language models in symbolic languages.arXiv preprint arXiv:2210.02875","work_id":"f8fe6642-904b-44b0-a533-ae63c3a213e1","year":2022},{"cited_arxiv_id":"2404.16130","doi":"","is_internal_anchor":true,"ref_index":5,"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","year":2024}],"snapshot_sha256":"623aa3942647c3c84ce1b82dd39849253305f391dfcfb130f4d96e437d2e6bc8"},"source":{"id":"2605.12975","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:59:18.013477Z","id":"39d37e6d-7d48-41cb-a11b-8896600d4507","model_set":{"reader":"grok-4.3"},"one_line_summary":"PyRAG turns multi-hop reasoning into executable Python code over retrieval tools for explicit, verifiable step-by-step RAG.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PyRAG reformulates multi-hop RAG as synthesis and execution of Python programs over retrieval tools.","strongest_claim":"PyRAG reformulates multi-hop RAG as program synthesis and execution, enabling compiler-grounded self-repair and execution-driven adaptive retrieval without any additional training, and consistently outperforms strong baselines on five QA benchmarks with large gains on compositional multi-hop datasets.","weakest_assumption":"That code-specialized language models can reliably synthesize correct executable programs for multi-hop reasoning and that execution feedback alone suffices for self-repair without additional training or human oversight."}},"verdict_id":"39d37e6d-7d48-41cb-a11b-8896600d4507"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c1ea910ad0054adf7b7d90a1dbfb18bf5d2ea1a75ddf916a61ed440dba808374","target":"record","created_at":"2026-05-18T03:09:08Z","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":"edd89fe4071ca30b1c3f0974ea426bf6988c50805ef42fad2f4913521ce95e34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T04:14:13Z","title_canon_sha256":"1d97c7f21586a0542518b277b13610e8eca1507d01b4dc4e6eb54a3a3817b6dd"},"schema_version":"1.0","source":{"id":"2605.12975","kind":"arxiv","version":1}},"canonical_sha256":"9de1510cc3a76ed5180929e2bee0a5738cae4cd717624087ade232a72852cc07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9de1510cc3a76ed5180929e2bee0a5738cae4cd717624087ade232a72852cc07","first_computed_at":"2026-05-18T03:09:08.763960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:08.763960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TMkC/6L0TYhuiB1mKHExE9OkcNaqNs+/Uco6zN7IfVorT/vE3a17cKuXz40HtUGUAiDnslQ8PHWRk20ykd6qCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:08.764742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1ea910ad0054adf7b7d90a1dbfb18bf5d2ea1a75ddf916a61ed440dba808374","sha256:5a52dae5b46e192c2aee4e30ae236037fcdf1ea01e20d1a70c8f823ee7547c2d"],"state_sha256":"5848d2a0efb199e9bb34fd804bd1ac3668e2867b86835ff5e2e86f9a2e8ea713"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+r7D98AeJaQWk4dxTOCdGdY+EH6L1m0Xoj/iDf2BdPAPfpn6f8byIH43rjdhXaTEdAmB6tPTEAl1x+cnYI5Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T03:40:55.616090Z","bundle_sha256":"81caa4f3792769bab6d0689c3f417d8db71114d6443b8dc004a1e2a50d4f9532"}}