{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ABOPGO4IOWB3A3OTJQASI5TPYD","short_pith_number":"pith:ABOPGO4I","canonical_record":{"source":{"id":"2602.17555","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T17:09:30Z","cross_cats_sorted":[],"title_canon_sha256":"1d065cabbd4798020bb1a5f91a4a1cc24944fc30f3020b58d068a8196b4cd80d","abstract_canon_sha256":"738bbbadb35f4aaa474394bc167435c3e2efc39fbc041992bcf5b04ccb0614c0"},"schema_version":"1.0"},"canonical_sha256":"005cf33b887583b06dd34c0124766fc0d734630627c5bf474c4457dfd2ddf59e","source":{"kind":"arxiv","id":"2602.17555","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17555","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17555v3","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17555","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"ABOPGO4IOWB3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ABOPGO4IOWB3A3OT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ABOPGO4I","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ABOPGO4IOWB3A3OTJQASI5TPYD","target":"record","payload":{"canonical_record":{"source":{"id":"2602.17555","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T17:09:30Z","cross_cats_sorted":[],"title_canon_sha256":"1d065cabbd4798020bb1a5f91a4a1cc24944fc30f3020b58d068a8196b4cd80d","abstract_canon_sha256":"738bbbadb35f4aaa474394bc167435c3e2efc39fbc041992bcf5b04ccb0614c0"},"schema_version":"1.0"},"canonical_sha256":"005cf33b887583b06dd34c0124766fc0d734630627c5bf474c4457dfd2ddf59e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:31.104691Z","signature_b64":"0eaaB42sYqmPnw/Udtu0c6g7C/PTLotaiaYnrDI9orzKEsUDV6tIBOpkBQQlYRHtZuFY5oJJ/r2v17+zFYj+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"005cf33b887583b06dd34c0124766fc0d734630627c5bf474c4457dfd2ddf59e","last_reissued_at":"2026-05-18T02:44:31.104022Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:31.104022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.17555","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":"2026-05-18T02:44:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PhW32gBVnTh+YBPumN7Ibk9Mzywm9CY8CpHixb6F26CvTwK4Xcu/Trgqwx6bUwXiGxWZk9ppG8GtwHsvjiuZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T21:36:02.161018Z"},"content_sha256":"4851ed48421688b5cba282ca2185f3c1f84ee6109beb7dc77d8981e17b97f90a","schema_version":"1.0","event_id":"sha256:4851ed48421688b5cba282ca2185f3c1f84ee6109beb7dc77d8981e17b97f90a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ABOPGO4IOWB3A3OTJQASI5TPYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GraphThinker builds event graphs and applies visual rewards in reinforcement finetuning to ground MLLM video reasoning and reduce temporal hallucinations.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Da Li, Jian Hu, Shaogang Gong, Wei Li, Yuhang Zang, Ziquan Liu, Zixu Cheng","submitted_at":"2026-02-19T17:09:30Z","abstract_excerpt":"Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. Current Multimodal Large Language Models (MLLMs) are prone to severe temporal hallucinations in video reasoning. An underlying cause of these hallucinations is weak visual-temporal grounding and the lack of explicit structure for modelling event relations. Models often rely on auxiliary text, such as dense captions, rather than explicitly anchoring their reasoning in actual visual evidence. However, these textual representations are inherently unstr"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GraphThinker achieves an over 4% improvement in IoU=0.3 for moment localisation on RexTime and a 9.8% improvement in reducing temporal sequence hallucination plus 7.6% gain in Binary QA for action hallucination on VidHalluc compared to state-of-the-art methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an MLLM can reliably construct an accurate Event-based Video Scene Graph capturing true intra- and inter-event relations without introducing its own hallucinations or errors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GraphThinker reduces temporal hallucinations in video reasoning by constructing event-based scene graphs and applying visual attention rewards in reinforcement finetuning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GraphThinker builds event graphs and applies visual rewards in reinforcement finetuning to ground MLLM video reasoning and reduce temporal hallucinations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3a2b4b2fdb19db7222e0308328a6b0a5cf45b4f1b00ff78054a57661e199431e"},"source":{"id":"2602.17555","kind":"arxiv","version":3},"verdict":{"id":"5281cbdd-1d4e-47c3-86db-e9284fffed1e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T20:44:49.440450Z","strongest_claim":"GraphThinker achieves an over 4% improvement in IoU=0.3 for moment localisation on RexTime and a 9.8% improvement in reducing temporal sequence hallucination plus 7.6% gain in Binary QA for action hallucination on VidHalluc compared to state-of-the-art methods.","one_line_summary":"GraphThinker reduces temporal hallucinations in video reasoning by constructing event-based scene graphs and applying visual attention rewards in reinforcement finetuning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an MLLM can reliably construct an accurate Event-based Video Scene Graph capturing true intra- and inter-event relations without introducing its own hallucinations or errors.","pith_extraction_headline":"GraphThinker builds event graphs and applies visual rewards in reinforcement finetuning to ground MLLM video reasoning and reduce temporal hallucinations."},"references":{"count":74,"sample":[{"doi":"","year":2024,"title":"The claude 3 model family: Opus, sonnet, haiku.Claude-3 Model Card, 1(1):4, 2024","work_id":"b43ef26d-361f-46b3-a5f6-c74536435f1b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":2,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":null,"title":"arXiv preprint arXiv:2503.06486 (2025)","work_id":"7a75722a-70bd-4c38-81cc-ddbe39ab29cd","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Rextime: A benchmark suite for reasoning-across-time in videos.Advances in Neural In- formation Processing Systems, 37:28662–28673, 2024","work_id":"ff67c7e1-a377-46ec-aca7-3b2da5457373","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Sharegpt4video: Improving video understand- ing and generation with better captions.Advances in Neural Information Processing Systems, 37:19472–19495, 2024","work_id":"6dd48033-ac11-4d41-91dd-b567f0fcc51f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":74,"snapshot_sha256":"6cf95587fe44e6e795998d2d88bcb7fabe58d2dc169428129b87ff53749b4e72","internal_anchors":13},"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":"5281cbdd-1d4e-47c3-86db-e9284fffed1e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zlmxxDMF5TULC0oh5KHs9fWFYwQiJa7fTD+Gy52ea2p4EzlHqjeUdvfX5TQ18JOz0HuO3c9dK1Xd0JtmD+F4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T21:36:02.162105Z"},"content_sha256":"51c102711a417fbb4df01809bf34088b8f9d1f775e74b24dc20ec145c12ea795","schema_version":"1.0","event_id":"sha256:51c102711a417fbb4df01809bf34088b8f9d1f775e74b24dc20ec145c12ea795"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ABOPGO4IOWB3A3OTJQASI5TPYD/bundle.json","state_url":"https://pith.science/pith/ABOPGO4IOWB3A3OTJQASI5TPYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ABOPGO4IOWB3A3OTJQASI5TPYD/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":"2026-05-18T21:36:02Z","links":{"resolver":"https://pith.science/pith/ABOPGO4IOWB3A3OTJQASI5TPYD","bundle":"https://pith.science/pith/ABOPGO4IOWB3A3OTJQASI5TPYD/bundle.json","state":"https://pith.science/pith/ABOPGO4IOWB3A3OTJQASI5TPYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ABOPGO4IOWB3A3OTJQASI5TPYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ABOPGO4IOWB3A3OTJQASI5TPYD","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":"738bbbadb35f4aaa474394bc167435c3e2efc39fbc041992bcf5b04ccb0614c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T17:09:30Z","title_canon_sha256":"1d065cabbd4798020bb1a5f91a4a1cc24944fc30f3020b58d068a8196b4cd80d"},"schema_version":"1.0","source":{"id":"2602.17555","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17555","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17555v3","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17555","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"ABOPGO4IOWB3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ABOPGO4IOWB3A3OT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ABOPGO4I","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:51c102711a417fbb4df01809bf34088b8f9d1f775e74b24dc20ec145c12ea795","target":"graph","created_at":"2026-05-18T02:44:31Z","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":"GraphThinker achieves an over 4% improvement in IoU=0.3 for moment localisation on RexTime and a 9.8% improvement in reducing temporal sequence hallucination plus 7.6% gain in Binary QA for action hallucination on VidHalluc compared to state-of-the-art methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That an MLLM can reliably construct an accurate Event-based Video Scene Graph capturing true intra- and inter-event relations without introducing its own hallucinations or errors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GraphThinker reduces temporal hallucinations in video reasoning by constructing event-based scene graphs and applying visual attention rewards in reinforcement finetuning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GraphThinker builds event graphs and applies visual rewards in reinforcement finetuning to ground MLLM video reasoning and reduce temporal hallucinations."}],"snapshot_sha256":"3a2b4b2fdb19db7222e0308328a6b0a5cf45b4f1b00ff78054a57661e199431e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. Current Multimodal Large Language Models (MLLMs) are prone to severe temporal hallucinations in video reasoning. An underlying cause of these hallucinations is weak visual-temporal grounding and the lack of explicit structure for modelling event relations. Models often rely on auxiliary text, such as dense captions, rather than explicitly anchoring their reasoning in actual visual evidence. However, these textual representations are inherently unstr","authors_text":"Da Li, Jian Hu, Shaogang Gong, Wei Li, Yuhang Zang, Ziquan Liu, Zixu Cheng","cross_cats":[],"headline":"GraphThinker builds event graphs and applies visual rewards in reinforcement finetuning to ground MLLM video reasoning and reduce temporal hallucinations.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T17:09:30Z","title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking"},"references":{"count":74,"internal_anchors":13,"resolved_work":74,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"The claude 3 model family: Opus, sonnet, haiku.Claude-3 Model Card, 1(1):4, 2024","work_id":"b43ef26d-361f-46b3-a5f6-c74536435f1b","year":2024},{"cited_arxiv_id":"2502.13923","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"arXiv preprint arXiv:2503.06486 (2025)","work_id":"7a75722a-70bd-4c38-81cc-ddbe39ab29cd","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Rextime: A benchmark suite for reasoning-across-time in videos.Advances in Neural In- formation Processing Systems, 37:28662–28673, 2024","work_id":"ff67c7e1-a377-46ec-aca7-3b2da5457373","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Sharegpt4video: Improving video understand- ing and generation with better captions.Advances in Neural Information Processing Systems, 37:19472–19495, 2024","work_id":"6dd48033-ac11-4d41-91dd-b567f0fcc51f","year":2024}],"snapshot_sha256":"6cf95587fe44e6e795998d2d88bcb7fabe58d2dc169428129b87ff53749b4e72"},"source":{"id":"2602.17555","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T20:44:49.440450Z","id":"5281cbdd-1d4e-47c3-86db-e9284fffed1e","model_set":{"reader":"grok-4.3"},"one_line_summary":"GraphThinker reduces temporal hallucinations in video reasoning by constructing event-based scene graphs and applying visual attention rewards in reinforcement finetuning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GraphThinker builds event graphs and applies visual rewards in reinforcement finetuning to ground MLLM video reasoning and reduce temporal hallucinations.","strongest_claim":"GraphThinker achieves an over 4% improvement in IoU=0.3 for moment localisation on RexTime and a 9.8% improvement in reducing temporal sequence hallucination plus 7.6% gain in Binary QA for action hallucination on VidHalluc compared to state-of-the-art methods.","weakest_assumption":"That an MLLM can reliably construct an accurate Event-based Video Scene Graph capturing true intra- and inter-event relations without introducing its own hallucinations or errors."}},"verdict_id":"5281cbdd-1d4e-47c3-86db-e9284fffed1e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4851ed48421688b5cba282ca2185f3c1f84ee6109beb7dc77d8981e17b97f90a","target":"record","created_at":"2026-05-18T02:44:31Z","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":"738bbbadb35f4aaa474394bc167435c3e2efc39fbc041992bcf5b04ccb0614c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T17:09:30Z","title_canon_sha256":"1d065cabbd4798020bb1a5f91a4a1cc24944fc30f3020b58d068a8196b4cd80d"},"schema_version":"1.0","source":{"id":"2602.17555","kind":"arxiv","version":3}},"canonical_sha256":"005cf33b887583b06dd34c0124766fc0d734630627c5bf474c4457dfd2ddf59e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"005cf33b887583b06dd34c0124766fc0d734630627c5bf474c4457dfd2ddf59e","first_computed_at":"2026-05-18T02:44:31.104022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:31.104022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0eaaB42sYqmPnw/Udtu0c6g7C/PTLotaiaYnrDI9orzKEsUDV6tIBOpkBQQlYRHtZuFY5oJJ/r2v17+zFYj+DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:31.104691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17555","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4851ed48421688b5cba282ca2185f3c1f84ee6109beb7dc77d8981e17b97f90a","sha256:51c102711a417fbb4df01809bf34088b8f9d1f775e74b24dc20ec145c12ea795"],"state_sha256":"dd715c68d4deb7e8dd107dcd2e3ca5687a0bba3c2e2443d1915952bde0278ded"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s2U6dO/4lDZR7LEuf8oQzkx9Ls/TE0Gh/i/0V5NRyQ6/2NEDzVFQM7Nq8Q9NdXizWTjpwln4Zeg57jNQG4L5Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T21:36:02.165177Z","bundle_sha256":"7d0fcf06ef9f9ef2e2d8430e6c85cb11d52df4a86ff7a66adb072eef7313c302"}}