{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SYEL732W6KW6XCO5UDXL5WDWEF","short_pith_number":"pith:SYEL732W","canonical_record":{"source":{"id":"2605.13933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:11:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fe8a048d96c788449a7d9662070466f628847ec186ae3efa9cae63bddaa31fc4","abstract_canon_sha256":"cb602efc973523abe655d073cd740241bf8ab4ed73e850f9cad44288dfa31c64"},"schema_version":"1.0"},"canonical_sha256":"9608bfef56f2adeb89dda0eebed876216f071225838bbe3857d05ee6f46ee0e6","source":{"kind":"arxiv","id":"2605.13933","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13933","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13933v1","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13933","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"SYEL732W6KW6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SYEL732W6KW6XCO5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SYEL732W","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SYEL732W6KW6XCO5UDXL5WDWEF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:11:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fe8a048d96c788449a7d9662070466f628847ec186ae3efa9cae63bddaa31fc4","abstract_canon_sha256":"cb602efc973523abe655d073cd740241bf8ab4ed73e850f9cad44288dfa31c64"},"schema_version":"1.0"},"canonical_sha256":"9608bfef56f2adeb89dda0eebed876216f071225838bbe3857d05ee6f46ee0e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:13.958036Z","signature_b64":"XA9TYSZbEEIo7PSBOPSHIYyzb2nZCzRUqWnl853jwGxs5Vha6weqgbXkRQX/7MLrwwyyr8FSg+8dtW2ltWauCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9608bfef56f2adeb89dda0eebed876216f071225838bbe3857d05ee6f46ee0e6","last_reissued_at":"2026-05-17T23:39:13.957363Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:13.957363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13933","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":"2026-05-17T23:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4OZT3xpL0HdkAWk+sN+WyO+qo1ePCG73H6asJTubYYlEh1HJNH8GsEDihvsxIh4VOXl+k7Ng8ZWKIDLc10E1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T09:49:45.553762Z"},"content_sha256":"ad2b01c2ba8f7db6468cba538e1dcee78e6e4e864d9390c971bf922c7931b187","schema_version":"1.0","event_id":"sha256:ad2b01c2ba8f7db6468cba538e1dcee78e6e4e864d9390c971bf922c7931b187"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SYEL732W6KW6XCO5UDXL5WDWEF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Hybrid latent space modeling with architectural annealing separates acquisition variability from biological signals in structural connectomes.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam M. Saunders, Aravind R. Krishnan, Bennett A. Landman, Chenyu Gao, Daniel C. Moyer, Derek Archer, Elyssa McMaster, Gaurav Rudravaram, Jongyeon Yoon, Karthik Ramadass, Laura A. Barquero, Laurie B. Cutting, Lianrui Zuo, Lori L. Beason Held, Micah DArchangel, Murat Bilgel, Nancy R. Newlin, Praitayini Kanakaraj, Timothy J. Hohman, Tin Q. Nguyen","submitted_at":"2026-05-13T16:11:49Z","abstract_excerpt":"Acquisition differences across sites, scanners, and protocols in dMRI introduce variability that complicates structural connectome analysis. This motivates deep learning models that can represent high-dimensional connectomes in a low-dimensional space while explicitly separating acquisition-related effects from biological variation. Conventional dimensionality reduction methods model all variance as continuous, so acquisition effects often get absorbed into a continuous latent space. Recent hybrid latent-space models combine discrete and continuous components to address this, but typically req"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our architectural annealing produces stronger site learning (ARI=0.53, p<0.05) than these baselines. Results show that a hybrid continuous-discrete latent space, with architectural rather than loss-based annealing, provides a useful unsupervised mechanism for capturing acquisition variability in dMRI.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the discrete latent component specifically isolates acquisition variability rather than other unmeasured categorical factors such as age groups or disease status, and that the architectural annealing reliably prevents the discrete capacity from collapsing or absorbing continuous variance.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A hybrid VAE with architectural annealing learns discrete clusters aligned with scanner and protocol differences in a dataset of 7416 structural connectomes spanning 13 studies.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hybrid latent space modeling with architectural annealing separates acquisition variability from biological signals in structural connectomes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fa14f6637807e93acb8f1022f4abf4001012784e0daa7898c478d43a0ebb8358"},"source":{"id":"2605.13933","kind":"arxiv","version":1},"verdict":{"id":"171ccd48-18f1-4385-baf0-a52e505a5091","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T04:59:43.303927Z","strongest_claim":"Our architectural annealing produces stronger site learning (ARI=0.53, p<0.05) than these baselines. Results show that a hybrid continuous-discrete latent space, with architectural rather than loss-based annealing, provides a useful unsupervised mechanism for capturing acquisition variability in dMRI.","one_line_summary":"A hybrid VAE with architectural annealing learns discrete clusters aligned with scanner and protocol differences in a dataset of 7416 structural connectomes spanning 13 studies.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the discrete latent component specifically isolates acquisition variability rather than other unmeasured categorical factors such as age groups or disease status, and that the architectural annealing reliably prevents the discrete capacity from collapsing or absorbing continuous variance.","pith_extraction_headline":"Hybrid latent space modeling with architectural annealing separates acquisition variability from biological signals in structural connectomes."},"references":{"count":46,"sample":[{"doi":"","year":1986,"title":"1986 , isbn =","work_id":"77b20036-16a4-4f8c-beaf-386fe5f48bc3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Distilling the knowledge in a neural network , author=","work_id":"3359c732-9658-45f2-ad8a-cffc7591a8a7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Advances in neural information processing systems , volume=","work_id":"9b04d959-2f42-449a-829e-ee63c2972110","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"Magnetic Resonance in Medicine: An Official Journal of the International Society for Magnetic Resonance in Medicine , volume=","work_id":"cd02343c-c3eb-4667-bdd0-fb973d3d30bf","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"European journal of radiology , volume=","work_id":"3cd61704-f9f3-4694-96ba-a17841382436","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":46,"snapshot_sha256":"2c884d0c8ca17970a9176c4a136b52c43c75746a2874e881adeb8058307d015b","internal_anchors":1},"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":"171ccd48-18f1-4385-baf0-a52e505a5091"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHsMzAo6GmwKCg13fLP9j66gwvdBlBuyK/qnZOl4c7clATvNANUwXxsVn43eEA1PkcTvW35h87+NWc01NHXaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T09:49:45.554281Z"},"content_sha256":"b69d53ba09e69f063d0c43e5031cd5319887a7bbe208574cafebe3969c8be7cc","schema_version":"1.0","event_id":"sha256:b69d53ba09e69f063d0c43e5031cd5319887a7bbe208574cafebe3969c8be7cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYEL732W6KW6XCO5UDXL5WDWEF/bundle.json","state_url":"https://pith.science/pith/SYEL732W6KW6XCO5UDXL5WDWEF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYEL732W6KW6XCO5UDXL5WDWEF/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":"2026-06-02T09:49:45Z","links":{"resolver":"https://pith.science/pith/SYEL732W6KW6XCO5UDXL5WDWEF","bundle":"https://pith.science/pith/SYEL732W6KW6XCO5UDXL5WDWEF/bundle.json","state":"https://pith.science/pith/SYEL732W6KW6XCO5UDXL5WDWEF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYEL732W6KW6XCO5UDXL5WDWEF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SYEL732W6KW6XCO5UDXL5WDWEF","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":"cb602efc973523abe655d073cd740241bf8ab4ed73e850f9cad44288dfa31c64","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:11:49Z","title_canon_sha256":"fe8a048d96c788449a7d9662070466f628847ec186ae3efa9cae63bddaa31fc4"},"schema_version":"1.0","source":{"id":"2605.13933","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13933","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13933v1","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13933","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"SYEL732W6KW6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SYEL732W6KW6XCO5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SYEL732W","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b69d53ba09e69f063d0c43e5031cd5319887a7bbe208574cafebe3969c8be7cc","target":"graph","created_at":"2026-05-17T23:39:13Z","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":"Our architectural annealing produces stronger site learning (ARI=0.53, p<0.05) than these baselines. Results show that a hybrid continuous-discrete latent space, with architectural rather than loss-based annealing, provides a useful unsupervised mechanism for capturing acquisition variability in dMRI."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the discrete latent component specifically isolates acquisition variability rather than other unmeasured categorical factors such as age groups or disease status, and that the architectural annealing reliably prevents the discrete capacity from collapsing or absorbing continuous variance."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A hybrid VAE with architectural annealing learns discrete clusters aligned with scanner and protocol differences in a dataset of 7416 structural connectomes spanning 13 studies."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Hybrid latent space modeling with architectural annealing separates acquisition variability from biological signals in structural connectomes."}],"snapshot_sha256":"fa14f6637807e93acb8f1022f4abf4001012784e0daa7898c478d43a0ebb8358"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Acquisition differences across sites, scanners, and protocols in dMRI introduce variability that complicates structural connectome analysis. This motivates deep learning models that can represent high-dimensional connectomes in a low-dimensional space while explicitly separating acquisition-related effects from biological variation. Conventional dimensionality reduction methods model all variance as continuous, so acquisition effects often get absorbed into a continuous latent space. Recent hybrid latent-space models combine discrete and continuous components to address this, but typically req","authors_text":"Adam M. Saunders, Aravind R. Krishnan, Bennett A. Landman, Chenyu Gao, Daniel C. Moyer, Derek Archer, Elyssa McMaster, Gaurav Rudravaram, Jongyeon Yoon, Karthik Ramadass, Laura A. Barquero, Laurie B. Cutting, Lianrui Zuo, Lori L. Beason Held, Micah DArchangel, Murat Bilgel, Nancy R. Newlin, Praitayini Kanakaraj, Timothy J. Hohman, Tin Q. Nguyen","cross_cats":["cs.AI","stat.ML"],"headline":"Hybrid latent space modeling with architectural annealing separates acquisition variability from biological signals in structural connectomes.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:11:49Z","title":"Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling"},"references":{"count":46,"internal_anchors":1,"resolved_work":46,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"1986 , isbn =","work_id":"77b20036-16a4-4f8c-beaf-386fe5f48bc3","year":1986},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Distilling the knowledge in a neural network , author=","work_id":"3359c732-9658-45f2-ad8a-cffc7591a8a7","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Advances in neural information processing systems , volume=","work_id":"9b04d959-2f42-449a-829e-ee63c2972110","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Magnetic Resonance in Medicine: An Official Journal of the International Society for Magnetic Resonance in Medicine , volume=","work_id":"cd02343c-c3eb-4667-bdd0-fb973d3d30bf","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"European journal of radiology , volume=","work_id":"3cd61704-f9f3-4694-96ba-a17841382436","year":2011}],"snapshot_sha256":"2c884d0c8ca17970a9176c4a136b52c43c75746a2874e881adeb8058307d015b"},"source":{"id":"2605.13933","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T04:59:43.303927Z","id":"171ccd48-18f1-4385-baf0-a52e505a5091","model_set":{"reader":"grok-4.3"},"one_line_summary":"A hybrid VAE with architectural annealing learns discrete clusters aligned with scanner and protocol differences in a dataset of 7416 structural connectomes spanning 13 studies.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Hybrid latent space modeling with architectural annealing separates acquisition variability from biological signals in structural connectomes.","strongest_claim":"Our architectural annealing produces stronger site learning (ARI=0.53, p<0.05) than these baselines. Results show that a hybrid continuous-discrete latent space, with architectural rather than loss-based annealing, provides a useful unsupervised mechanism for capturing acquisition variability in dMRI.","weakest_assumption":"That the discrete latent component specifically isolates acquisition variability rather than other unmeasured categorical factors such as age groups or disease status, and that the architectural annealing reliably prevents the discrete capacity from collapsing or absorbing continuous variance."}},"verdict_id":"171ccd48-18f1-4385-baf0-a52e505a5091"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ad2b01c2ba8f7db6468cba538e1dcee78e6e4e864d9390c971bf922c7931b187","target":"record","created_at":"2026-05-17T23:39:13Z","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":"cb602efc973523abe655d073cd740241bf8ab4ed73e850f9cad44288dfa31c64","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:11:49Z","title_canon_sha256":"fe8a048d96c788449a7d9662070466f628847ec186ae3efa9cae63bddaa31fc4"},"schema_version":"1.0","source":{"id":"2605.13933","kind":"arxiv","version":1}},"canonical_sha256":"9608bfef56f2adeb89dda0eebed876216f071225838bbe3857d05ee6f46ee0e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9608bfef56f2adeb89dda0eebed876216f071225838bbe3857d05ee6f46ee0e6","first_computed_at":"2026-05-17T23:39:13.957363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:13.957363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XA9TYSZbEEIo7PSBOPSHIYyzb2nZCzRUqWnl853jwGxs5Vha6weqgbXkRQX/7MLrwwyyr8FSg+8dtW2ltWauCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:13.958036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13933","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad2b01c2ba8f7db6468cba538e1dcee78e6e4e864d9390c971bf922c7931b187","sha256:b69d53ba09e69f063d0c43e5031cd5319887a7bbe208574cafebe3969c8be7cc"],"state_sha256":"6a1916dcbe47081d6d63c99967b91a6591e2f2853a58a52291ef0e0ec5cc5597"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C7COZHu9iGRpIyuN8rhzX3Ww25goHJAwB98z0KKQHni3Z7HApatcuf11QHDv6trvaMZyKD3ACQijO56bv/MoDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T09:49:45.556722Z","bundle_sha256":"abb114f55d74d3d36f7cc7acc0dbdc106e781c972047a39f1e33e979e91e0e89"}}