{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VV6ZO7CAHAGPGER476ZT4MZ3UC","short_pith_number":"pith:VV6ZO7CA","canonical_record":{"source":{"id":"2605.13675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T15:34:41Z","cross_cats_sorted":["cs.LG","q-bio.NC"],"title_canon_sha256":"1e2f0e11f256be3fad11a3981774c2c565bd502d9034ab45f85a08f61e45285f","abstract_canon_sha256":"e7aadf53fad99880373cbdc5a74975621a83eae015ba3bb9b6f47839ff0c2d3a"},"schema_version":"1.0"},"canonical_sha256":"ad7d977c40380cf3123cffb33e333ba08aa22105a61901a6abdc251e16968480","source":{"kind":"arxiv","id":"2605.13675","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13675","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13675v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13675","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"VV6ZO7CAHAGP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VV6ZO7CAHAGPGER4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VV6ZO7CA","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VV6ZO7CAHAGPGER476ZT4MZ3UC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T15:34:41Z","cross_cats_sorted":["cs.LG","q-bio.NC"],"title_canon_sha256":"1e2f0e11f256be3fad11a3981774c2c565bd502d9034ab45f85a08f61e45285f","abstract_canon_sha256":"e7aadf53fad99880373cbdc5a74975621a83eae015ba3bb9b6f47839ff0c2d3a"},"schema_version":"1.0"},"canonical_sha256":"ad7d977c40380cf3123cffb33e333ba08aa22105a61901a6abdc251e16968480","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:17.113418Z","signature_b64":"vcE2AHu7dWUBpcQVaZfvvfNpnFiUtwXDuINXACYqqPDGFYqhGAN8uo6QHxhnmpMZIoHmlIuV1o6Fq2tP/qZNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad7d977c40380cf3123cffb33e333ba08aa22105a61901a6abdc251e16968480","last_reissued_at":"2026-05-18T02:44:17.112127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:17.112127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13675","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":"2026-05-18T02:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOcRIwWfirFsMAMYKy0IBInG23jFyWGYgOKNdiv6R43ME+5y61TcnTBbwJzcRRriwwxR6vuMC5AjluOHw/nOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T15:10:25.159718Z"},"content_sha256":"8ee19c9bc715ede7926607d70134b5804ff39092badf400a476ae5bb9185b158","schema_version":"1.0","event_id":"sha256:8ee19c9bc715ede7926607d70134b5804ff39092badf400a476ae5bb9185b158"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VV6ZO7CAHAGPGER476ZT4MZ3UC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Characterizing Universal Object Representations Across Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Vision models converge on universal object dimensions that are more interpretable and align better with biological vision.","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Florian P. Mahner, Francisco Pereira, Johannes Roth, Ka Chun Lam, Martin N. Hebart, Michael F. Bonner","submitted_at":"2026-05-13T15:34:41Z","abstract_excerpt":"Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. However, what remains unknown is which visual properties models actually converge on and which factors may underlie this convergence. To address this, we decompose the object similarity structure of 162 diverse vision models into a small set of non-negative dimensions. To determine universal versus model-specific dimensions, we then estimate how often each dimension reappears across models. In contrast to model-specific dimensions, universal dime"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In contrast to model-specific dimensions, universal dimensions are more interpretable and more strongly driven by conceptual image properties... models with more universal dimensions also better predict macaque IT activity and human similarity judgments, suggesting that universality reflects representations relevant to biological vision.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That reappearance frequency across the 162 models reliably identifies universal dimensions and that the non-negative decomposition fully captures the relevant object similarity structure without significant loss of information.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Vision models converge on universal object dimensions that are semantically interpretable and align more closely with biological vision than model-specific ones.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Vision models converge on universal object dimensions that are more interpretable and align better with biological vision.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"afee106e478b72a98cb374266c459a46784f6af23993a3e8ad725b64c2585de8"},"source":{"id":"2605.13675","kind":"arxiv","version":1},"verdict":{"id":"484d3aca-b695-4f7e-ad4b-77886aa3b967","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:19:41.183498Z","strongest_claim":"In contrast to model-specific dimensions, universal dimensions are more interpretable and more strongly driven by conceptual image properties... models with more universal dimensions also better predict macaque IT activity and human similarity judgments, suggesting that universality reflects representations relevant to biological vision.","one_line_summary":"Vision models converge on universal object dimensions that are semantically interpretable and align more closely with biological vision than model-specific ones.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That reappearance frequency across the 162 models reliably identifies universal dimensions and that the non-negative decomposition fully captures the relevant object similarity structure without significant loss of information.","pith_extraction_headline":"Vision models converge on universal object dimensions that are more interpretable and align better with biological vision."},"references":{"count":54,"sample":[{"doi":"","year":2015,"title":"Y . LeCun, Y . Bengio, and G. Hinton. Deep learning.Nature, 521:436–444, 2015","work_id":"543124df-682f-4497-ad6f-ee7092497552","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"N. Kanwisher, M. Khosla, and K. Dobs. Using artificial neural networks to ask ’why’ questions of minds and brains.Trends in Neurosciences, 46:240–254, 2023","work_id":"a85db324-dc6a-4af5-8db9-cbd8029e8ec8","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A. Doerig, R. P. Sommers, K. Seeliger, B. Richards, J. Ismael, G. W. Lindsay, K. P. Kording, T. Konkle, M. A. J. van Gerven, N. Kriegeskorte, and T. C. Kietzmann. The neuroconnectionist research progr","work_id":"25ed3788-5764-47a2-857b-95be3646d2aa","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"D. L. K. Yamins and J. J. DiCarlo. Using goal-driven deep learning models to understand sensory cortex. Nature Neuroscience, 19:356–365, 2016","work_id":"cd2dd6df-3e3c-4cd1-bf10-93e217bbda53","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"M. Huh, B. Cheung, T. Wang, and P. Isola. Position: The platonic representation hypothesis.Proceedings of Machine Learning Research, 235:20617–20642, 2024","work_id":"e10f2c45-e82f-4a42-8f9e-b1bbdd09d5ba","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":54,"snapshot_sha256":"ed7ca553ee21c2ef0037ec346b300c701e7b52b5ae6e08e3eb210e5a59a3a28d","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"62f60f321f6c843d9bb9d8880e5c70fae1621f48621961108d16dd20ce222c38"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"484d3aca-b695-4f7e-ad4b-77886aa3b967"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s/u/UeGie1EAwkwDFT0/FsXFAOxqfP3TqAc5cdhc36/wP4NFr5upU7X37Cl1rn7uehDWQA012ikEmiV0lAebCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T15:10:25.160364Z"},"content_sha256":"c2acc14a35a4cabf3c157b894f37c262cd8d9c037911561af4f722f1c0aa1a17","schema_version":"1.0","event_id":"sha256:c2acc14a35a4cabf3c157b894f37c262cd8d9c037911561af4f722f1c0aa1a17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VV6ZO7CAHAGPGER476ZT4MZ3UC/bundle.json","state_url":"https://pith.science/pith/VV6ZO7CAHAGPGER476ZT4MZ3UC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VV6ZO7CAHAGPGER476ZT4MZ3UC/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":"2026-06-25T15:10:25Z","links":{"resolver":"https://pith.science/pith/VV6ZO7CAHAGPGER476ZT4MZ3UC","bundle":"https://pith.science/pith/VV6ZO7CAHAGPGER476ZT4MZ3UC/bundle.json","state":"https://pith.science/pith/VV6ZO7CAHAGPGER476ZT4MZ3UC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VV6ZO7CAHAGPGER476ZT4MZ3UC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VV6ZO7CAHAGPGER476ZT4MZ3UC","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":"e7aadf53fad99880373cbdc5a74975621a83eae015ba3bb9b6f47839ff0c2d3a","cross_cats_sorted":["cs.LG","q-bio.NC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T15:34:41Z","title_canon_sha256":"1e2f0e11f256be3fad11a3981774c2c565bd502d9034ab45f85a08f61e45285f"},"schema_version":"1.0","source":{"id":"2605.13675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13675","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13675v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13675","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"VV6ZO7CAHAGP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VV6ZO7CAHAGPGER4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VV6ZO7CA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c2acc14a35a4cabf3c157b894f37c262cd8d9c037911561af4f722f1c0aa1a17","target":"graph","created_at":"2026-05-18T02:44:17Z","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":"In contrast to model-specific dimensions, universal dimensions are more interpretable and more strongly driven by conceptual image properties... models with more universal dimensions also better predict macaque IT activity and human similarity judgments, suggesting that universality reflects representations relevant to biological vision."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That reappearance frequency across the 162 models reliably identifies universal dimensions and that the non-negative decomposition fully captures the relevant object similarity structure without significant loss of information."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Vision models converge on universal object dimensions that are semantically interpretable and align more closely with biological vision than model-specific ones."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Vision models converge on universal object dimensions that are more interpretable and align better with biological vision."}],"snapshot_sha256":"afee106e478b72a98cb374266c459a46784f6af23993a3e8ad725b64c2585de8"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"62f60f321f6c843d9bb9d8880e5c70fae1621f48621961108d16dd20ce222c38"},"paper":{"abstract_excerpt":"Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. However, what remains unknown is which visual properties models actually converge on and which factors may underlie this convergence. To address this, we decompose the object similarity structure of 162 diverse vision models into a small set of non-negative dimensions. To determine universal versus model-specific dimensions, we then estimate how often each dimension reappears across models. In contrast to model-specific dimensions, universal dime","authors_text":"Florian P. Mahner, Francisco Pereira, Johannes Roth, Ka Chun Lam, Martin N. Hebart, Michael F. Bonner","cross_cats":["cs.LG","q-bio.NC"],"headline":"Vision models converge on universal object dimensions that are more interpretable and align better with biological vision.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T15:34:41Z","title":"Characterizing Universal Object Representations Across Vision Models"},"references":{"count":54,"internal_anchors":0,"resolved_work":54,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Y . LeCun, Y . Bengio, and G. Hinton. Deep learning.Nature, 521:436–444, 2015","work_id":"543124df-682f-4497-ad6f-ee7092497552","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"N. Kanwisher, M. Khosla, and K. Dobs. Using artificial neural networks to ask ’why’ questions of minds and brains.Trends in Neurosciences, 46:240–254, 2023","work_id":"a85db324-dc6a-4af5-8db9-cbd8029e8ec8","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"A. Doerig, R. P. Sommers, K. Seeliger, B. Richards, J. Ismael, G. W. Lindsay, K. P. Kording, T. Konkle, M. A. J. van Gerven, N. Kriegeskorte, and T. C. Kietzmann. The neuroconnectionist research progr","work_id":"25ed3788-5764-47a2-857b-95be3646d2aa","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"D. L. K. Yamins and J. J. DiCarlo. Using goal-driven deep learning models to understand sensory cortex. Nature Neuroscience, 19:356–365, 2016","work_id":"cd2dd6df-3e3c-4cd1-bf10-93e217bbda53","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"M. Huh, B. Cheung, T. Wang, and P. Isola. Position: The platonic representation hypothesis.Proceedings of Machine Learning Research, 235:20617–20642, 2024","work_id":"e10f2c45-e82f-4a42-8f9e-b1bbdd09d5ba","year":2024}],"snapshot_sha256":"ed7ca553ee21c2ef0037ec346b300c701e7b52b5ae6e08e3eb210e5a59a3a28d"},"source":{"id":"2605.13675","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:19:41.183498Z","id":"484d3aca-b695-4f7e-ad4b-77886aa3b967","model_set":{"reader":"grok-4.3"},"one_line_summary":"Vision models converge on universal object dimensions that are semantically interpretable and align more closely with biological vision than model-specific ones.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Vision models converge on universal object dimensions that are more interpretable and align better with biological vision.","strongest_claim":"In contrast to model-specific dimensions, universal dimensions are more interpretable and more strongly driven by conceptual image properties... models with more universal dimensions also better predict macaque IT activity and human similarity judgments, suggesting that universality reflects representations relevant to biological vision.","weakest_assumption":"That reappearance frequency across the 162 models reliably identifies universal dimensions and that the non-negative decomposition fully captures the relevant object similarity structure without significant loss of information."}},"verdict_id":"484d3aca-b695-4f7e-ad4b-77886aa3b967"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8ee19c9bc715ede7926607d70134b5804ff39092badf400a476ae5bb9185b158","target":"record","created_at":"2026-05-18T02:44:17Z","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":"e7aadf53fad99880373cbdc5a74975621a83eae015ba3bb9b6f47839ff0c2d3a","cross_cats_sorted":["cs.LG","q-bio.NC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T15:34:41Z","title_canon_sha256":"1e2f0e11f256be3fad11a3981774c2c565bd502d9034ab45f85a08f61e45285f"},"schema_version":"1.0","source":{"id":"2605.13675","kind":"arxiv","version":1}},"canonical_sha256":"ad7d977c40380cf3123cffb33e333ba08aa22105a61901a6abdc251e16968480","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad7d977c40380cf3123cffb33e333ba08aa22105a61901a6abdc251e16968480","first_computed_at":"2026-05-18T02:44:17.112127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:17.112127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vcE2AHu7dWUBpcQVaZfvvfNpnFiUtwXDuINXACYqqPDGFYqhGAN8uo6QHxhnmpMZIoHmlIuV1o6Fq2tP/qZNDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:17.113418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ee19c9bc715ede7926607d70134b5804ff39092badf400a476ae5bb9185b158","sha256:c2acc14a35a4cabf3c157b894f37c262cd8d9c037911561af4f722f1c0aa1a17"],"state_sha256":"30a453637ef919dfc60c1d15c8fa48204774d323a146729b4f5ccb2f7d019881"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iQ2QHI3JcxMszmi6WvEYRnKd/9gVWYm5P2eDBe0mhSworkZwgvvVhmMYSHX0mlrMYOfC1ZGcQXxB4+iwBUkbAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T15:10:25.162925Z","bundle_sha256":"d098e9f611e620a9c0d164e52f4b23c116597d8896ec222f5e9a1b880552089c"}}