{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MZT5BHUOGCICVJQIXMF4PZKG57","short_pith_number":"pith:MZT5BHUO","canonical_record":{"source":{"id":"2601.06521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T10:42:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"39b8de3f26956be41342086393767becabc558491f7c9d889ec21d5fb410921c","abstract_canon_sha256":"0fb39b5127390a8ffe372f7f1b22a9f87cb3bf3594c245f9aaddd2625295d629"},"schema_version":"1.0"},"canonical_sha256":"6667d09e8e30902aa608bb0bc7e546efce89b7eee40721c39df540515be970ea","source":{"kind":"arxiv","id":"2601.06521","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06521","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06521v2","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06521","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"MZT5BHUOGCIC","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"MZT5BHUOGCICVJQI","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"MZT5BHUO","created_at":"2026-07-08T01:19:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MZT5BHUOGCICVJQIXMF4PZKG57","target":"record","payload":{"canonical_record":{"source":{"id":"2601.06521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T10:42:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"39b8de3f26956be41342086393767becabc558491f7c9d889ec21d5fb410921c","abstract_canon_sha256":"0fb39b5127390a8ffe372f7f1b22a9f87cb3bf3594c245f9aaddd2625295d629"},"schema_version":"1.0"},"canonical_sha256":"6667d09e8e30902aa608bb0bc7e546efce89b7eee40721c39df540515be970ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:09.495998Z","signature_b64":"S14gNvTlW8klczrKtyBH5YXAkOtL4SFNpFPI5Q5NI30VenZqbOzOxL6jyQY1ZDVTWQzAaMYbQjcDfjimqSmkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6667d09e8e30902aa608bb0bc7e546efce89b7eee40721c39df540515be970ea","last_reissued_at":"2026-07-08T01:19:09.495394Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:09.495394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.06521","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-08T01:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h0JfnJJe7sw4zXo/jSwK2fWjazgjySn08YX9NBWnWgZsUjbcA93nL9clR6JCyRkn1DUFBwHwfrsPJNo0zubaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T08:15:07.230529Z"},"content_sha256":"005623c1802c288e2a60410bbdbd799452842a54cfadc31f0e192f94d10402e0","schema_version":"1.0","event_id":"sha256:005623c1802c288e2a60410bbdbd799452842a54cfadc31f0e192f94d10402e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MZT5BHUOGCICVJQIXMF4PZKG57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BabyVision: Visual Reasoning Beyond Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baobao Chang, Fangfu Liu, Guopeng Li, Haiyang Shen, Hans Zhao, Haoning Wu, Haoyu Lu, Hongfeng He, Kaiyuan Chen, Kuan Li, Liang Chen, Ming Wu, Shuzheng Si, Tianyu Liu, Weichu Xie, Wendong Xu, Wenhao Chai, Xiaobo Hu, Xuanzhong Chen, Yang Liu, Y. Charles, Yiping Bao, Yixin Ren, Yiyan Liang, Yuan Gong, Yuantao Fan, Zefan Cai, Zhibo Yang, Zhiqi Huang, Ziqi Huang","submitted_at":"2026-01-10T10:42:44Z","abstract_excerpt":"While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06521","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.06521/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-08T01:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZquasOpFqOf/6xy1piURZiniqcPg2qFwlUl1y8ULtiyT7ioV4n2i6ELLb1TYAUL5kbzaZgrrGknSvwVJAuRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T08:15:07.230924Z"},"content_sha256":"fe36d6d2436b93529bfb299c5daa3c4132e9813bf378773f551b5d05568af3b5","schema_version":"1.0","event_id":"sha256:fe36d6d2436b93529bfb299c5daa3c4132e9813bf378773f551b5d05568af3b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZT5BHUOGCICVJQIXMF4PZKG57/bundle.json","state_url":"https://pith.science/pith/MZT5BHUOGCICVJQIXMF4PZKG57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZT5BHUOGCICVJQIXMF4PZKG57/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":"2026-07-19T08:15:07Z","links":{"resolver":"https://pith.science/pith/MZT5BHUOGCICVJQIXMF4PZKG57","bundle":"https://pith.science/pith/MZT5BHUOGCICVJQIXMF4PZKG57/bundle.json","state":"https://pith.science/pith/MZT5BHUOGCICVJQIXMF4PZKG57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZT5BHUOGCICVJQIXMF4PZKG57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MZT5BHUOGCICVJQIXMF4PZKG57","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":"0fb39b5127390a8ffe372f7f1b22a9f87cb3bf3594c245f9aaddd2625295d629","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T10:42:44Z","title_canon_sha256":"39b8de3f26956be41342086393767becabc558491f7c9d889ec21d5fb410921c"},"schema_version":"1.0","source":{"id":"2601.06521","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06521","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06521v2","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06521","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"MZT5BHUOGCIC","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"MZT5BHUOGCICVJQI","created_at":"2026-07-08T01:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"MZT5BHUO","created_at":"2026-07-08T01:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:fe36d6d2436b93529bfb299c5daa3c4132e9813bf378773f551b5d05568af3b5","target":"graph","created_at":"2026-07-08T01:19:09Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.06521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses acr","authors_text":"Baobao Chang, Fangfu Liu, Guopeng Li, Haiyang Shen, Hans Zhao, Haoning Wu, Haoyu Lu, Hongfeng He, Kaiyuan Chen, Kuan Li, Liang Chen, Ming Wu, Shuzheng Si, Tianyu Liu, Weichu Xie, Wendong Xu, Wenhao Chai, Xiaobo Hu, Xuanzhong Chen, Yang Liu, Y. Charles, Yiping Bao, Yixin Ren, Yiyan Liang, Yuan Gong, Yuantao Fan, Zefan Cai, Zhibo Yang, Zhiqi Huang, Ziqi Huang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T10:42:44Z","title":"BabyVision: Visual Reasoning Beyond Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06521","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:005623c1802c288e2a60410bbdbd799452842a54cfadc31f0e192f94d10402e0","target":"record","created_at":"2026-07-08T01:19:09Z","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":"0fb39b5127390a8ffe372f7f1b22a9f87cb3bf3594c245f9aaddd2625295d629","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T10:42:44Z","title_canon_sha256":"39b8de3f26956be41342086393767becabc558491f7c9d889ec21d5fb410921c"},"schema_version":"1.0","source":{"id":"2601.06521","kind":"arxiv","version":2}},"canonical_sha256":"6667d09e8e30902aa608bb0bc7e546efce89b7eee40721c39df540515be970ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6667d09e8e30902aa608bb0bc7e546efce89b7eee40721c39df540515be970ea","first_computed_at":"2026-07-08T01:19:09.495394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:09.495394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S14gNvTlW8klczrKtyBH5YXAkOtL4SFNpFPI5Q5NI30VenZqbOzOxL6jyQY1ZDVTWQzAaMYbQjcDfjimqSmkAw==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:09.495998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.06521","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:005623c1802c288e2a60410bbdbd799452842a54cfadc31f0e192f94d10402e0","sha256:fe36d6d2436b93529bfb299c5daa3c4132e9813bf378773f551b5d05568af3b5"],"state_sha256":"dc5e6218f0292b8c1069f996cb6dfcfc1331f6ed4404299d4a236e235104133f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDqBA9lg5wE+aPZbN4o4dT0ektgmfGdrBhqgEpaBPS2oebIG8qwqhwvzQBOx47Jg7R35ZUMiYtvX/mwButeRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T08:15:07.233391Z","bundle_sha256":"c037b4788d45683517558d2a0c192e877a43ed00222680e0135ca7d3683c195b"}}