{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I5TKNXZW27SZT2QVSRB5KZOCHC","short_pith_number":"pith:I5TKNXZW","canonical_record":{"source":{"id":"2412.08111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T05:37:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3c7e42c69d09d924a0bf39f902f552a4dae386c40aaef85d0487e50f077c41fb","abstract_canon_sha256":"f73261e1265d54bfbca1bbe078b2b88185e701fc47686c8168b66711ff5cd1ba"},"schema_version":"1.0"},"canonical_sha256":"4766a6df36d7e599ea159443d565c238bb04b1d491bc12aee03ffeb83f8abc65","source":{"kind":"arxiv","id":"2412.08111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08111","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08111v1","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08111","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"I5TKNXZW27SZ","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"I5TKNXZW27SZT2QV","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"I5TKNXZW","created_at":"2026-07-05T09:47:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I5TKNXZW27SZT2QVSRB5KZOCHC","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T05:37:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3c7e42c69d09d924a0bf39f902f552a4dae386c40aaef85d0487e50f077c41fb","abstract_canon_sha256":"f73261e1265d54bfbca1bbe078b2b88185e701fc47686c8168b66711ff5cd1ba"},"schema_version":"1.0"},"canonical_sha256":"4766a6df36d7e599ea159443d565c238bb04b1d491bc12aee03ffeb83f8abc65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:44.618798Z","signature_b64":"S3UoEaP1N4bUoRCNEeFEEzwn/SokUNxBo9Dw60Unpv5WnkxtrZmVBnEiHmzmVDXEoCnk20ZVmckYdQ0si7ckDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4766a6df36d7e599ea159443d565c238bb04b1d491bc12aee03ffeb83f8abc65","last_reissued_at":"2026-07-05T09:47:44.618382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:44.618382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08111","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":"2026-07-05T09:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9p8s4sRMJB810uEGKY1pemN0cXE3Tj9JINKiVSRJps+ppUe6/0kLGDCQ3kFRSmwsUetzRXLS0eNX/2j/DqoqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:06:04.699484Z"},"content_sha256":"8e1930ecd83e22b7a5780b217c2b81b4474b9ff7f6254883fe88d6fb63517a55","schema_version":"1.0","event_id":"sha256:8e1930ecd83e22b7a5780b217c2b81b4474b9ff7f6254883fe88d6fb63517a55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I5TKNXZW27SZT2QVSRB5KZOCHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Arps, Hassan Sajjad, Laura Kallmeyer, Sageev Oore, Sri Harsha Dumpala","submitted_at":"2024-12-11T05:37:04Z","abstract_excerpt":"Vision-language models (VLMs), serve as foundation models for multi-modal applications such as image captioning and text-to-image generation. Recent studies have highlighted limitations in VLM text encoders, particularly in areas like compositionality and semantic understanding, though the underlying reasons for these limitations remain unclear. In this work, we aim to address this gap by analyzing the syntactic information, one of the fundamental linguistic properties, encoded by the text encoders of VLMs. We perform a thorough analysis comparing VLMs with different objective functions, param"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08111","kind":"arxiv","version":1},"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/2412.08111/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":"2026-07-05T09:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lBbmzphr6vTHXtcvImUh6TgiWwza4ZQ3d/ICUJ8Xni/OhplSm6b/p7Jfh9/4phfUz2V75ZSpWCocGvlZUOtrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:06:04.700042Z"},"content_sha256":"170b3164cfaf8162cea1664e8504d3eb9730d840e042fa47aa8f8af870773841","schema_version":"1.0","event_id":"sha256:170b3164cfaf8162cea1664e8504d3eb9730d840e042fa47aa8f8af870773841"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5TKNXZW27SZT2QVSRB5KZOCHC/bundle.json","state_url":"https://pith.science/pith/I5TKNXZW27SZT2QVSRB5KZOCHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5TKNXZW27SZT2QVSRB5KZOCHC/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":"2026-08-21T14:06:04Z","links":{"resolver":"https://pith.science/pith/I5TKNXZW27SZT2QVSRB5KZOCHC","bundle":"https://pith.science/pith/I5TKNXZW27SZT2QVSRB5KZOCHC/bundle.json","state":"https://pith.science/pith/I5TKNXZW27SZT2QVSRB5KZOCHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5TKNXZW27SZT2QVSRB5KZOCHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I5TKNXZW27SZT2QVSRB5KZOCHC","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":"f73261e1265d54bfbca1bbe078b2b88185e701fc47686c8168b66711ff5cd1ba","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T05:37:04Z","title_canon_sha256":"3c7e42c69d09d924a0bf39f902f552a4dae386c40aaef85d0487e50f077c41fb"},"schema_version":"1.0","source":{"id":"2412.08111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08111","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08111v1","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08111","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"I5TKNXZW27SZ","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"I5TKNXZW27SZT2QV","created_at":"2026-07-05T09:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"I5TKNXZW","created_at":"2026-07-05T09:47:44Z"}],"graph_snapshots":[{"event_id":"sha256:170b3164cfaf8162cea1664e8504d3eb9730d840e042fa47aa8f8af870773841","target":"graph","created_at":"2026-07-05T09:47:44Z","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/2412.08111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs), serve as foundation models for multi-modal applications such as image captioning and text-to-image generation. Recent studies have highlighted limitations in VLM text encoders, particularly in areas like compositionality and semantic understanding, though the underlying reasons for these limitations remain unclear. In this work, we aim to address this gap by analyzing the syntactic information, one of the fundamental linguistic properties, encoded by the text encoders of VLMs. We perform a thorough analysis comparing VLMs with different objective functions, param","authors_text":"David Arps, Hassan Sajjad, Laura Kallmeyer, Sageev Oore, Sri Harsha Dumpala","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T05:37:04Z","title":"Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08111","kind":"arxiv","version":1},"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":"sha256:8e1930ecd83e22b7a5780b217c2b81b4474b9ff7f6254883fe88d6fb63517a55","target":"record","created_at":"2026-07-05T09:47:44Z","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":"f73261e1265d54bfbca1bbe078b2b88185e701fc47686c8168b66711ff5cd1ba","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T05:37:04Z","title_canon_sha256":"3c7e42c69d09d924a0bf39f902f552a4dae386c40aaef85d0487e50f077c41fb"},"schema_version":"1.0","source":{"id":"2412.08111","kind":"arxiv","version":1}},"canonical_sha256":"4766a6df36d7e599ea159443d565c238bb04b1d491bc12aee03ffeb83f8abc65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4766a6df36d7e599ea159443d565c238bb04b1d491bc12aee03ffeb83f8abc65","first_computed_at":"2026-07-05T09:47:44.618382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:44.618382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S3UoEaP1N4bUoRCNEeFEEzwn/SokUNxBo9Dw60Unpv5WnkxtrZmVBnEiHmzmVDXEoCnk20ZVmckYdQ0si7ckDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:44.618798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e1930ecd83e22b7a5780b217c2b81b4474b9ff7f6254883fe88d6fb63517a55","sha256:170b3164cfaf8162cea1664e8504d3eb9730d840e042fa47aa8f8af870773841"],"state_sha256":"fa012345fdf6512a27cbf75d04b90c52a2d23bb079ada65d6b4967de7949b09e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqDuspGcYijpFPDBrjiEMzr1WwhrwEvdHbEqCeQkX3uKAvRCqRsTQW36PriLJNadeyBEbz5KyvRhhm/ZgzCRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T14:06:04.704315Z","bundle_sha256":"668518c089bad4fee1dc3550b6b7040fefbdcf147b04b8d2ae41db04e40a60d9"}}