{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MFNARZR7EENZ4FTMQI3CDO2GMK","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":"a045296359831860c0851d98305b15a6d92cab413c56a788db64d7eda87bd9c3","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:48:44Z","title_canon_sha256":"6d75d7dcebf24379fcc041c94405f3df9286d972c759ea149907997987530a86"},"schema_version":"1.0","source":{"id":"2305.14897","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14897","created_at":"2026-07-05T07:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14897v2","created_at":"2026-07-05T07:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14897","created_at":"2026-07-05T07:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"MFNARZR7EENZ","created_at":"2026-07-05T07:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"MFNARZR7EENZ4FTM","created_at":"2026-07-05T07:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"MFNARZR7","created_at":"2026-07-05T07:06:27Z"}],"graph_snapshots":[{"event_id":"sha256:9daa51bfdc2a88074200acbcf4d40aef283b52dd3e18e2f4c2e2c6b6168f7b9d","target":"graph","created_at":"2026-07-05T07:06:27Z","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/2305.14897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Performant vision-language (VL) models like CLIP represent captions using a single vector. How much information about language is lost in this bottleneck? We first curate CompPrompts, a set of increasingly compositional image captions that VL models should be able to capture (e.g., single object, to object+property, to multiple interacting objects). Then, we train text-only recovery probes that aim to reconstruct captions from single-vector text representations produced by several VL models. This approach does not require images, allowing us to test on a broader range of scenes compared to pri","authors_text":"Amita Kamath, Jack Hessel, Kai-Wei Chang","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:48:44Z","title":"Text encoders bottleneck compositionality in contrastive vision-language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14897","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:ab00e9672d39effa86224569f7b1330a2c71b98b442126f73b2c1ea3bacc6769","target":"record","created_at":"2026-07-05T07:06:27Z","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":"a045296359831860c0851d98305b15a6d92cab413c56a788db64d7eda87bd9c3","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:48:44Z","title_canon_sha256":"6d75d7dcebf24379fcc041c94405f3df9286d972c759ea149907997987530a86"},"schema_version":"1.0","source":{"id":"2305.14897","kind":"arxiv","version":2}},"canonical_sha256":"615a08e63f211b9e166c823621bb46629402e274fb151b00a8f1aaa75ef5ba12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"615a08e63f211b9e166c823621bb46629402e274fb151b00a8f1aaa75ef5ba12","first_computed_at":"2026-07-05T07:06:27.639008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:27.639008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R061rESuSVw7vPHAw44IAyuS05+YWftQNOFjNiSW9slb41UnUWn8Ga49Z74fuT4MpNsUtTdCsHzxBYA8NEo4AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:27.639495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14897","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab00e9672d39effa86224569f7b1330a2c71b98b442126f73b2c1ea3bacc6769","sha256:9daa51bfdc2a88074200acbcf4d40aef283b52dd3e18e2f4c2e2c6b6168f7b9d"],"state_sha256":"175471cf5bbd4cba0f5d4b220d6d5ca7ce9dae1c1517526b5dabdb7d5598d985"}