{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7X4543FPF2TTWOG6RJRBMNMPDR","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":"de48d7f4575fa2347dcf068745eec51f0ee6178de6a6e2b45a310be65f597714","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-18T17:59:45Z","title_canon_sha256":"038e0f4c79a5a766c2b2ff7b65defa0eb78b43e041160e4344a43ce23a61ab8c"},"schema_version":"1.0","source":{"id":"2304.09172","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09172","created_at":"2026-07-05T07:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09172v3","created_at":"2026-07-05T07:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09172","created_at":"2026-07-05T07:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"7X4543FPF2TT","created_at":"2026-07-05T07:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"7X4543FPF2TTWOG6","created_at":"2026-07-05T07:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"7X4543FP","created_at":"2026-07-05T07:34:47Z"}],"graph_snapshots":[{"event_id":"sha256:3153e55d48e514b81df93ee63e143148303b5c8561d97ea4c97efb0acc29c82e","target":"graph","created_at":"2026-07-05T07:34:47Z","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/2304.09172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept \"dog\" entails all images that contain dogs. Despite being intuitive, current large-scale vision and language models such as CLIP do not explicitly capture such hierarchy. We propose MERU, a contrastive model that yields hyperbolic representations of images and text. Hyperbolic spaces have suitable geometric properties to embed tree-like data, so MERU can better capture the underlying hierarchy in image-text datasets. Our results show that MERU learns a highly interpretable and structured repres","authors_text":"Justin Johnson, Karan Desai, Maximilian Nickel, Ramakrishna Vedantam, Tanmay Rajpurohit","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-18T17:59:45Z","title":"Hyperbolic Image-Text Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09172","kind":"arxiv","version":3},"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":"sha256:30d5e0f0abbe7b72e85646facc2b206b2af0342f7bc59dff6001b9c73c5d6360","target":"record","created_at":"2026-07-05T07:34:47Z","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":"de48d7f4575fa2347dcf068745eec51f0ee6178de6a6e2b45a310be65f597714","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-18T17:59:45Z","title_canon_sha256":"038e0f4c79a5a766c2b2ff7b65defa0eb78b43e041160e4344a43ce23a61ab8c"},"schema_version":"1.0","source":{"id":"2304.09172","kind":"arxiv","version":3}},"canonical_sha256":"fdf9de6caf2ea73b38de8a6216358f1c4822e1645d1d774c2e852e5729c12fe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdf9de6caf2ea73b38de8a6216358f1c4822e1645d1d774c2e852e5729c12fe2","first_computed_at":"2026-07-05T07:34:47.732684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:47.732684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5lKmaGdq1Z9eTdnXvi5CIXJ17uuimaGame8vvxGv4+Ib6DRN0NeQyhzmWE0GRmmAFcwfbgcxIhHJcZTksibWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:47.733160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.09172","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30d5e0f0abbe7b72e85646facc2b206b2af0342f7bc59dff6001b9c73c5d6360","sha256:3153e55d48e514b81df93ee63e143148303b5c8561d97ea4c97efb0acc29c82e"],"state_sha256":"fdca55369794809a225eef8edbccb52e47ccf03f3cc91124bd3c07b9eed0f46c"}