{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XUTFLNM2VAM4WF6SJACB6NOTHG","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":"1f13486743d21d10c6e4b70c78e0745ccffbae81f6ee5791028fa24e3fa00ef3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-25T12:56:41Z","title_canon_sha256":"95b1d6497b6681b4d164bbe63c43889e149edb03abfd95fd28e7710aba0c9201"},"schema_version":"1.0","source":{"id":"1908.09317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.09317","created_at":"2026-07-04T23:59:39Z"},{"alias_kind":"arxiv_version","alias_value":"1908.09317v1","created_at":"2026-07-04T23:59:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09317","created_at":"2026-07-04T23:59:39Z"},{"alias_kind":"pith_short_12","alias_value":"XUTFLNM2VAM4","created_at":"2026-07-04T23:59:39Z"},{"alias_kind":"pith_short_16","alias_value":"XUTFLNM2VAM4WF6S","created_at":"2026-07-04T23:59:39Z"},{"alias_kind":"pith_short_8","alias_value":"XUTFLNM2","created_at":"2026-07-04T23:59:39Z"}],"graph_snapshots":[{"event_id":"sha256:5c9bd07818eed18e05b177f63900fe4c245fb17a591143c0a0a1c9733dab5d98","target":"graph","created_at":"2026-07-04T23:59:39Z","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/1908.09317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding images without explicit supervision has become an important problem in computer vision. In this paper, we address image captioning by generating language descriptions of scenes without learning from annotated pairs of images and their captions. The core component of our approach is a shared latent space that is structured by visual concepts. In this space, the two modalities should be indistinguishable. A language model is first trained to encode sentences into semantically structured embeddings. Image features that are translated into this embedding space can be decoded into des","authors_text":"Christian Rupprecht, Iro Laina, Nassir Navab","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-25T12:56:41Z","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09317","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":"sha256:2fab1c51baec955192f011d7b2361d5633d5a405507aa6da16d1515888130895","target":"record","created_at":"2026-07-04T23:59:39Z","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":"1f13486743d21d10c6e4b70c78e0745ccffbae81f6ee5791028fa24e3fa00ef3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-25T12:56:41Z","title_canon_sha256":"95b1d6497b6681b4d164bbe63c43889e149edb03abfd95fd28e7710aba0c9201"},"schema_version":"1.0","source":{"id":"1908.09317","kind":"arxiv","version":1}},"canonical_sha256":"bd2655b59aa819cb17d248041f35d339b32420e29c73330032397e167c129f42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd2655b59aa819cb17d248041f35d339b32420e29c73330032397e167c129f42","first_computed_at":"2026-07-04T23:59:39.121095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:39.121095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yfe/cvbT9o6igVCjI794yIIS0KI7Zc3YnV6H8S2guxgPhtZypy+ASm/peYqRT+6rxAfkgdq6vk7SU+1nVplOAw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:39.121439Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.09317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fab1c51baec955192f011d7b2361d5633d5a405507aa6da16d1515888130895","sha256:5c9bd07818eed18e05b177f63900fe4c245fb17a591143c0a0a1c9733dab5d98"],"state_sha256":"e4471e64376ca6e64d4ac76938ab0b85e959056acd9d41cf15e93c406cc7f9cc"}