{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UAWXLVH55HQ6G42E3B6KY3TGBW","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":"1ed70ce9004c2a367b1b0be3be45b48866e76f1a9dc6e18099f7ad0aa7fec79f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T08:13:37Z","title_canon_sha256":"73ae855a45f0e7f48f1631a5c77b7ebe8e9133f1ca0894bdd3f8cbfe286a1e65"},"schema_version":"1.0","source":{"id":"1804.01720","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01720","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01720v2","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01720","created_at":"2026-05-18T00:19:08Z"},{"alias_kind":"pith_short_12","alias_value":"UAWXLVH55HQ6","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UAWXLVH55HQ6G42E","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UAWXLVH5","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:1e3e08f603e8bb7a450c0ae1e98ef3cd6c72c18afd1ece1f2bfcbb8bd8d86e4a","target":"graph","created_at":"2026-05-18T00:19:08Z","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"},"paper":{"abstract_excerpt":"Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships. Such a multi-modal embedding can be trained and used for various tasks, notably image captioning. In the present work, we introduce a new architecture of this type, with a visual path that leverages recent space-aware pooling mechanisms. Combined with a textual path which is jointly trained from scratch, our semantic-visual embedding offers a versatile model. Once trained under the supervision of caption","authors_text":"Louis Chevallier, Martin Engilberge, Matthieu Cord, Patrick P\\'erez","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T08:13:37Z","title":"Finding beans in burgers: Deep semantic-visual embedding with localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01720","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":"sha256:50ec986534c70e93e0bed80811689e53347b9f88b5f9b1fd2b6a7ad8d7dddffd","target":"record","created_at":"2026-05-18T00:19:08Z","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":"1ed70ce9004c2a367b1b0be3be45b48866e76f1a9dc6e18099f7ad0aa7fec79f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T08:13:37Z","title_canon_sha256":"73ae855a45f0e7f48f1631a5c77b7ebe8e9133f1ca0894bdd3f8cbfe286a1e65"},"schema_version":"1.0","source":{"id":"1804.01720","kind":"arxiv","version":2}},"canonical_sha256":"a02d75d4fde9e1e37344d87cac6e660da6bc2f83a7af805d37bc45248791fe20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a02d75d4fde9e1e37344d87cac6e660da6bc2f83a7af805d37bc45248791fe20","first_computed_at":"2026-05-18T00:19:08.134468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:08.134468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hfN8ayKRjqjI8AilLGjLXkbPrNeNNsoO6RQTaocoSY0jbIMQHnyuRbrJu08N2/elPyoahiipSqekwWSPOcANBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:08.135177Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.01720","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50ec986534c70e93e0bed80811689e53347b9f88b5f9b1fd2b6a7ad8d7dddffd","sha256:1e3e08f603e8bb7a450c0ae1e98ef3cd6c72c18afd1ece1f2bfcbb8bd8d86e4a"],"state_sha256":"c8369e4a0c977c1a19280b3c238b17fd189fde3a8d4eb26ea3a0225908f8cf0b"}