{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:C2TOJLOGGPHKHOI4W43VPSTZMJ","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":"74c5c832f9d9506e2781d65160459dd5a6ccf47b1f4de3b0fbf319dec6be70ec","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-22T06:22:50Z","title_canon_sha256":"7d1644f5b02e44ce8c078166f1182f7988783164688f866563e7fe1139a37ec0"},"schema_version":"1.0","source":{"id":"1406.5679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.5679","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"1406.5679v1","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.5679","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"C2TOJLOGGPHK","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"C2TOJLOGGPHKHOI4","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"C2TOJLOG","created_at":"2026-05-18T12:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:9b5a980474b7e1e58daf03ecd579e890167855571205e5ad3076f2e1ba63be47","target":"graph","created_at":"2026-05-18T02:49:10Z","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":"We introduce a model for bidirectional retrieval of images and sentences through a multi-modal embedding of visual and natural language data. Unlike previous models that directly map images or sentences into a common embedding space, our model works on a finer level and embeds fragments of images (objects) and fragments of sentences (typed dependency tree relations) into a common space. In addition to a ranking objective seen in previous work, this allows us to add a new fragment alignment objective that learns to directly associate these fragments across modalities. Extensive experimental eva","authors_text":"Andrej Karpathy, Armand Joulin, Li Fei-Fei","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-22T06:22:50Z","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.5679","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:eb4ed15a39d662b8304fd6a49a508fd2a4abc02ab3bef36c1f27d52032c364ef","target":"record","created_at":"2026-05-18T02:49:10Z","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":"74c5c832f9d9506e2781d65160459dd5a6ccf47b1f4de3b0fbf319dec6be70ec","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-22T06:22:50Z","title_canon_sha256":"7d1644f5b02e44ce8c078166f1182f7988783164688f866563e7fe1139a37ec0"},"schema_version":"1.0","source":{"id":"1406.5679","kind":"arxiv","version":1}},"canonical_sha256":"16a6e4adc633cea3b91cb73757ca79624341f207d872cde55db3bdcd8d464fee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16a6e4adc633cea3b91cb73757ca79624341f207d872cde55db3bdcd8d464fee","first_computed_at":"2026-05-18T02:49:10.995254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:49:10.995254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lE2X3tD9eSxJvGkqz5H7F4szdKLte7FSkUxxlrPhVOGl+K3WYwZV4Z+bX44agx/HDaGqOwBZbxrS2q9EGoqdCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:49:10.995825Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.5679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb4ed15a39d662b8304fd6a49a508fd2a4abc02ab3bef36c1f27d52032c364ef","sha256:9b5a980474b7e1e58daf03ecd579e890167855571205e5ad3076f2e1ba63be47"],"state_sha256":"ec6b12011b2e652805bcfac4edc94a6c913bc2558527ef0d98d64e4ae1863471"}