{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:C2TOJLOGGPHKHOI4W43VPSTZMJ","short_pith_number":"pith:C2TOJLOG","schema_version":"1.0","canonical_sha256":"16a6e4adc633cea3b91cb73757ca79624341f207d872cde55db3bdcd8d464fee","source":{"kind":"arxiv","id":"1406.5679","version":1},"attestation_state":"computed","paper":{"title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrej Karpathy, Armand Joulin, Li Fei-Fei","submitted_at":"2014-06-22T06:22:50Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1406.5679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-22T06:22:50Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"7d1644f5b02e44ce8c078166f1182f7988783164688f866563e7fe1139a37ec0","abstract_canon_sha256":"74c5c832f9d9506e2781d65160459dd5a6ccf47b1f4de3b0fbf319dec6be70ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:10.995825Z","signature_b64":"lE2X3tD9eSxJvGkqz5H7F4szdKLte7FSkUxxlrPhVOGl+K3WYwZV4Z+bX44agx/HDaGqOwBZbxrS2q9EGoqdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16a6e4adc633cea3b91cb73757ca79624341f207d872cde55db3bdcd8d464fee","last_reissued_at":"2026-05-18T02:49:10.995254Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:10.995254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrej Karpathy, Armand Joulin, Li Fei-Fei","submitted_at":"2014-06-22T06:22:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.5679","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1406.5679","created_at":"2026-05-18T02:49:10.995368+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.5679v1","created_at":"2026-05-18T02:49:10.995368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.5679","created_at":"2026-05-18T02:49:10.995368+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2TOJLOGGPHK","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2TOJLOGGPHKHOI4","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2TOJLOG","created_at":"2026-05-18T12:28:22.404517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ","json":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ.json","graph_json":"https://pith.science/api/pith-number/C2TOJLOGGPHKHOI4W43VPSTZMJ/graph.json","events_json":"https://pith.science/api/pith-number/C2TOJLOGGPHKHOI4W43VPSTZMJ/events.json","paper":"https://pith.science/paper/C2TOJLOG"},"agent_actions":{"view_html":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ","download_json":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ.json","view_paper":"https://pith.science/paper/C2TOJLOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.5679&json=true","fetch_graph":"https://pith.science/api/pith-number/C2TOJLOGGPHKHOI4W43VPSTZMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/C2TOJLOGGPHKHOI4W43VPSTZMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ/action/storage_attestation","attest_author":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ/action/author_attestation","sign_citation":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ/action/citation_signature","submit_replication":"https://pith.science/pith/C2TOJLOGGPHKHOI4W43VPSTZMJ/action/replication_record"}},"created_at":"2026-05-18T02:49:10.995368+00:00","updated_at":"2026-05-18T02:49:10.995368+00:00"}