{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:YPBC2O2YXSNZL5RXIUYTWM54U3","short_pith_number":"pith:YPBC2O2Y","schema_version":"1.0","canonical_sha256":"c3c22d3b58bc9b95f63745313b33bca6e60c67148a74301c9c4c3c53d92ff294","source":{"kind":"arxiv","id":"1507.08818","version":6},"attestation_state":"computed","paper":{"title":"A Visual Embedding for the Unsupervised Extraction of Abstract Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"D. Garcia-Gasulla, E. Ayguad\\'e, J. B\\'ejar, J. Labarta, R. Chen, T. Suzumura, U. Cort\\'es","submitted_at":"2015-07-31T10:16:42Z","abstract_excerpt":"Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existence of similar information on vector representations of images. For that purpose we define a methodology to obtain large, sparse vector representations of image classes, and generate vectors through the state-of-the-art deep learning architecture GoogLeNet for 20K images obtained from ImageNet. We first evaluate the resultant vector-space semantics through its correlation with WordNet distances, and find vector dista"},"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":"1507.08818","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-31T10:16:42Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"fdef63d08edd02f1383dae1d6461079376d576918950d6ce82c14f7bd742d218","abstract_canon_sha256":"bb97b1cb122ba2a197cd6cb606d1e98c65be343bea277838e834dff14595cb65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:53.022114Z","signature_b64":"TZtHN1Tb9s6r64jDoP0s0a8wjfmedHcBvQtASHauf5LA8rpFFoB6i5mvuo0dU9rnmlxen/3FZmznzgHbZ0cXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3c22d3b58bc9b95f63745313b33bca6e60c67148a74301c9c4c3c53d92ff294","last_reissued_at":"2026-05-18T00:54:53.021726Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:53.021726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Visual Embedding for the Unsupervised Extraction of Abstract Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"D. Garcia-Gasulla, E. Ayguad\\'e, J. B\\'ejar, J. Labarta, R. Chen, T. Suzumura, U. Cort\\'es","submitted_at":"2015-07-31T10:16:42Z","abstract_excerpt":"Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existence of similar information on vector representations of images. For that purpose we define a methodology to obtain large, sparse vector representations of image classes, and generate vectors through the state-of-the-art deep learning architecture GoogLeNet for 20K images obtained from ImageNet. We first evaluate the resultant vector-space semantics through its correlation with WordNet distances, and find vector dista"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08818","kind":"arxiv","version":6},"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":"1507.08818","created_at":"2026-05-18T00:54:53.021782+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.08818v6","created_at":"2026-05-18T00:54:53.021782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08818","created_at":"2026-05-18T00:54:53.021782+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPBC2O2YXSNZ","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPBC2O2YXSNZL5RX","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPBC2O2Y","created_at":"2026-05-18T12:29:50.041715+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/YPBC2O2YXSNZL5RXIUYTWM54U3","json":"https://pith.science/pith/YPBC2O2YXSNZL5RXIUYTWM54U3.json","graph_json":"https://pith.science/api/pith-number/YPBC2O2YXSNZL5RXIUYTWM54U3/graph.json","events_json":"https://pith.science/api/pith-number/YPBC2O2YXSNZL5RXIUYTWM54U3/events.json","paper":"https://pith.science/paper/YPBC2O2Y"},"agent_actions":{"view_html":"https://pith.science/pith/YPBC2O2YXSNZL5RXIUYTWM54U3","download_json":"https://pith.science/pith/YPBC2O2YXSNZL5RXIUYTWM54U3.json","view_paper":"https://pith.science/paper/YPBC2O2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.08818&json=true","fetch_graph":"https://pith.science/api/pith-number/YPBC2O2YXSNZL5RXIUYTWM54U3/graph.json","fetch_events":"https://pith.science/api/pith-number/YPBC2O2YXSNZL5RXIUYTWM54U3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPBC2O2YXSNZL5RXIUYTWM54U3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPBC2O2YXSNZL5RXIUYTWM54U3/action/storage_attestation","attest_author":"https://pith.science/pith/YPBC2O2YXSNZL5RXIUYTWM54U3/action/author_attestation","sign_citation":"https://pith.science/pith/YPBC2O2YXSNZL5RXIUYTWM54U3/action/citation_signature","submit_replication":"https://pith.science/pith/YPBC2O2YXSNZL5RXIUYTWM54U3/action/replication_record"}},"created_at":"2026-05-18T00:54:53.021782+00:00","updated_at":"2026-05-18T00:54:53.021782+00:00"}