{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MGC6DRCXIJYPWYRTSWI2USELPO","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":"b80cdccf36cef215a4c5c5872e39e73e49842202455e0c7f1092ec72ceb19e3c","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-01-07T15:43:22Z","title_canon_sha256":"43e36193c5d9c05bd07a87e63bff0bbd862037ef65f2e20ba61d5c2563177e6b"},"schema_version":"1.0","source":{"id":"1801.02200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.02200","created_at":"2026-05-18T00:26:34Z"},{"alias_kind":"arxiv_version","alias_value":"1801.02200v1","created_at":"2026-05-18T00:26:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.02200","created_at":"2026-05-18T00:26:34Z"},{"alias_kind":"pith_short_12","alias_value":"MGC6DRCXIJYP","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MGC6DRCXIJYPWYRT","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MGC6DRCX","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:f34a790b52db936a8a901a32c2091dd4bcdb7500193e54f4a87fd08dffe6d851","target":"graph","created_at":"2026-05-18T00:26:34Z","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":"The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube-8M allows us to deal with this large amount of data in manageable way. In this work, we find new ways of exploiting this dataset by taking advantage of the multi-modal information it provides. By means of a neural network, we are able to create links between audio and visual documents, by projecting them into a common region of the feature space, obtaining joint audio-visual embeddings. These links are used to retri","authors_text":"Amaia Salvador, Amanda Duarte, Didac Sur\\'is, Jordi Torres, Xavier Gir\\'o-i-Nieto","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-01-07T15:43:22Z","title":"Cross-modal Embeddings for Video and Audio Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.02200","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:f87f20e2b8765f371f513a565216ec442e545ee8a2956cf8c347de8742482a1f","target":"record","created_at":"2026-05-18T00:26:34Z","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":"b80cdccf36cef215a4c5c5872e39e73e49842202455e0c7f1092ec72ceb19e3c","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-01-07T15:43:22Z","title_canon_sha256":"43e36193c5d9c05bd07a87e63bff0bbd862037ef65f2e20ba61d5c2563177e6b"},"schema_version":"1.0","source":{"id":"1801.02200","kind":"arxiv","version":1}},"canonical_sha256":"6185e1c4574270fb62339591aa488b7b801fbfc7b10b9d31d5dd802fd54904a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6185e1c4574270fb62339591aa488b7b801fbfc7b10b9d31d5dd802fd54904a2","first_computed_at":"2026-05-18T00:26:34.580245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:34.580245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g0ahkyzqFUZXi8caAGqaH0oHRJSMVNGhMcHnpse27Fk0rExWS71IYGLdttLKPu8dUSjG7a3y/3+UqO6nEtbeBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:34.580805Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.02200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f87f20e2b8765f371f513a565216ec442e545ee8a2956cf8c347de8742482a1f","sha256:f34a790b52db936a8a901a32c2091dd4bcdb7500193e54f4a87fd08dffe6d851"],"state_sha256":"404567d78ef7bcf53e659b073ad91a9b20e7c5e65797acde777342b01b4b78d6"}