{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EQI4KFJ47AA7JM2SSF7NIOIYRH","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":"064b2d053ee53b749e01146819fc6dd08e95680587aa394bdcbf8fac165eac1d","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-10T12:03:48Z","title_canon_sha256":"eff0be5fd65dad141f31fe4a719b5c0b8228e6976afcbfaa118b185d56ce371e"},"schema_version":"1.0","source":{"id":"1908.03737","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03737","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03737v3","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03737","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"pith_short_12","alias_value":"EQI4KFJ47AA7","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"pith_short_16","alias_value":"EQI4KFJ47AA7JM2S","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"pith_short_8","alias_value":"EQI4KFJ4","created_at":"2026-07-05T02:37:39Z"}],"graph_snapshots":[{"event_id":"sha256:d9f79b980cb153ffc247a52497237c6831cc60dfcd34064c8708929d5d8c44c6","target":"graph","created_at":"2026-07-05T02:37:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.03737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal retrieval aims to retrieve data in one modality by a query in another modality, which has been a very interesting research issue in the field of multimedia, information retrieval, and computer vision, and database. Most existing works focus on cross-modal retrieval between text-image, text-video, and lyrics-audio.Little research addresses cross-modal retrieval between audio and video due to limited audio-video paired datasets and semantic information. The main challenge of audio-visual cross-modal retrieval task focuses on learning joint embeddings from a shared subspace for comput","authors_text":"Donghuo Zeng, Keizo Oyama, Yi Yu","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-10T12:03:48Z","title":"Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03737","kind":"arxiv","version":3},"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:a9022321d946200398f5ef84715c123a49b96991c321ee713cbef074d5dffd48","target":"record","created_at":"2026-07-05T02:37:39Z","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":"064b2d053ee53b749e01146819fc6dd08e95680587aa394bdcbf8fac165eac1d","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-10T12:03:48Z","title_canon_sha256":"eff0be5fd65dad141f31fe4a719b5c0b8228e6976afcbfaa118b185d56ce371e"},"schema_version":"1.0","source":{"id":"1908.03737","kind":"arxiv","version":3}},"canonical_sha256":"2411c5153cf801f4b352917ed4391889e2f8cd144d03750148e245a1faecbd38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2411c5153cf801f4b352917ed4391889e2f8cd144d03750148e245a1faecbd38","first_computed_at":"2026-07-05T02:37:39.956701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:39.956701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DyHET912L8QUb0jgCZGoYhxrC9vx3OMAJEWatpHHGFFNc0mBA1xIuypZAy9bOVQ01E3n3WLpxlfDdZucR+YGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:39.957148Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.03737","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9022321d946200398f5ef84715c123a49b96991c321ee713cbef074d5dffd48","sha256:d9f79b980cb153ffc247a52497237c6831cc60dfcd34064c8708929d5d8c44c6"],"state_sha256":"f5d80c58a12269b1e08c409fb71dbdc9ed57c6a5e47a2bf8fb9029b2d1cc37a2"}