{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3QF4EDTRWX67FBM2UOS7DSSVTS","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":"33a07db4af2aab5bd458ade40552a4bd607bd371689d6fea6e29c5a536855d4e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T02:21:49Z","title_canon_sha256":"37fb1f8922cdcc7dd11e733a49e369a136481e1b7fc85e0a7d957ca999211986"},"schema_version":"1.0","source":{"id":"2408.13119","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13119","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13119v2","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13119","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"3QF4EDTRWX67","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"3QF4EDTRWX67FBM2","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"3QF4EDTR","created_at":"2026-07-05T09:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:bc00f569688c62d0436086a7a75fa3914c6976d16b02c91491a267ff89e16f85","target":"graph","created_at":"2026-07-05T09:05:38Z","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/2408.13119/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel framework for speech-image retrieval. We utilize speech-image contrastive (SIC) learning tasks to align speech and image representations at a coarse level and speech-image matching (SIM) learning tasks to further refine the fine-grained cross-modal alignment. SIC and SIM learning tasks are jointly trained in a unified manner. To optimize the learning process, we utilize an embedding queue that facilitates efficient sampling of high-quality and diverse negative representations during SIC learning. Additionally, it enhances the learning of SIM tasks by effective","authors_text":"Lifeng Zhou, Yuke Li","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T02:21:49Z","title":"Coarse-to-fine Alignment Makes Better Speech-image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13119","kind":"arxiv","version":2},"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":"sha256:82e9c3ddf876f40df78a6cb7358b367b15f51079d2525dba92c7afc4568d5bd7","target":"record","created_at":"2026-07-05T09:05:38Z","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":"33a07db4af2aab5bd458ade40552a4bd607bd371689d6fea6e29c5a536855d4e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T02:21:49Z","title_canon_sha256":"37fb1f8922cdcc7dd11e733a49e369a136481e1b7fc85e0a7d957ca999211986"},"schema_version":"1.0","source":{"id":"2408.13119","kind":"arxiv","version":2}},"canonical_sha256":"dc0bc20e71b5fdf2859aa3a5f1ca559cb10b14bbd9fe068b68b01142d455c388","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc0bc20e71b5fdf2859aa3a5f1ca559cb10b14bbd9fe068b68b01142d455c388","first_computed_at":"2026-07-05T09:05:38.641686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:38.641686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBnX7MxpQCWKrtttIcBz27Gval6e5/zkURsj/MGF1bL8YA2i/LRpJx0tMjQviIRiwLk1Xa1w0lCt4puAhsoSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:38.642165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13119","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82e9c3ddf876f40df78a6cb7358b367b15f51079d2525dba92c7afc4568d5bd7","sha256:bc00f569688c62d0436086a7a75fa3914c6976d16b02c91491a267ff89e16f85"],"state_sha256":"de72cb7dca495d77e1d823e5c9e074926f78ec02fdb1c5db593ef0c418cd9d40"}