{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PE77VCYN2OQ4NY2DNVBEZVXDZN","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":"53db0a8a4b018f049aa71095591d4b339c475720ecf8521ac960b6ad26e0c77c","cross_cats_sorted":["cs.CV","cs.IR","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-20T12:35:54Z","title_canon_sha256":"d260d05d3abbf440a79ae27c481a894e765c19b8e039a0130dde4c60ce0a8319"},"schema_version":"1.0","source":{"id":"2310.13451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13451","created_at":"2026-07-05T07:03:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13451v1","created_at":"2026-07-05T07:03:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13451","created_at":"2026-07-05T07:03:03Z"},{"alias_kind":"pith_short_12","alias_value":"PE77VCYN2OQ4","created_at":"2026-07-05T07:03:03Z"},{"alias_kind":"pith_short_16","alias_value":"PE77VCYN2OQ4NY2D","created_at":"2026-07-05T07:03:03Z"},{"alias_kind":"pith_short_8","alias_value":"PE77VCYN","created_at":"2026-07-05T07:03:03Z"}],"graph_snapshots":[{"event_id":"sha256:a84c2e0c00a551cb07f0f87ec9088d3c8b7ebf6916361d0c688c4895e430f5e9","target":"graph","created_at":"2026-07-05T07:03:03Z","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/2310.13451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The cross-modal retrieval model leverages the potential of triple loss optimization to learn robust embedding spaces. However, existing methods often train these models in a singular pass, overlooking the distinction between semi-hard and hard triples in the optimization process. The oversight of not distinguishing between semi-hard and hard triples leads to suboptimal model performance. In this paper, we introduce a novel approach rooted in curriculum learning to address this problem. We propose a two-stage training paradigm that guides the model's learning process from semi-hard to hard trip","authors_text":"Donghuo Zeng, Kazushi Ikeda","cross_cats":["cs.CV","cs.IR","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-20T12:35:54Z","title":"Two-Stage Triplet Loss Training with Curriculum Augmentation for Audio-Visual Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13451","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":"sha256:9b1550cf8fec5b2aabd73166754afae54e0c89c501f5531f0dd7f310487f09cc","target":"record","created_at":"2026-07-05T07:03:03Z","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":"53db0a8a4b018f049aa71095591d4b339c475720ecf8521ac960b6ad26e0c77c","cross_cats_sorted":["cs.CV","cs.IR","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-20T12:35:54Z","title_canon_sha256":"d260d05d3abbf440a79ae27c481a894e765c19b8e039a0130dde4c60ce0a8319"},"schema_version":"1.0","source":{"id":"2310.13451","kind":"arxiv","version":1}},"canonical_sha256":"793ffa8b0dd3a1c6e3436d424cd6e3cb55681528091a13a62a68dd99ddae286c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"793ffa8b0dd3a1c6e3436d424cd6e3cb55681528091a13a62a68dd99ddae286c","first_computed_at":"2026-07-05T07:03:03.797111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:03.797111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hCfoNrvvbeGo40il3RDWXy+YyuhtdvLZqqwlFiG+dwy6SHUYSdIQXIudPMYZf442eTn52XTrDOVfkPzwqfOlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:03.797569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b1550cf8fec5b2aabd73166754afae54e0c89c501f5531f0dd7f310487f09cc","sha256:a84c2e0c00a551cb07f0f87ec9088d3c8b7ebf6916361d0c688c4895e430f5e9"],"state_sha256":"2d04c16ad8588653a73280522e336bcb5d4abca8ee7b1ef7493b1be96604a8e0"}