{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WMXZ4LUAIGZN6GS4HK7WEXPCR3","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":"78f607e2fdca7f85c0776a9b468a0b99399b4a949f6b3c2bc0c9da8fbd5fa6fb","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-05-16T13:28:10Z","title_canon_sha256":"1a79e0097dbddfff578f3bb540726624884ec068c6208bf67481f2627bb5eeb5"},"schema_version":"1.0","source":{"id":"2405.10084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10084","created_at":"2026-07-05T08:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10084v1","created_at":"2026-07-05T08:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10084","created_at":"2026-07-05T08:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"WMXZ4LUAIGZN","created_at":"2026-07-05T08:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"WMXZ4LUAIGZN6GS4","created_at":"2026-07-05T08:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"WMXZ4LUA","created_at":"2026-07-05T08:19:52Z"}],"graph_snapshots":[{"event_id":"sha256:137192a827d9d6161e99673f79ca78a2bcd58971ed3fea02c427994852858721","target":"graph","created_at":"2026-07-05T08:19:52Z","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/2405.10084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Learning-to-match (LTM) framework proves to be an effective inverse optimal transport approach for learning the underlying ground metric between two sources of data, facilitating subsequent matching. However, the conventional LTM framework faces scalability challenges, necessitating the use of the entire dataset each time the parameters of the ground metric are updated. In adapting LTM to the deep learning context, we introduce the mini-batch Learning-to-match (m-LTM) framework for audio-text retrieval problems. This framework leverages mini-batch subsampling and Mahalanobis-enhanced famil","authors_text":"Dinh Phung, Khai Nguyen, Lizhen Qu, Manh Luong, Nhat Ho, Reza Haf","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-05-16T13:28:10Z","title":"Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10084","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:e39877ebd0d9a05872d22ff40602ea6853c74966fa4a98474da9eced606e6781","target":"record","created_at":"2026-07-05T08:19:52Z","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":"78f607e2fdca7f85c0776a9b468a0b99399b4a949f6b3c2bc0c9da8fbd5fa6fb","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-05-16T13:28:10Z","title_canon_sha256":"1a79e0097dbddfff578f3bb540726624884ec068c6208bf67481f2627bb5eeb5"},"schema_version":"1.0","source":{"id":"2405.10084","kind":"arxiv","version":1}},"canonical_sha256":"b32f9e2e8041b2df1a5c3abf625de28ece2a569a107bc52fa19430b6a6fa2057","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b32f9e2e8041b2df1a5c3abf625de28ece2a569a107bc52fa19430b6a6fa2057","first_computed_at":"2026-07-05T08:19:52.519192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:52.519192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hDff+SKKcJ7h+3QCPC9pK+70lyQ49YQKWvrc+epZBr6kO7kAsWKwfEwoQrA1XocvnPYw80mip0hvpx1sFaF0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:52.519738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e39877ebd0d9a05872d22ff40602ea6853c74966fa4a98474da9eced606e6781","sha256:137192a827d9d6161e99673f79ca78a2bcd58971ed3fea02c427994852858721"],"state_sha256":"8d3fa083dbac3b3d8ec24571b1af13038761f11cf8bf235b698ce3957ed58ab7"}