{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7BOXSLVMWNNEKITRNRJUYY5ISH","short_pith_number":"pith:7BOXSLVM","canonical_record":{"source":{"id":"2607.28129","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T12:37:58Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"355de476b6aa033957fa4d70e9c3eb5bb2399bf4a83888bb52168a0f61d1985f","abstract_canon_sha256":"05af4919c069df65362d8627947a8671db529efd2ab2cf68705c0dd9b74bd598"},"schema_version":"1.0"},"canonical_sha256":"f85d792eacb35a4522716c534c63a891e06a96676fe11b4c6be2851ddcafe7ef","source":{"kind":"arxiv","id":"2607.28129","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28129","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28129v1","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28129","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"pith_short_12","alias_value":"7BOXSLVMWNNE","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"pith_short_16","alias_value":"7BOXSLVMWNNEKITR","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"pith_short_8","alias_value":"7BOXSLVM","created_at":"2026-07-31T01:35:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7BOXSLVMWNNEKITRNRJUYY5ISH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28129","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T12:37:58Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"355de476b6aa033957fa4d70e9c3eb5bb2399bf4a83888bb52168a0f61d1985f","abstract_canon_sha256":"05af4919c069df65362d8627947a8671db529efd2ab2cf68705c0dd9b74bd598"},"schema_version":"1.0"},"canonical_sha256":"f85d792eacb35a4522716c534c63a891e06a96676fe11b4c6be2851ddcafe7ef","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85d792eacb35a4522716c534c63a891e06a96676fe11b4c6be2851ddcafe7ef","last_reissued_at":"2026-07-31T01:35:49.980184Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:49.980184Z"},"source_kind":"arxiv","source_id":"2607.28129","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:35:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7hWVAELg4kivl6/kfNRZrQTuOKlZ+8/H/9qkJDJhHYKWfpNwL/KurTJcwTrjywRHla4uBZiMldYK62oslS8kDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T10:54:10.091008Z"},"content_sha256":"6f2351477b29c1f1ff554982cd6aa97f5fc30a1c279bd36a016f9fc2195ca0ad","schema_version":"1.0","event_id":"sha256:6f2351477b29c1f1ff554982cd6aa97f5fc30a1c279bd36a016f9fc2195ca0ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7BOXSLVMWNNEKITRNRJUYY5ISH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Face and Voice Cross-modal Association with Learning Convex Feature Embedding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Jiwoo Kang, Taewan Kim","submitted_at":"2026-07-30T12:37:58Z","abstract_excerpt":"Face-and-voice association learning is one of the most challenging tasks in deep learning. In this paper, we propose a simple but powerful cross-modal feature embedding method for the association of faces and voices. Previous work has studied cross-modal association tasks to establish the correlation between voice clips and facial images. These works have addressed cross-modal discrimination but underestimate the importance of handling heterogeneity in inter-modal features between audio and video, resulting in a lot of false positives and false negatives. To tackle the problem, the proposed me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28129","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.28129/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:35:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gea0R3GezVWcb9/FrAbcrbnGJmqmyj9HocG8j3EsDq9RNmC2QijvoKcna9rwJWSQRGNc6bWqqnl3pmFIbGPwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T10:54:10.091835Z"},"content_sha256":"7f6f19de79b1811bef8a150563e3f23b152ab4bde8c7a4b6a32ffb2286acfea1","schema_version":"1.0","event_id":"sha256:7f6f19de79b1811bef8a150563e3f23b152ab4bde8c7a4b6a32ffb2286acfea1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/bundle.json","state_url":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T10:54:10Z","links":{"resolver":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH","bundle":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/bundle.json","state":"https://pith.science/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7BOXSLVMWNNEKITRNRJUYY5ISH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7BOXSLVMWNNEKITRNRJUYY5ISH","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":"05af4919c069df65362d8627947a8671db529efd2ab2cf68705c0dd9b74bd598","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T12:37:58Z","title_canon_sha256":"355de476b6aa033957fa4d70e9c3eb5bb2399bf4a83888bb52168a0f61d1985f"},"schema_version":"1.0","source":{"id":"2607.28129","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28129","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28129v1","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28129","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"pith_short_12","alias_value":"7BOXSLVMWNNE","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"pith_short_16","alias_value":"7BOXSLVMWNNEKITR","created_at":"2026-07-31T01:35:49Z"},{"alias_kind":"pith_short_8","alias_value":"7BOXSLVM","created_at":"2026-07-31T01:35:49Z"}],"graph_snapshots":[{"event_id":"sha256:7f6f19de79b1811bef8a150563e3f23b152ab4bde8c7a4b6a32ffb2286acfea1","target":"graph","created_at":"2026-07-31T01:35:49Z","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/2607.28129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Face-and-voice association learning is one of the most challenging tasks in deep learning. In this paper, we propose a simple but powerful cross-modal feature embedding method for the association of faces and voices. Previous work has studied cross-modal association tasks to establish the correlation between voice clips and facial images. These works have addressed cross-modal discrimination but underestimate the importance of handling heterogeneity in inter-modal features between audio and video, resulting in a lot of false positives and false negatives. To tackle the problem, the proposed me","authors_text":"Jiwoo Kang, Taewan Kim","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T12:37:58Z","title":"Face and Voice Cross-modal Association with Learning Convex Feature Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28129","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":"sha256:6f2351477b29c1f1ff554982cd6aa97f5fc30a1c279bd36a016f9fc2195ca0ad","target":"record","created_at":"2026-07-31T01:35:49Z","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":"05af4919c069df65362d8627947a8671db529efd2ab2cf68705c0dd9b74bd598","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T12:37:58Z","title_canon_sha256":"355de476b6aa033957fa4d70e9c3eb5bb2399bf4a83888bb52168a0f61d1985f"},"schema_version":"1.0","source":{"id":"2607.28129","kind":"arxiv","version":1}},"canonical_sha256":"f85d792eacb35a4522716c534c63a891e06a96676fe11b4c6be2851ddcafe7ef","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f85d792eacb35a4522716c534c63a891e06a96676fe11b4c6be2851ddcafe7ef","first_computed_at":"2026-07-31T01:35:49.980184Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:35:49.980184Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28129","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f2351477b29c1f1ff554982cd6aa97f5fc30a1c279bd36a016f9fc2195ca0ad","sha256:7f6f19de79b1811bef8a150563e3f23b152ab4bde8c7a4b6a32ffb2286acfea1"],"state_sha256":"590295f4fddae9e3f104a59c5693801695d122070c790abb4ed01972b2393d21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jcb1H70kqICYdmPG2zsBWGhJbnrtlCbbVb+lut3CTGcnqw/guPKaBUi7zVzJJtnyiyJZvezKrO+rMmKwTZWCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T10:54:10.100737Z","bundle_sha256":"055e8c2445139bc790bc2ba41d9a1b8693111a27f89e507ea153e65186c9e137"}}