{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WD3CQZTMPL6PATKX4SKAKI6XR4","short_pith_number":"pith:WD3CQZTM","schema_version":"1.0","canonical_sha256":"b0f628666c7afcf04d57e4940523d78f3f6d5548550a404d617d4890e579fb6f","source":{"kind":"arxiv","id":"2606.20418","version":1},"attestation_state":"computed","paper":{"title":"MixProLAP: Mixture-Induced Uncertainty Modeling for Probabilistic Language-Audio Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Jaesong Lee, Soo-Whan Chung, Yu Nakagome","submitted_at":"2026-06-18T16:02:39Z","abstract_excerpt":"Acoustic environments often contain multiple overlapping sound events, and the same acoustic scene can be described using diverse textual expressions, making audio-text alignment inherently ambiguous. This paper proposes a probabilistic audio-language pretraining framework to model many-to-many correspondence ambiguity in audio-text alignment. Unlike conventional contrastive methods that learn deterministic point embeddings, our approach represents each modality as a distribution and learns uncertainty-aware cross-modal alignment. Rather than relying on masking-based uncertainty simulation, we"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.20418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-18T16:02:39Z","cross_cats_sorted":[],"title_canon_sha256":"fbbe8bd7e5689394c664d29730db2ca1f0202fad796bcfac533a268c23d96dd5","abstract_canon_sha256":"d16adf6efd3288a849878f329d2ba9089998085488478e6a0c6c7009e5ba9b57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:11.980753Z","signature_b64":"atzdD4USrtM9Cj70Yq9W4XoF32vJs6hlqPu9Gt50sruc6lhpv3E74yx7KLSnHHWQl70q3eWD3N5ACNtmCKjpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0f628666c7afcf04d57e4940523d78f3f6d5548550a404d617d4890e579fb6f","last_reissued_at":"2026-06-19T16:13:11.980377Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:11.980377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixProLAP: Mixture-Induced Uncertainty Modeling for Probabilistic Language-Audio Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Jaesong Lee, Soo-Whan Chung, Yu Nakagome","submitted_at":"2026-06-18T16:02:39Z","abstract_excerpt":"Acoustic environments often contain multiple overlapping sound events, and the same acoustic scene can be described using diverse textual expressions, making audio-text alignment inherently ambiguous. This paper proposes a probabilistic audio-language pretraining framework to model many-to-many correspondence ambiguity in audio-text alignment. Unlike conventional contrastive methods that learn deterministic point embeddings, our approach represents each modality as a distribution and learns uncertainty-aware cross-modal alignment. Rather than relying on masking-based uncertainty simulation, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20418","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/2606.20418/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.20418","created_at":"2026-06-19T16:13:11.980438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20418v1","created_at":"2026-06-19T16:13:11.980438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20418","created_at":"2026-06-19T16:13:11.980438+00:00"},{"alias_kind":"pith_short_12","alias_value":"WD3CQZTMPL6P","created_at":"2026-06-19T16:13:11.980438+00:00"},{"alias_kind":"pith_short_16","alias_value":"WD3CQZTMPL6PATKX","created_at":"2026-06-19T16:13:11.980438+00:00"},{"alias_kind":"pith_short_8","alias_value":"WD3CQZTM","created_at":"2026-06-19T16:13:11.980438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4","json":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4.json","graph_json":"https://pith.science/api/pith-number/WD3CQZTMPL6PATKX4SKAKI6XR4/graph.json","events_json":"https://pith.science/api/pith-number/WD3CQZTMPL6PATKX4SKAKI6XR4/events.json","paper":"https://pith.science/paper/WD3CQZTM"},"agent_actions":{"view_html":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4","download_json":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4.json","view_paper":"https://pith.science/paper/WD3CQZTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20418&json=true","fetch_graph":"https://pith.science/api/pith-number/WD3CQZTMPL6PATKX4SKAKI6XR4/graph.json","fetch_events":"https://pith.science/api/pith-number/WD3CQZTMPL6PATKX4SKAKI6XR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4/action/storage_attestation","attest_author":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4/action/author_attestation","sign_citation":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4/action/citation_signature","submit_replication":"https://pith.science/pith/WD3CQZTMPL6PATKX4SKAKI6XR4/action/replication_record"}},"created_at":"2026-06-19T16:13:11.980438+00:00","updated_at":"2026-06-19T16:13:11.980438+00:00"}