{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DHKNOVS4L2ND77ZCGBNO22CBO2","short_pith_number":"pith:DHKNOVS4","schema_version":"1.0","canonical_sha256":"19d4d7565c5e9a3fff22305aed684176aef9ce7882ed16ccd0d765bb474d5cf5","source":{"kind":"arxiv","id":"2505.14562","version":1},"attestation_state":"computed","paper":{"title":"Representation Learning for Semantic Alignment of Language, Audio, and Visual Modalities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Irene Mart\\'in-Morat\\'o, Parthasaarathy Sudarsanam, Tuomas Virtanen","submitted_at":"2025-05-20T16:21:27Z","abstract_excerpt":"This paper proposes a single-stage training approach that semantically aligns three modalities - audio, visual, and text using a contrastive learning framework. Contrastive training has gained prominence for multimodal alignment, utilizing large-scale unlabeled data to learn shared representations. Existing deep learning approach for trimodal alignment involves two-stages, that separately align visual-text and audio-text modalities. This approach suffers from mismatched data distributions, resulting in suboptimal alignment. Leveraging the AVCaps dataset, which provides audio, visual and audio-"},"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":"2505.14562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T16:21:27Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"dba8b05db7750d98944eaf5ea09b73c6e3a9330574ed98e7a999c1f3663f2116","abstract_canon_sha256":"447cf2e2892c19ffd6cc0c7778393f296a9b544cfd1a12cbe2f56326e2d3d2c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:15.538026Z","signature_b64":"AUcma/A93W/vvRmuZU9sAC09f1zjgMPsyaTQkU6HgjyDnP8yv5XwFkKaVKwmGfLXto0qq8gntCXmkSQme7mrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d4d7565c5e9a3fff22305aed684176aef9ce7882ed16ccd0d765bb474d5cf5","last_reissued_at":"2026-07-05T11:06:15.537503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:15.537503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation Learning for Semantic Alignment of Language, Audio, and Visual Modalities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Irene Mart\\'in-Morat\\'o, Parthasaarathy Sudarsanam, Tuomas Virtanen","submitted_at":"2025-05-20T16:21:27Z","abstract_excerpt":"This paper proposes a single-stage training approach that semantically aligns three modalities - audio, visual, and text using a contrastive learning framework. Contrastive training has gained prominence for multimodal alignment, utilizing large-scale unlabeled data to learn shared representations. Existing deep learning approach for trimodal alignment involves two-stages, that separately align visual-text and audio-text modalities. This approach suffers from mismatched data distributions, resulting in suboptimal alignment. Leveraging the AVCaps dataset, which provides audio, visual and audio-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14562","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/2505.14562/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":"2505.14562","created_at":"2026-07-05T11:06:15.537572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14562v1","created_at":"2026-07-05T11:06:15.537572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14562","created_at":"2026-07-05T11:06:15.537572+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHKNOVS4L2ND","created_at":"2026-07-05T11:06:15.537572+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHKNOVS4L2ND77ZC","created_at":"2026-07-05T11:06:15.537572+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHKNOVS4","created_at":"2026-07-05T11:06:15.537572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21080","citing_title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2","json":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2.json","graph_json":"https://pith.science/api/pith-number/DHKNOVS4L2ND77ZCGBNO22CBO2/graph.json","events_json":"https://pith.science/api/pith-number/DHKNOVS4L2ND77ZCGBNO22CBO2/events.json","paper":"https://pith.science/paper/DHKNOVS4"},"agent_actions":{"view_html":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2","download_json":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2.json","view_paper":"https://pith.science/paper/DHKNOVS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14562&json=true","fetch_graph":"https://pith.science/api/pith-number/DHKNOVS4L2ND77ZCGBNO22CBO2/graph.json","fetch_events":"https://pith.science/api/pith-number/DHKNOVS4L2ND77ZCGBNO22CBO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2/action/storage_attestation","attest_author":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2/action/author_attestation","sign_citation":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2/action/citation_signature","submit_replication":"https://pith.science/pith/DHKNOVS4L2ND77ZCGBNO22CBO2/action/replication_record"}},"created_at":"2026-07-05T11:06:15.537572+00:00","updated_at":"2026-07-05T11:06:15.537572+00:00"}