{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LYT4LBU2SNZGTPEPOJD5HNCTZ4","short_pith_number":"pith:LYT4LBU2","schema_version":"1.0","canonical_sha256":"5e27c5869a937269bc8f7247d3b453cf0a376ec43e14f5a548842a541a46f4bd","source":{"kind":"arxiv","id":"2507.22008","version":1},"attestation_state":"computed","paper":{"title":"VeS: Teaching Pixels to Listen Without Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Sajay Raj","submitted_at":"2025-07-29T16:58:52Z","abstract_excerpt":"Recent dense audio-visual (AV) models achieve impressive retrieval and emergent localization, but almost all evidence comes from English-centric, caption-rich web video. It is unclear whether these objectives survive in low-resource, code-switched, and noisy multilingual settings that typify developing regions. We show they do**-**and that the choice of aggregation function becomes even more critical. Using a multilingual subset of Project Vaani spanning dozens of Indian languages and dialectal variants, we compare three contrastive objectives: (i) a global mean-pooled loss (CLIP-style), (ii) "},"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":"2507.22008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T16:58:52Z","cross_cats_sorted":[],"title_canon_sha256":"48ad2f63cf37bd1ce5d8621b442c0d7a98d89bde09990bcc575c69d014b61424","abstract_canon_sha256":"49aeaf255570c285a5fa271051e9efb172e3ae8536bc2e83ea5954581b9cb9bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:11.333266Z","signature_b64":"6m0ZDUh5NoFP+3bp9SeOPvzPGBi/ASzCDYro24QpSCHaeiK5mGwSQwjg3Qx8yna9XbuJSy3xdSNvMsBEZTeqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e27c5869a937269bc8f7247d3b453cf0a376ec43e14f5a548842a541a46f4bd","last_reissued_at":"2026-07-05T11:45:11.332757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:11.332757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VeS: Teaching Pixels to Listen Without Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Sajay Raj","submitted_at":"2025-07-29T16:58:52Z","abstract_excerpt":"Recent dense audio-visual (AV) models achieve impressive retrieval and emergent localization, but almost all evidence comes from English-centric, caption-rich web video. It is unclear whether these objectives survive in low-resource, code-switched, and noisy multilingual settings that typify developing regions. We show they do**-**and that the choice of aggregation function becomes even more critical. Using a multilingual subset of Project Vaani spanning dozens of Indian languages and dialectal variants, we compare three contrastive objectives: (i) a global mean-pooled loss (CLIP-style), (ii) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22008","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/2507.22008/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":"2507.22008","created_at":"2026-07-05T11:45:11.332827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22008v1","created_at":"2026-07-05T11:45:11.332827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22008","created_at":"2026-07-05T11:45:11.332827+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYT4LBU2SNZG","created_at":"2026-07-05T11:45:11.332827+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYT4LBU2SNZGTPEP","created_at":"2026-07-05T11:45:11.332827+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYT4LBU2","created_at":"2026-07-05T11:45:11.332827+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/LYT4LBU2SNZGTPEPOJD5HNCTZ4","json":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4.json","graph_json":"https://pith.science/api/pith-number/LYT4LBU2SNZGTPEPOJD5HNCTZ4/graph.json","events_json":"https://pith.science/api/pith-number/LYT4LBU2SNZGTPEPOJD5HNCTZ4/events.json","paper":"https://pith.science/paper/LYT4LBU2"},"agent_actions":{"view_html":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4","download_json":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4.json","view_paper":"https://pith.science/paper/LYT4LBU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22008&json=true","fetch_graph":"https://pith.science/api/pith-number/LYT4LBU2SNZGTPEPOJD5HNCTZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/LYT4LBU2SNZGTPEPOJD5HNCTZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/action/storage_attestation","attest_author":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/action/author_attestation","sign_citation":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/action/citation_signature","submit_replication":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/action/replication_record"}},"created_at":"2026-07-05T11:45:11.332827+00:00","updated_at":"2026-07-05T11:45:11.332827+00:00"}