{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LYT4LBU2SNZGTPEPOJD5HNCTZ4","short_pith_number":"pith:LYT4LBU2","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"},"canonical_sha256":"5e27c5869a937269bc8f7247d3b453cf0a376ec43e14f5a548842a541a46f4bd","source":{"kind":"arxiv","id":"2507.22008","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22008","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22008v1","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22008","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"LYT4LBU2SNZG","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_16","alias_value":"LYT4LBU2SNZGTPEP","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_8","alias_value":"LYT4LBU2","created_at":"2026-07-05T11:45:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LYT4LBU2SNZGTPEPOJD5HNCTZ4","target":"record","payload":{"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"},"canonical_sha256":"5e27c5869a937269bc8f7247d3b453cf0a376ec43e14f5a548842a541a46f4bd","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"},"source_kind":"arxiv","source_id":"2507.22008","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":"2026-07-05T11:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QnNPqrNB+5bo6dOtfsbOqdZJyJ8AWyU2yjuPiKvI72QrZIzUW8hQOGP26BJTWH9J6fDumv2vX943c5i+yU+pCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T09:01:38.893726Z"},"content_sha256":"c936856ad2b407e9c55b238c51b23e6a129247b64b48fb39f945681b81519d50","schema_version":"1.0","event_id":"sha256:c936856ad2b407e9c55b238c51b23e6a129247b64b48fb39f945681b81519d50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LYT4LBU2SNZGTPEPOJD5HNCTZ4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g8gOPSxH2WqRrvkHJkfbM6p1zCQ1dmKh+DK6Vgmyl6XsaeHiWS/cDO/z6ilSfBIbc49OZ0OOtXFJZ3MClKj/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T09:01:38.894786Z"},"content_sha256":"980cba9ae8bd9b8e8846c799be5129514b1c3ed5facbb59611a1a75993f96b00","schema_version":"1.0","event_id":"sha256:980cba9ae8bd9b8e8846c799be5129514b1c3ed5facbb59611a1a75993f96b00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/bundle.json","state_url":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/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":"2026-08-12T09:01:38Z","links":{"resolver":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4","bundle":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/bundle.json","state":"https://pith.science/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYT4LBU2SNZGTPEPOJD5HNCTZ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LYT4LBU2SNZGTPEPOJD5HNCTZ4","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":"49aeaf255570c285a5fa271051e9efb172e3ae8536bc2e83ea5954581b9cb9bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T16:58:52Z","title_canon_sha256":"48ad2f63cf37bd1ce5d8621b442c0d7a98d89bde09990bcc575c69d014b61424"},"schema_version":"1.0","source":{"id":"2507.22008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22008","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22008v1","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22008","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"LYT4LBU2SNZG","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_16","alias_value":"LYT4LBU2SNZGTPEP","created_at":"2026-07-05T11:45:11Z"},{"alias_kind":"pith_short_8","alias_value":"LYT4LBU2","created_at":"2026-07-05T11:45:11Z"}],"graph_snapshots":[{"event_id":"sha256:980cba9ae8bd9b8e8846c799be5129514b1c3ed5facbb59611a1a75993f96b00","target":"graph","created_at":"2026-07-05T11:45:11Z","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/2507.22008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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) ","authors_text":"Sajay Raj","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T16:58:52Z","title":"VeS: Teaching Pixels to Listen Without Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22008","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:c936856ad2b407e9c55b238c51b23e6a129247b64b48fb39f945681b81519d50","target":"record","created_at":"2026-07-05T11:45:11Z","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":"49aeaf255570c285a5fa271051e9efb172e3ae8536bc2e83ea5954581b9cb9bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T16:58:52Z","title_canon_sha256":"48ad2f63cf37bd1ce5d8621b442c0d7a98d89bde09990bcc575c69d014b61424"},"schema_version":"1.0","source":{"id":"2507.22008","kind":"arxiv","version":1}},"canonical_sha256":"5e27c5869a937269bc8f7247d3b453cf0a376ec43e14f5a548842a541a46f4bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e27c5869a937269bc8f7247d3b453cf0a376ec43e14f5a548842a541a46f4bd","first_computed_at":"2026-07-05T11:45:11.332757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:11.332757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6m0ZDUh5NoFP+3bp9SeOPvzPGBi/ASzCDYro24QpSCHaeiK5mGwSQwjg3Qx8yna9XbuJSy3xdSNvMsBEZTeqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:11.333266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c936856ad2b407e9c55b238c51b23e6a129247b64b48fb39f945681b81519d50","sha256:980cba9ae8bd9b8e8846c799be5129514b1c3ed5facbb59611a1a75993f96b00"],"state_sha256":"54299505bbd67357db0d6653c4169fe76c26fb54360800cf0a8c34ad42a1abca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HHC2hUVS2ugHGx+0/V6U8L4QGvDhYRJnIMyWORuuv8GEm4ZoQqe2Zno7/fwd2UJWyA2bloyG1KDgEvda7kI4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T09:01:38.902057Z","bundle_sha256":"294e7dd821f304184e5d8e754f937d6f1fab7450a8fa86f63b526055c27a02a7"}}