{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2SMK63CLIMMJVHTJ6PAXLZNYN2","short_pith_number":"pith:2SMK63CL","canonical_record":{"source":{"id":"2409.02865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T17:59:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a729b691a9d846fd6bb5c84dea2684188528e3510148c33970e8ec2706b235bb","abstract_canon_sha256":"21059e09068a1811997c70b8680720ff3e8679b7f37f1aa34f3df3943d8758f1"},"schema_version":"1.0"},"canonical_sha256":"d498af6c4b43189a9e69f3c175e5b86ea1c51089ee950d905acdf611b4228133","source":{"kind":"arxiv","id":"2409.02865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02865","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02865v1","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02865","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"2SMK63CLIMMJ","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"2SMK63CLIMMJVHTJ","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"2SMK63CL","created_at":"2026-07-05T09:03:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2SMK63CLIMMJVHTJ6PAXLZNYN2","target":"record","payload":{"canonical_record":{"source":{"id":"2409.02865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T17:59:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a729b691a9d846fd6bb5c84dea2684188528e3510148c33970e8ec2706b235bb","abstract_canon_sha256":"21059e09068a1811997c70b8680720ff3e8679b7f37f1aa34f3df3943d8758f1"},"schema_version":"1.0"},"canonical_sha256":"d498af6c4b43189a9e69f3c175e5b86ea1c51089ee950d905acdf611b4228133","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:11.467894Z","signature_b64":"Yp/CHbkA92q4FJfD7UEigTOTygtDXT+vGrAJUgtz0b1aMxDK3pMCgF+bgpB+V6nLcBhKQdyR0Ujdzdztz6qlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d498af6c4b43189a9e69f3c175e5b86ea1c51089ee950d905acdf611b4228133","last_reissued_at":"2026-07-05T09:03:11.467478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:11.467478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.02865","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":"2026-07-05T09:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbnwjM1bz6l6Y+K4sFaTv9q9TMcsBLPL5dJ+XjOjiKs5r+pxCk8B4zPccoBgM86MCwZv9f55rk9J4ViEDiXRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:10.794818Z"},"content_sha256":"f3363423bf50352de64aa65f50b8dc60fec6b1c6b520513cb0d36421e21ef29e","schema_version":"1.0","event_id":"sha256:f3363423bf50352de64aa65f50b8dc60fec6b1c6b520513cb0d36421e21ef29e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2SMK63CLIMMJVHTJ6PAXLZNYN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visually Grounded Speech Models for Low-resource Languages and Cognitive Modelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Leanne Nortje","submitted_at":"2024-09-03T17:59:50Z","abstract_excerpt":"This dissertation examines visually grounded speech (VGS) models that learn from unlabelled speech paired with images. It focuses on applications for low-resource languages and understanding human language acquisition. We introduce a task called visually prompted keyword localisation to detect and localise keywords in speech using images. We demonstrate the effectiveness of VGS models in few-shot learning scenarios for low-resource languages like Yoruba. Additionally, we examine the mutual exclusivity bias in VGS models. Our monolingual VGS model exhibits this bias, but we found that multiling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02865","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/2409.02865/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":"2026-07-05T09:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"99d+HXTsot6k8lAKYmA4HixxCXyzWT85OXFZ5FvDPjOTNH4Ht7Iy15EK6MWjxxxj4amskQUrCoUCjX7Wx2ZCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:10.795314Z"},"content_sha256":"d2f40da71e584ca3556fbe39cdc828bf311a46e67d8b2790a662f0337913f2fb","schema_version":"1.0","event_id":"sha256:d2f40da71e584ca3556fbe39cdc828bf311a46e67d8b2790a662f0337913f2fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2SMK63CLIMMJVHTJ6PAXLZNYN2/bundle.json","state_url":"https://pith.science/pith/2SMK63CLIMMJVHTJ6PAXLZNYN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2SMK63CLIMMJVHTJ6PAXLZNYN2/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":"2026-08-08T10:22:10Z","links":{"resolver":"https://pith.science/pith/2SMK63CLIMMJVHTJ6PAXLZNYN2","bundle":"https://pith.science/pith/2SMK63CLIMMJVHTJ6PAXLZNYN2/bundle.json","state":"https://pith.science/pith/2SMK63CLIMMJVHTJ6PAXLZNYN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2SMK63CLIMMJVHTJ6PAXLZNYN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2SMK63CLIMMJVHTJ6PAXLZNYN2","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":"21059e09068a1811997c70b8680720ff3e8679b7f37f1aa34f3df3943d8758f1","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T17:59:50Z","title_canon_sha256":"a729b691a9d846fd6bb5c84dea2684188528e3510148c33970e8ec2706b235bb"},"schema_version":"1.0","source":{"id":"2409.02865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02865","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02865v1","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02865","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"2SMK63CLIMMJ","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"2SMK63CLIMMJVHTJ","created_at":"2026-07-05T09:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"2SMK63CL","created_at":"2026-07-05T09:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:d2f40da71e584ca3556fbe39cdc828bf311a46e67d8b2790a662f0337913f2fb","target":"graph","created_at":"2026-07-05T09:03:11Z","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/2409.02865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This dissertation examines visually grounded speech (VGS) models that learn from unlabelled speech paired with images. It focuses on applications for low-resource languages and understanding human language acquisition. We introduce a task called visually prompted keyword localisation to detect and localise keywords in speech using images. We demonstrate the effectiveness of VGS models in few-shot learning scenarios for low-resource languages like Yoruba. Additionally, we examine the mutual exclusivity bias in VGS models. Our monolingual VGS model exhibits this bias, but we found that multiling","authors_text":"Leanne Nortje","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T17:59:50Z","title":"Visually Grounded Speech Models for Low-resource Languages and Cognitive Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02865","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:f3363423bf50352de64aa65f50b8dc60fec6b1c6b520513cb0d36421e21ef29e","target":"record","created_at":"2026-07-05T09:03:11Z","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":"21059e09068a1811997c70b8680720ff3e8679b7f37f1aa34f3df3943d8758f1","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T17:59:50Z","title_canon_sha256":"a729b691a9d846fd6bb5c84dea2684188528e3510148c33970e8ec2706b235bb"},"schema_version":"1.0","source":{"id":"2409.02865","kind":"arxiv","version":1}},"canonical_sha256":"d498af6c4b43189a9e69f3c175e5b86ea1c51089ee950d905acdf611b4228133","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d498af6c4b43189a9e69f3c175e5b86ea1c51089ee950d905acdf611b4228133","first_computed_at":"2026-07-05T09:03:11.467478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:11.467478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yp/CHbkA92q4FJfD7UEigTOTygtDXT+vGrAJUgtz0b1aMxDK3pMCgF+bgpB+V6nLcBhKQdyR0Ujdzdztz6qlDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:11.467894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3363423bf50352de64aa65f50b8dc60fec6b1c6b520513cb0d36421e21ef29e","sha256:d2f40da71e584ca3556fbe39cdc828bf311a46e67d8b2790a662f0337913f2fb"],"state_sha256":"ffca0b5aff2df67f9bc6492f8939aeac6102774f46e2fb306abbabf22a008a96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJzPBN0i2OQRWVdADE/5UMfDGr3wHzZRkxH4je3dyqKJoDmsRfYT7CwLGAkB8hSBxj5ED3TsIb5y/4x4g94ECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:22:10.799376Z","bundle_sha256":"948a43e81e1c60a7a7c293c72196d5a3c04385805cbb5a3b309d5d2cdf4115f5"}}