{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZXKVDULX74ATIVKV3BXU3M2PNM","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":"a044a6ed82cdb267458333bf5cab01b6ddb2a9ed60ff290150d5d4418406e2aa","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-19T02:50:23Z","title_canon_sha256":"4f2918a62bc192628be4fca1365cb05883cf807afc91498ab93101b2dff9f67a"},"schema_version":"1.0","source":{"id":"1909.08782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.08782","created_at":"2026-07-05T00:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"1909.08782v1","created_at":"2026-07-05T00:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.08782","created_at":"2026-07-05T00:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZXKVDULX74AT","created_at":"2026-07-05T00:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZXKVDULX74ATIVKV","created_at":"2026-07-05T00:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZXKVDULX","created_at":"2026-07-05T00:05:37Z"}],"graph_snapshots":[{"event_id":"sha256:199aca892225b3248a99856dad15e0f4e58ebe0565c802546e0cc80c8215cdde","target":"graph","created_at":"2026-07-05T00:05:37Z","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/1909.08782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Systems that can associate images with their spoken audio captions are an important step towards visually grounded language learning. We describe a scalable method to automatically generate diverse audio for image captioning datasets. This supports pretraining deep networks for encoding both audio and images, which we do via a dual encoder that learns to align latent representations from both modalities. We show that a masked margin softmax loss for such models is superior to the standard triplet loss. We fine-tune these models on the Flickr8k Audio Captions Corpus and obtain state-of-the-art ","authors_text":"Gabriel Ilharco, Jason Baldridge, Yuan Zhang","cross_cats":["cs.CL","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-19T02:50:23Z","title":"Large-scale representation learning from visually grounded untranscribed speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.08782","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":"sha256:525bb4956fd9f4ac84f8a054bc5e1c804c1d51e3190c13fb807a2352cb5539dc","target":"record","created_at":"2026-07-05T00:05:37Z","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":"a044a6ed82cdb267458333bf5cab01b6ddb2a9ed60ff290150d5d4418406e2aa","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-19T02:50:23Z","title_canon_sha256":"4f2918a62bc192628be4fca1365cb05883cf807afc91498ab93101b2dff9f67a"},"schema_version":"1.0","source":{"id":"1909.08782","kind":"arxiv","version":1}},"canonical_sha256":"cdd551d177ff01345555d86f4db34f6b0c1e3b12aae1ec2789117e4f7e8aeaeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdd551d177ff01345555d86f4db34f6b0c1e3b12aae1ec2789117e4f7e8aeaeb","first_computed_at":"2026-07-05T00:05:37.616119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:05:37.616119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HNAmjtcb6osPAVHP3CR4m5Kqvw8x5gVfTDCx54mGccfn4blS45nTb/a+ZFuzd1xC1AhMKbQcwhwPjwv0gGtlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:05:37.616587Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.08782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:525bb4956fd9f4ac84f8a054bc5e1c804c1d51e3190c13fb807a2352cb5539dc","sha256:199aca892225b3248a99856dad15e0f4e58ebe0565c802546e0cc80c8215cdde"],"state_sha256":"f48f779f3cbce1254de87b2ce9f06a16eb9d7f314e10cab4f16f418233a721da"}