{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZXKVDULX74ATIVKV3BXU3M2PNM","short_pith_number":"pith:ZXKVDULX","canonical_record":{"source":{"id":"1909.08782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-19T02:50:23Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"4f2918a62bc192628be4fca1365cb05883cf807afc91498ab93101b2dff9f67a","abstract_canon_sha256":"a044a6ed82cdb267458333bf5cab01b6ddb2a9ed60ff290150d5d4418406e2aa"},"schema_version":"1.0"},"canonical_sha256":"cdd551d177ff01345555d86f4db34f6b0c1e3b12aae1ec2789117e4f7e8aeaeb","source":{"kind":"arxiv","id":"1909.08782","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZXKVDULX74ATIVKV3BXU3M2PNM","target":"record","payload":{"canonical_record":{"source":{"id":"1909.08782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-19T02:50:23Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"4f2918a62bc192628be4fca1365cb05883cf807afc91498ab93101b2dff9f67a","abstract_canon_sha256":"a044a6ed82cdb267458333bf5cab01b6ddb2a9ed60ff290150d5d4418406e2aa"},"schema_version":"1.0"},"canonical_sha256":"cdd551d177ff01345555d86f4db34f6b0c1e3b12aae1ec2789117e4f7e8aeaeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:37.616587Z","signature_b64":"HNAmjtcb6osPAVHP3CR4m5Kqvw8x5gVfTDCx54mGccfn4blS45nTb/a+ZFuzd1xC1AhMKbQcwhwPjwv0gGtlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdd551d177ff01345555d86f4db34f6b0c1e3b12aae1ec2789117e4f7e8aeaeb","last_reissued_at":"2026-07-05T00:05:37.616119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:37.616119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.08782","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":"2026-07-05T00:05:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZDca/udi0GEhQbR/nK7xKsMEUf1HUCMBMUbS3gxnZJ8tPsmuonyj4ikDKFbE2DYfNSvODfOJ3l2AG5bhOa59CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:00:39.030540Z"},"content_sha256":"525bb4956fd9f4ac84f8a054bc5e1c804c1d51e3190c13fb807a2352cb5539dc","schema_version":"1.0","event_id":"sha256:525bb4956fd9f4ac84f8a054bc5e1c804c1d51e3190c13fb807a2352cb5539dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZXKVDULX74ATIVKV3BXU3M2PNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-scale representation learning from visually grounded untranscribed speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Gabriel Ilharco, Jason Baldridge, Yuan Zhang","submitted_at":"2019-09-19T02:50:23Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.08782","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/1909.08782/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":"2026-07-05T00:05:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FNOhjc+HLB8i4VSg9cHCBEiAGbI/aAENqJUZPWGL53EdcjYeDw63EcgoxG/ez8ycI14N/5mVGjZ342hCaTVTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:00:39.031634Z"},"content_sha256":"199aca892225b3248a99856dad15e0f4e58ebe0565c802546e0cc80c8215cdde","schema_version":"1.0","event_id":"sha256:199aca892225b3248a99856dad15e0f4e58ebe0565c802546e0cc80c8215cdde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZXKVDULX74ATIVKV3BXU3M2PNM/bundle.json","state_url":"https://pith.science/pith/ZXKVDULX74ATIVKV3BXU3M2PNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZXKVDULX74ATIVKV3BXU3M2PNM/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":"2026-08-12T05:00:39Z","links":{"resolver":"https://pith.science/pith/ZXKVDULX74ATIVKV3BXU3M2PNM","bundle":"https://pith.science/pith/ZXKVDULX74ATIVKV3BXU3M2PNM/bundle.json","state":"https://pith.science/pith/ZXKVDULX74ATIVKV3BXU3M2PNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZXKVDULX74ATIVKV3BXU3M2PNM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8mRjnVms1mNCnJP+L+jCYnkzVCgnMUDbQr2soCM6DL/qSMuDbu6kuKzNwRpTEH1KPPVILdr9vI7eAlQwW7UQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T05:00:39.041894Z","bundle_sha256":"fea444b17c5e6458ca71f434b51dde146098a73df6e5a53bfda27ca8e4237dc8"}}