{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:52RNN4MISEWCUKTOJOJ6K5NXRF","short_pith_number":"pith:52RNN4MI","canonical_record":{"source":{"id":"1804.03052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-09T15:15:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"782ddd9ef02c41c9a751785ddd4b958d62c072998781ea800528d803de41104f","abstract_canon_sha256":"7f882f575e6b6c2570101620cbe7a85b6d0b5052615166cf12d24396a34ace0e"},"schema_version":"1.0"},"canonical_sha256":"eea2d6f188912c2a2a6e4b93e575b78966f3eab17ecef4cfe06d4a689df08828","source":{"kind":"arxiv","id":"1804.03052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03052","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03052v1","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03052","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"52RNN4MISEWC","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"52RNN4MISEWCUKTO","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"52RNN4MI","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:52RNN4MISEWCUKTOJOJ6K5NXRF","target":"record","payload":{"canonical_record":{"source":{"id":"1804.03052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-09T15:15:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"782ddd9ef02c41c9a751785ddd4b958d62c072998781ea800528d803de41104f","abstract_canon_sha256":"7f882f575e6b6c2570101620cbe7a85b6d0b5052615166cf12d24396a34ace0e"},"schema_version":"1.0"},"canonical_sha256":"eea2d6f188912c2a2a6e4b93e575b78966f3eab17ecef4cfe06d4a689df08828","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:57.517374Z","signature_b64":"5tsfYzmRjQ5qdUHrzmVDMdIuzoWxewLIf+ggb506p5f5ukE0QVqi3f06hZ5qLSGDhrFNCj+15a9Y6SFUCwn/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eea2d6f188912c2a2a6e4b93e575b78966f3eab17ecef4cfe06d4a689df08828","last_reissued_at":"2026-05-18T00:18:57.516628Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:57.516628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.03052","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":"2026-05-18T00:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nNY5FvEk3GcPyfRcCxqhvqI/RHbgx4gTU7j47todsZAGNus+A+OTpSGHVjSCrAamQKUFNsoPfqt7FnTGlmdBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T15:01:12.942023Z"},"content_sha256":"3ee0e7dcb0b6254011a328cddd90569b28c9b9a30f052c75d340e364375771d0","schema_version":"1.0","event_id":"sha256:3ee0e7dcb0b6254011a328cddd90569b28c9b9a30f052c75d340e364375771d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:52RNN4MISEWCUKTOJOJ6K5NXRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision as an Interlingua: Learning Multilingual Semantic Embeddings of Untranscribed Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Harwath, Galen Chuang, James Glass","submitted_at":"2018-04-09T15:15:37Z","abstract_excerpt":"In this paper, we explore the learning of neural network embeddings for natural images and speech waveforms describing the content of those images. These embeddings are learned directly from the waveforms without the use of linguistic transcriptions or conventional speech recognition technology. While prior work has investigated this setting in the monolingual case using English speech data, this work represents the first effort to apply these techniques to languages beyond English. Using spoken captions collected in English and Hindi, we show that the same model architecture can be successful"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03052","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":""},"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":"2026-05-18T00:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6s9I64msMoNXrtxOAs63SypGbNGYHtq2IPdc5zjDqaMwAiDe11DRG/cVQSTM5CF4LBh76bEwgdj2uy4buk82BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T15:01:12.942519Z"},"content_sha256":"c1271df4995f56cbec686121422ffab82faa3952140324a107f3a29dbb6507ec","schema_version":"1.0","event_id":"sha256:c1271df4995f56cbec686121422ffab82faa3952140324a107f3a29dbb6507ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/52RNN4MISEWCUKTOJOJ6K5NXRF/bundle.json","state_url":"https://pith.science/pith/52RNN4MISEWCUKTOJOJ6K5NXRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/52RNN4MISEWCUKTOJOJ6K5NXRF/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":"2026-05-31T15:01:12Z","links":{"resolver":"https://pith.science/pith/52RNN4MISEWCUKTOJOJ6K5NXRF","bundle":"https://pith.science/pith/52RNN4MISEWCUKTOJOJ6K5NXRF/bundle.json","state":"https://pith.science/pith/52RNN4MISEWCUKTOJOJ6K5NXRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/52RNN4MISEWCUKTOJOJ6K5NXRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:52RNN4MISEWCUKTOJOJ6K5NXRF","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":"7f882f575e6b6c2570101620cbe7a85b6d0b5052615166cf12d24396a34ace0e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-09T15:15:37Z","title_canon_sha256":"782ddd9ef02c41c9a751785ddd4b958d62c072998781ea800528d803de41104f"},"schema_version":"1.0","source":{"id":"1804.03052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03052","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03052v1","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03052","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"52RNN4MISEWC","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"52RNN4MISEWCUKTO","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"52RNN4MI","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:c1271df4995f56cbec686121422ffab82faa3952140324a107f3a29dbb6507ec","target":"graph","created_at":"2026-05-18T00:18:57Z","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"},"paper":{"abstract_excerpt":"In this paper, we explore the learning of neural network embeddings for natural images and speech waveforms describing the content of those images. These embeddings are learned directly from the waveforms without the use of linguistic transcriptions or conventional speech recognition technology. While prior work has investigated this setting in the monolingual case using English speech data, this work represents the first effort to apply these techniques to languages beyond English. Using spoken captions collected in English and Hindi, we show that the same model architecture can be successful","authors_text":"David Harwath, Galen Chuang, James Glass","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-09T15:15:37Z","title":"Vision as an Interlingua: Learning Multilingual Semantic Embeddings of Untranscribed Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03052","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":"sha256:3ee0e7dcb0b6254011a328cddd90569b28c9b9a30f052c75d340e364375771d0","target":"record","created_at":"2026-05-18T00:18:57Z","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":"7f882f575e6b6c2570101620cbe7a85b6d0b5052615166cf12d24396a34ace0e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-09T15:15:37Z","title_canon_sha256":"782ddd9ef02c41c9a751785ddd4b958d62c072998781ea800528d803de41104f"},"schema_version":"1.0","source":{"id":"1804.03052","kind":"arxiv","version":1}},"canonical_sha256":"eea2d6f188912c2a2a6e4b93e575b78966f3eab17ecef4cfe06d4a689df08828","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eea2d6f188912c2a2a6e4b93e575b78966f3eab17ecef4cfe06d4a689df08828","first_computed_at":"2026-05-18T00:18:57.516628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:57.516628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5tsfYzmRjQ5qdUHrzmVDMdIuzoWxewLIf+ggb506p5f5ukE0QVqi3f06hZ5qLSGDhrFNCj+15a9Y6SFUCwn/Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:57.517374Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.03052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ee0e7dcb0b6254011a328cddd90569b28c9b9a30f052c75d340e364375771d0","sha256:c1271df4995f56cbec686121422ffab82faa3952140324a107f3a29dbb6507ec"],"state_sha256":"8b7f66b81b81de4c5dc0bae5fa0003627aa1e5d3421ab9415525328011478943"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tylT52Z/aUi5kqcB8xJroPDPl4PvqBk/yOSi4A3ytGhizV8+CEGcOLULCiObX44Iy5Y/W24JEQNUwWgQfYOZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T15:01:12.946533Z","bundle_sha256":"4a967afb53ad9eb746c349418ca9e6ead4ff66275070bf89e4619ed01e645623"}}