{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QED2UWWTITUG2O3UXKJCTT7BXY","short_pith_number":"pith:QED2UWWT","canonical_record":{"source":{"id":"1904.07078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-15T14:35:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a431aea844f9f68c60d745d5aec6b2d1b3df479f5c3fe6f55d3ef5bf9c0e6f75","abstract_canon_sha256":"8125deb60caea3508e98b620d20e7afd22b3e07471a9c70fbdb6fab9221cb434"},"schema_version":"1.0"},"canonical_sha256":"8107aa5ad344e86d3b74ba9229cfe1be3a6bbf924e7d9e57eee7ee674fa0709b","source":{"kind":"arxiv","id":"1904.07078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.07078","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"1904.07078v1","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07078","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"QED2UWWTITUG","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QED2UWWTITUG2O3U","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QED2UWWT","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QED2UWWTITUG2O3UXKJCTT7BXY","target":"record","payload":{"canonical_record":{"source":{"id":"1904.07078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-15T14:35:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a431aea844f9f68c60d745d5aec6b2d1b3df479f5c3fe6f55d3ef5bf9c0e6f75","abstract_canon_sha256":"8125deb60caea3508e98b620d20e7afd22b3e07471a9c70fbdb6fab9221cb434"},"schema_version":"1.0"},"canonical_sha256":"8107aa5ad344e86d3b74ba9229cfe1be3a6bbf924e7d9e57eee7ee674fa0709b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:35.339462Z","signature_b64":"HINCl/554FtdTSZD5XlXHzy94nGR2PY0qIUbiGVBSZKoiPZaANxuw/+ZSubG/25X7G7RQhaiQ79otBsWB1gpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8107aa5ad344e86d3b74ba9229cfe1be3a6bbf924e7d9e57eee7ee674fa0709b","last_reissued_at":"2026-05-17T23:48:35.338885Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:35.338885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.07078","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":"2026-05-17T23:48:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JvKOdiQ0gdizBWP4unH0f7a47djXFjVxob+VmHszQLruw+PJBmAJjmbtv76TG9CXgc12hXeyRrvxaIE37M7ADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:53:57.167804Z"},"content_sha256":"d15ed92631780bd52bee1a34fe6cb2c1528e3804c8d6d893fa82338251fa0b26","schema_version":"1.0","event_id":"sha256:d15ed92631780bd52bee1a34fe6cb2c1528e3804c8d6d893fa82338251fa0b26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QED2UWWTITUG2O3UXKJCTT7BXY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic query-by-example speech search using visual grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aristotelis Anastassiou, Herman Kamper, Karen Livescu","submitted_at":"2019-04-15T14:35:40Z","abstract_excerpt":"A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode retrieval. Here we consider how such models can be used for query-by-example (QbE) search, the task of retrieving utterances relevant to a given spoken query. We are particularly interested in semantic QbE, where the task is not only to retrieve utterances containing exact instances of the query, but also utterances whose meaning is relevant to the query. We f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07078","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":"2026-05-17T23:48:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J81KuzCe1ug+2T+F+bts6EZtG+MKuJBcDAHhfBJbE4wAsBsjBTcqbk2W/ZHsNXktskzgSbqBzp6KnnDw6zyvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:53:57.168526Z"},"content_sha256":"abe672b4034757365f5004a8b9da7f0e8f1c69df959dd4e7278b570b58161ced","schema_version":"1.0","event_id":"sha256:abe672b4034757365f5004a8b9da7f0e8f1c69df959dd4e7278b570b58161ced"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QED2UWWTITUG2O3UXKJCTT7BXY/bundle.json","state_url":"https://pith.science/pith/QED2UWWTITUG2O3UXKJCTT7BXY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QED2UWWTITUG2O3UXKJCTT7BXY/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":"2026-06-06T19:53:57Z","links":{"resolver":"https://pith.science/pith/QED2UWWTITUG2O3UXKJCTT7BXY","bundle":"https://pith.science/pith/QED2UWWTITUG2O3UXKJCTT7BXY/bundle.json","state":"https://pith.science/pith/QED2UWWTITUG2O3UXKJCTT7BXY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QED2UWWTITUG2O3UXKJCTT7BXY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QED2UWWTITUG2O3UXKJCTT7BXY","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":"8125deb60caea3508e98b620d20e7afd22b3e07471a9c70fbdb6fab9221cb434","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-15T14:35:40Z","title_canon_sha256":"a431aea844f9f68c60d745d5aec6b2d1b3df479f5c3fe6f55d3ef5bf9c0e6f75"},"schema_version":"1.0","source":{"id":"1904.07078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.07078","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"1904.07078v1","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07078","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"QED2UWWTITUG","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QED2UWWTITUG2O3U","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QED2UWWT","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:abe672b4034757365f5004a8b9da7f0e8f1c69df959dd4e7278b570b58161ced","target":"graph","created_at":"2026-05-17T23:48:35Z","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":"A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode retrieval. Here we consider how such models can be used for query-by-example (QbE) search, the task of retrieving utterances relevant to a given spoken query. We are particularly interested in semantic QbE, where the task is not only to retrieve utterances containing exact instances of the query, but also utterances whose meaning is relevant to the query. We f","authors_text":"Aristotelis Anastassiou, Herman Kamper, Karen Livescu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-15T14:35:40Z","title":"Semantic query-by-example speech search using visual grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07078","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:d15ed92631780bd52bee1a34fe6cb2c1528e3804c8d6d893fa82338251fa0b26","target":"record","created_at":"2026-05-17T23:48:35Z","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":"8125deb60caea3508e98b620d20e7afd22b3e07471a9c70fbdb6fab9221cb434","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-15T14:35:40Z","title_canon_sha256":"a431aea844f9f68c60d745d5aec6b2d1b3df479f5c3fe6f55d3ef5bf9c0e6f75"},"schema_version":"1.0","source":{"id":"1904.07078","kind":"arxiv","version":1}},"canonical_sha256":"8107aa5ad344e86d3b74ba9229cfe1be3a6bbf924e7d9e57eee7ee674fa0709b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8107aa5ad344e86d3b74ba9229cfe1be3a6bbf924e7d9e57eee7ee674fa0709b","first_computed_at":"2026-05-17T23:48:35.338885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:35.338885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HINCl/554FtdTSZD5XlXHzy94nGR2PY0qIUbiGVBSZKoiPZaANxuw/+ZSubG/25X7G7RQhaiQ79otBsWB1gpDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:35.339462Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.07078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d15ed92631780bd52bee1a34fe6cb2c1528e3804c8d6d893fa82338251fa0b26","sha256:abe672b4034757365f5004a8b9da7f0e8f1c69df959dd4e7278b570b58161ced"],"state_sha256":"10446eeabed93a74402dce9b2c40fc4c1fbf6aab8eadd93532d565ae0d8e5d22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWDH4oxVNgbL05TIPdWms3EmFSI5zvlnhciE+QNc59jTjOJkIQT4H7j7d+h8TBLggWQykBTPKE7qNpWEWFNYAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:53:57.172278Z","bundle_sha256":"142fb3ee06819a40a454e47ce5ee9b6e58ebea6a9b9cba1eb166aa27697b4010"}}