{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IUFD6AL36QCK34B5DUSI6XXVSY","short_pith_number":"pith:IUFD6AL3","canonical_record":{"source":{"id":"2307.02083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-05T07:46:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"02b68030fc9fd34f860c5148b5d4eb216a237e8031adb4d2d9f7f2075815f71f","abstract_canon_sha256":"33991fe9a02f1ce10c24c647c56b17c04b30b1ede4e78865cd880f9d4c6e8cfa"},"schema_version":"1.0"},"canonical_sha256":"450a3f017bf404adf03d1d248f5ef596397e24b22c0cbd935a313919df9cf010","source":{"kind":"arxiv","id":"2307.02083","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02083","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02083v1","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02083","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"IUFD6AL36QCK","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"IUFD6AL36QCK34B5","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"IUFD6AL3","created_at":"2026-07-05T06:28:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IUFD6AL36QCK34B5DUSI6XXVSY","target":"record","payload":{"canonical_record":{"source":{"id":"2307.02083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-05T07:46:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"02b68030fc9fd34f860c5148b5d4eb216a237e8031adb4d2d9f7f2075815f71f","abstract_canon_sha256":"33991fe9a02f1ce10c24c647c56b17c04b30b1ede4e78865cd880f9d4c6e8cfa"},"schema_version":"1.0"},"canonical_sha256":"450a3f017bf404adf03d1d248f5ef596397e24b22c0cbd935a313919df9cf010","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:05.158365Z","signature_b64":"qenpjilCA7i/itHHwI4pehlIzjQ059UIPKDhv2bgDyuM/33X+bbDpsOExXGFtmQltlIMP9ewMnD4KxDOPP32Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"450a3f017bf404adf03d1d248f5ef596397e24b22c0cbd935a313919df9cf010","last_reissued_at":"2026-07-05T06:28:05.157950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:05.157950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.02083","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":"2026-07-05T06:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ic119XrrxDHENEmty+QOl5fUoVR8fqRijY4W1kfGdeJWkOPJZetEQTE2ujMhg806gNByv/o5g37JtzpUSi+qBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:31:13.349800Z"},"content_sha256":"a7f2d466f04d9d17de0e139031ff99bdca14cae3472b18e64190c134feded17c","schema_version":"1.0","event_id":"sha256:a7f2d466f04d9d17de0e139031ff99bdca14cae3472b18e64190c134feded17c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IUFD6AL36QCK34B5DUSI6XXVSY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging multilingual transfer for unsupervised semantic acoustic word embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Christiaan Jacobs, Herman Kamper","submitted_at":"2023-07-05T07:46:54Z","abstract_excerpt":"Acoustic word embeddings (AWEs) are fixed-dimensional vector representations of speech segments that encode phonetic content so that different realisations of the same word have similar embeddings. In this paper we explore semantic AWE modelling. These AWEs should not only capture phonetics but also the meaning of a word (similar to textual word embeddings). We consider the scenario where we only have untranscribed speech in a target language. We introduce a number of strategies leveraging a pre-trained multilingual AWE model -- a phonetic AWE model trained on labelled data from multiple langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02083","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/2307.02083/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":"2026-07-05T06:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Y+ng3hka5SEvdep++9nxgn+R3IuXfUUtaSUPHisOYYxk09FGPOOhNsJa1VROMeyioO/HcngyDaAFXM3lN6oDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:31:13.350167Z"},"content_sha256":"264e3bcc4ffb1e6e0447d512006bbc9d000ebac2197f7f8cddb73e26da749a5b","schema_version":"1.0","event_id":"sha256:264e3bcc4ffb1e6e0447d512006bbc9d000ebac2197f7f8cddb73e26da749a5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUFD6AL36QCK34B5DUSI6XXVSY/bundle.json","state_url":"https://pith.science/pith/IUFD6AL36QCK34B5DUSI6XXVSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUFD6AL36QCK34B5DUSI6XXVSY/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":"2026-07-07T10:31:13Z","links":{"resolver":"https://pith.science/pith/IUFD6AL36QCK34B5DUSI6XXVSY","bundle":"https://pith.science/pith/IUFD6AL36QCK34B5DUSI6XXVSY/bundle.json","state":"https://pith.science/pith/IUFD6AL36QCK34B5DUSI6XXVSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUFD6AL36QCK34B5DUSI6XXVSY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IUFD6AL36QCK34B5DUSI6XXVSY","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":"33991fe9a02f1ce10c24c647c56b17c04b30b1ede4e78865cd880f9d4c6e8cfa","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-05T07:46:54Z","title_canon_sha256":"02b68030fc9fd34f860c5148b5d4eb216a237e8031adb4d2d9f7f2075815f71f"},"schema_version":"1.0","source":{"id":"2307.02083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02083","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02083v1","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02083","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"IUFD6AL36QCK","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"IUFD6AL36QCK34B5","created_at":"2026-07-05T06:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"IUFD6AL3","created_at":"2026-07-05T06:28:05Z"}],"graph_snapshots":[{"event_id":"sha256:264e3bcc4ffb1e6e0447d512006bbc9d000ebac2197f7f8cddb73e26da749a5b","target":"graph","created_at":"2026-07-05T06:28:05Z","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/2307.02083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Acoustic word embeddings (AWEs) are fixed-dimensional vector representations of speech segments that encode phonetic content so that different realisations of the same word have similar embeddings. In this paper we explore semantic AWE modelling. These AWEs should not only capture phonetics but also the meaning of a word (similar to textual word embeddings). We consider the scenario where we only have untranscribed speech in a target language. We introduce a number of strategies leveraging a pre-trained multilingual AWE model -- a phonetic AWE model trained on labelled data from multiple langu","authors_text":"Christiaan Jacobs, Herman Kamper","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-05T07:46:54Z","title":"Leveraging multilingual transfer for unsupervised semantic acoustic word embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02083","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:a7f2d466f04d9d17de0e139031ff99bdca14cae3472b18e64190c134feded17c","target":"record","created_at":"2026-07-05T06:28:05Z","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":"33991fe9a02f1ce10c24c647c56b17c04b30b1ede4e78865cd880f9d4c6e8cfa","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-05T07:46:54Z","title_canon_sha256":"02b68030fc9fd34f860c5148b5d4eb216a237e8031adb4d2d9f7f2075815f71f"},"schema_version":"1.0","source":{"id":"2307.02083","kind":"arxiv","version":1}},"canonical_sha256":"450a3f017bf404adf03d1d248f5ef596397e24b22c0cbd935a313919df9cf010","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"450a3f017bf404adf03d1d248f5ef596397e24b22c0cbd935a313919df9cf010","first_computed_at":"2026-07-05T06:28:05.157950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:05.157950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qenpjilCA7i/itHHwI4pehlIzjQ059UIPKDhv2bgDyuM/33X+bbDpsOExXGFtmQltlIMP9ewMnD4KxDOPP32Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:05.158365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7f2d466f04d9d17de0e139031ff99bdca14cae3472b18e64190c134feded17c","sha256:264e3bcc4ffb1e6e0447d512006bbc9d000ebac2197f7f8cddb73e26da749a5b"],"state_sha256":"4463e87f6357743369f47d632723002ca206cd3fe498a26005f1792f189954e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w070S7xfLrvWgfYAlxeQnZtV3RJxWaXozg4NENHsJlC9cpBorh/2kLlNFTX67XGE9Ij/eOupZFFNSurvgVQnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:31:13.352079Z","bundle_sha256":"3872bf56e7ed17f1256290b57376464f180fef40462c3b73c19c2ffd3cc48944"}}