{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XMBXPHBJJEFYFFPAUC4TZSBMZJ","short_pith_number":"pith:XMBXPHBJ","canonical_record":{"source":{"id":"1806.03621","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T09:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"e1cc3f53880cba2667c9d38ed968995c8e8c0cb0404662bf5466c125bf37edea","abstract_canon_sha256":"5b147377ada73d26b2882c2638570efc608c3482b3cb0a448153b0f9348cd172"},"schema_version":"1.0"},"canonical_sha256":"bb03779c29490b8295e0a0b93cc82cca5debe3fce9d9cebd0d709e4f2a978bce","source":{"kind":"arxiv","id":"1806.03621","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03621","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03621v2","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03621","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"XMBXPHBJJEFY","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XMBXPHBJJEFYFFPA","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XMBXPHBJ","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XMBXPHBJJEFYFFPAUC4TZSBMZJ","target":"record","payload":{"canonical_record":{"source":{"id":"1806.03621","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T09:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"e1cc3f53880cba2667c9d38ed968995c8e8c0cb0404662bf5466c125bf37edea","abstract_canon_sha256":"5b147377ada73d26b2882c2638570efc608c3482b3cb0a448153b0f9348cd172"},"schema_version":"1.0"},"canonical_sha256":"bb03779c29490b8295e0a0b93cc82cca5debe3fce9d9cebd0d709e4f2a978bce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:03.869732Z","signature_b64":"ATS8N7uh+0p91JNKvi36SOVBoIf1XhGAnYrKSmL2dh9AQOFa55S3j6HrydfdYeTQXOnw/NFjRkDf4/wPan+mCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb03779c29490b8295e0a0b93cc82cca5debe3fce9d9cebd0d709e4f2a978bce","last_reissued_at":"2026-05-18T00:13:03.869158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:03.869158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.03621","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6qAwDTT6o1OIFNHE+iq2gJ8gVATLulBIr+7k+nCJPn206x567XVAvR3e5iDo19NlO2rCwPR/Xf4jVu0khSoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:22:42.435771Z"},"content_sha256":"2c5357008579d083d49cd8dc328219539af3bb975527db2f6b9826333d0d19c0","schema_version":"1.0","event_id":"sha256:2c5357008579d083d49cd8dc328219539af3bb975527db2f6b9826333d0d19c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XMBXPHBJJEFYFFPAUC4TZSBMZJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Ma, Cheung-Chi Leung, Haizhou Li, Hongjie Chen, Lei Xie, Yougen Yuan","submitted_at":"2018-06-10T09:40:08Z","abstract_excerpt":"We propose to learn acoustic word embeddings with temporal context for query-by-example (QbE) speech search. The temporal context includes the leading and trailing word sequences of a word. We assume that there exist spoken word pairs in the training database. We pad the word pairs with their original temporal context to form fixed-length speech segment pairs. We obtain the acoustic word embeddings through a deep convolutional neural network (CNN) which is trained on the speech segment pairs with a triplet loss. Shifting a fixed-length analysis window through the search content, we obtain a ru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03621","kind":"arxiv","version":2},"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":"2026-05-18T00:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jxYFjQS+H4MG4Sx60Z83Q+VO0ZsOz//tWmfplAz1HZK/WzKyw73vhuVXz7VcezY7lB9dEomkctAh/rt4x7KDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:22:42.436126Z"},"content_sha256":"877095025d2bb0ac69f3734d44d4883774557f2f1f627163acbf67bb8f63dfe9","schema_version":"1.0","event_id":"sha256:877095025d2bb0ac69f3734d44d4883774557f2f1f627163acbf67bb8f63dfe9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMBXPHBJJEFYFFPAUC4TZSBMZJ/bundle.json","state_url":"https://pith.science/pith/XMBXPHBJJEFYFFPAUC4TZSBMZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMBXPHBJJEFYFFPAUC4TZSBMZJ/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":"2026-06-03T08:22:42Z","links":{"resolver":"https://pith.science/pith/XMBXPHBJJEFYFFPAUC4TZSBMZJ","bundle":"https://pith.science/pith/XMBXPHBJJEFYFFPAUC4TZSBMZJ/bundle.json","state":"https://pith.science/pith/XMBXPHBJJEFYFFPAUC4TZSBMZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMBXPHBJJEFYFFPAUC4TZSBMZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XMBXPHBJJEFYFFPAUC4TZSBMZJ","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":"5b147377ada73d26b2882c2638570efc608c3482b3cb0a448153b0f9348cd172","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T09:40:08Z","title_canon_sha256":"e1cc3f53880cba2667c9d38ed968995c8e8c0cb0404662bf5466c125bf37edea"},"schema_version":"1.0","source":{"id":"1806.03621","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03621","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03621v2","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03621","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"XMBXPHBJJEFY","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XMBXPHBJJEFYFFPA","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XMBXPHBJ","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:877095025d2bb0ac69f3734d44d4883774557f2f1f627163acbf67bb8f63dfe9","target":"graph","created_at":"2026-05-18T00:13:03Z","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":"We propose to learn acoustic word embeddings with temporal context for query-by-example (QbE) speech search. The temporal context includes the leading and trailing word sequences of a word. We assume that there exist spoken word pairs in the training database. We pad the word pairs with their original temporal context to form fixed-length speech segment pairs. We obtain the acoustic word embeddings through a deep convolutional neural network (CNN) which is trained on the speech segment pairs with a triplet loss. Shifting a fixed-length analysis window through the search content, we obtain a ru","authors_text":"Bin Ma, Cheung-Chi Leung, Haizhou Li, Hongjie Chen, Lei Xie, Yougen Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T09:40:08Z","title":"Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03621","kind":"arxiv","version":2},"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":"sha256:2c5357008579d083d49cd8dc328219539af3bb975527db2f6b9826333d0d19c0","target":"record","created_at":"2026-05-18T00:13:03Z","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":"5b147377ada73d26b2882c2638570efc608c3482b3cb0a448153b0f9348cd172","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T09:40:08Z","title_canon_sha256":"e1cc3f53880cba2667c9d38ed968995c8e8c0cb0404662bf5466c125bf37edea"},"schema_version":"1.0","source":{"id":"1806.03621","kind":"arxiv","version":2}},"canonical_sha256":"bb03779c29490b8295e0a0b93cc82cca5debe3fce9d9cebd0d709e4f2a978bce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb03779c29490b8295e0a0b93cc82cca5debe3fce9d9cebd0d709e4f2a978bce","first_computed_at":"2026-05-18T00:13:03.869158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:03.869158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ATS8N7uh+0p91JNKvi36SOVBoIf1XhGAnYrKSmL2dh9AQOFa55S3j6HrydfdYeTQXOnw/NFjRkDf4/wPan+mCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:03.869732Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03621","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c5357008579d083d49cd8dc328219539af3bb975527db2f6b9826333d0d19c0","sha256:877095025d2bb0ac69f3734d44d4883774557f2f1f627163acbf67bb8f63dfe9"],"state_sha256":"d111705c9d569302257292ded19137829cbe0843f1c76a57d13b16856d43996b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z25yxrI6Jng8UEiJFCzkwrLh1hpyEMXXzsddwi/u+XhXt2EbnWS/xMuFg7A/Wgu3rsRY4wljOi/XtyIHO03uCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:22:42.438116Z","bundle_sha256":"3360cf496f06fdc132eac024ce7a4d4be10c2219ef990191928e72a4bd0f96f8"}}