{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EQEFKUGYDOD767U74KALJJ2NZT","short_pith_number":"pith:EQEFKUGY","canonical_record":{"source":{"id":"2206.15400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-06-30T16:40:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a15df0e4909a4f79abfb35025ecbdcdbb085febd94735c4cd6d373863c1d254f","abstract_canon_sha256":"1628e4a2c834ecf83e1f7a518ba432f8c4f7bf53a801cc64768f074b7b653913"},"schema_version":"1.0"},"canonical_sha256":"24085550d81b87ff7e9fe280b4a74dccff508cca9ab8d9f09e15258ffd3348ce","source":{"kind":"arxiv","id":"2206.15400","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15400","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15400v2","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15400","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"pith_short_12","alias_value":"EQEFKUGYDOD7","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"pith_short_16","alias_value":"EQEFKUGYDOD767U7","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"pith_short_8","alias_value":"EQEFKUGY","created_at":"2026-07-05T04:36:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EQEFKUGYDOD767U74KALJJ2NZT","target":"record","payload":{"canonical_record":{"source":{"id":"2206.15400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-06-30T16:40:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a15df0e4909a4f79abfb35025ecbdcdbb085febd94735c4cd6d373863c1d254f","abstract_canon_sha256":"1628e4a2c834ecf83e1f7a518ba432f8c4f7bf53a801cc64768f074b7b653913"},"schema_version":"1.0"},"canonical_sha256":"24085550d81b87ff7e9fe280b4a74dccff508cca9ab8d9f09e15258ffd3348ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:38.103058Z","signature_b64":"Jr/0R5W6v8Nj8nICFBDPo10jSaXunT9e44FBSlYrRNOFXxwM6Jq1T/U3/SsaWETMyRMQfm77qMV09Lidcq69Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24085550d81b87ff7e9fe280b4a74dccff508cca9ab8d9f09e15258ffd3348ce","last_reissued_at":"2026-07-05T04:36:38.102526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:38.102526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.15400","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":"2026-07-05T04:36:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vtFNahU+6Hdgc8nLh1F2ZTGpOlNsJTOqnzqiXs4TzwBxOt9IEAs6SFY0M8vdeWd0HgeJUGbhEbb6I5zZ6bPVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:20:30.872877Z"},"content_sha256":"a7a0f0b2837de63cf7fcef51e868e87f9e5993c957641536fdda3ef495c07abe","schema_version":"1.0","event_id":"sha256:a7a0f0b2837de63cf7fcef51e868e87f9e5993c957641536fdda3ef495c07abe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EQEFKUGYDOD767U74KALJJ2NZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"eess.AS","authors_text":"Doyeon Kim, Hong-Goo Kang, Hyeon-Kyeong Shin, Hyewon Han, Soo-Whan Chung","submitted_at":"2022-06-30T16:40:31Z","abstract_excerpt":"In this paper, we propose a novel end-to-end user-defined keyword spotting method that utilizes linguistically corresponding patterns between speech and text sequences. Unlike previous approaches requiring speech keyword enrollment, our method compares input queries with an enrolled text keyword sequence. To place the audio and text representations within a common latent space, we adopt an attention-based cross-modal matching approach that is trained in an end-to-end manner with monotonic matching loss and keyword classification loss. We also utilize a de-noising loss for the acoustic embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15400","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.15400/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":"2026-07-05T04:36:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H8I1c02YNx6dYB0YqNOKK3ES/ntBTdjUr/wiv5YMnyrMfjAk4CDy2s244wYt1bN989SxFbdJzPnARm+ud7jrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:20:30.873409Z"},"content_sha256":"fb70b64f73e691b0e1258cd01461fa410fabf0b4a70cc8ec65e819e71e73f8ea","schema_version":"1.0","event_id":"sha256:fb70b64f73e691b0e1258cd01461fa410fabf0b4a70cc8ec65e819e71e73f8ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQEFKUGYDOD767U74KALJJ2NZT/bundle.json","state_url":"https://pith.science/pith/EQEFKUGYDOD767U74KALJJ2NZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQEFKUGYDOD767U74KALJJ2NZT/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":"2026-08-18T18:20:30Z","links":{"resolver":"https://pith.science/pith/EQEFKUGYDOD767U74KALJJ2NZT","bundle":"https://pith.science/pith/EQEFKUGYDOD767U74KALJJ2NZT/bundle.json","state":"https://pith.science/pith/EQEFKUGYDOD767U74KALJJ2NZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQEFKUGYDOD767U74KALJJ2NZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EQEFKUGYDOD767U74KALJJ2NZT","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":"1628e4a2c834ecf83e1f7a518ba432f8c4f7bf53a801cc64768f074b7b653913","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-06-30T16:40:31Z","title_canon_sha256":"a15df0e4909a4f79abfb35025ecbdcdbb085febd94735c4cd6d373863c1d254f"},"schema_version":"1.0","source":{"id":"2206.15400","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15400","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15400v2","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15400","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"pith_short_12","alias_value":"EQEFKUGYDOD7","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"pith_short_16","alias_value":"EQEFKUGYDOD767U7","created_at":"2026-07-05T04:36:38Z"},{"alias_kind":"pith_short_8","alias_value":"EQEFKUGY","created_at":"2026-07-05T04:36:38Z"}],"graph_snapshots":[{"event_id":"sha256:fb70b64f73e691b0e1258cd01461fa410fabf0b4a70cc8ec65e819e71e73f8ea","target":"graph","created_at":"2026-07-05T04:36:38Z","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/2206.15400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel end-to-end user-defined keyword spotting method that utilizes linguistically corresponding patterns between speech and text sequences. Unlike previous approaches requiring speech keyword enrollment, our method compares input queries with an enrolled text keyword sequence. To place the audio and text representations within a common latent space, we adopt an attention-based cross-modal matching approach that is trained in an end-to-end manner with monotonic matching loss and keyword classification loss. We also utilize a de-noising loss for the acoustic embeddin","authors_text":"Doyeon Kim, Hong-Goo Kang, Hyeon-Kyeong Shin, Hyewon Han, Soo-Whan Chung","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-06-30T16:40:31Z","title":"Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15400","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:a7a0f0b2837de63cf7fcef51e868e87f9e5993c957641536fdda3ef495c07abe","target":"record","created_at":"2026-07-05T04:36:38Z","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":"1628e4a2c834ecf83e1f7a518ba432f8c4f7bf53a801cc64768f074b7b653913","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-06-30T16:40:31Z","title_canon_sha256":"a15df0e4909a4f79abfb35025ecbdcdbb085febd94735c4cd6d373863c1d254f"},"schema_version":"1.0","source":{"id":"2206.15400","kind":"arxiv","version":2}},"canonical_sha256":"24085550d81b87ff7e9fe280b4a74dccff508cca9ab8d9f09e15258ffd3348ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24085550d81b87ff7e9fe280b4a74dccff508cca9ab8d9f09e15258ffd3348ce","first_computed_at":"2026-07-05T04:36:38.102526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:38.102526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jr/0R5W6v8Nj8nICFBDPo10jSaXunT9e44FBSlYrRNOFXxwM6Jq1T/U3/SsaWETMyRMQfm77qMV09Lidcq69Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:38.103058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.15400","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7a0f0b2837de63cf7fcef51e868e87f9e5993c957641536fdda3ef495c07abe","sha256:fb70b64f73e691b0e1258cd01461fa410fabf0b4a70cc8ec65e819e71e73f8ea"],"state_sha256":"80febd7cfa6927b14d0bb150631bbeb307c6c8d8eb322a5f99f77ead5bdc90ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JtOlkS4p9OoVICPh+6bEBMXP5cJa27q+nQFQfRa6dLmEjQk1fGbdI7DeyqajvYNaq7ojfYSMqF9CRCJnId4fBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:20:30.879070Z","bundle_sha256":"9faea7b8f10c00ef70e5c66d04039666277a789788ac46cf06e923abc7108ec5"}}