{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZCI24745RX2FCWPYEAHMDE5OFT","short_pith_number":"pith:ZCI24745","canonical_record":{"source":{"id":"1806.05030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T13:37:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dbeb6bcde10065b73f58286aab9c95908f19e7d2131c90bad17604e81ee6e93d","abstract_canon_sha256":"38183b727a418582d4860aa688c01a16eddf441c97d42aec282063e4d7feea6a"},"schema_version":"1.0"},"canonical_sha256":"c891ae7f9d8df45159f8200ec193ae2cfc715d83fb21b63815ea85f927f8884e","source":{"kind":"arxiv","id":"1806.05030","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05030","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05030v1","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05030","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZCI24745RX2F","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZCI24745RX2FCWPY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZCI24745","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZCI24745RX2FCWPYEAHMDE5OFT","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T13:37:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dbeb6bcde10065b73f58286aab9c95908f19e7d2131c90bad17604e81ee6e93d","abstract_canon_sha256":"38183b727a418582d4860aa688c01a16eddf441c97d42aec282063e4d7feea6a"},"schema_version":"1.0"},"canonical_sha256":"c891ae7f9d8df45159f8200ec193ae2cfc715d83fb21b63815ea85f927f8884e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:20.305324Z","signature_b64":"UjSLb9ObVuwXweV5dPuYamVZvglHx4FVyZ0G9q5l54CPFDetrQNQqt5p7j2ung0+BrBAxiTG1vMB8ntSNi75BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c891ae7f9d8df45159f8200ec193ae2cfc715d83fb21b63815ea85f927f8884e","last_reissued_at":"2026-05-18T00:13:20.304767Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:20.304767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05030","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":"2026-05-18T00:13:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AkXNfH7iVH4IgjnNpuWYQJJaOcR+v9rBBNK0FRQi6BSuGeYTt6fZb12oLRW68k12jasZnuSRJz0XmrFhZTxjDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:41:19.921065Z"},"content_sha256":"3e736128d05d1ed425f80fbbed38ada7260cca37611f0caddcc623192069d445","schema_version":"1.0","event_id":"sha256:3e736128d05d1ed425f80fbbed38ada7260cca37611f0caddcc623192069d445"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZCI24745RX2FCWPYEAHMDE5OFT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visually grounded cross-lingual keyword spotting in speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Herman Kamper, Michael Roth","submitted_at":"2018-06-13T13:37:34Z","abstract_excerpt":"Recent work considered how images paired with speech can be used as supervision for building speech systems when transcriptions are not available. We ask whether visual grounding can be used for cross-lingual keyword spotting: given a text keyword in one language, the task is to retrieve spoken utterances containing that keyword in another language. This could enable searching through speech in a low-resource language using text queries in a high-resource language. As a proof-of-concept, we use English speech with German queries: we use a German visual tagger to add keyword labels to each trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05030","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":"2026-05-18T00:13:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a8Gbx4p4axIGg7Day8Nw/GgV9D/Dp5+KVafbwlXzLMzjCgZulfUEFzypti0GbkWQATO5G3OTYjzCd7g5gymGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:41:19.921747Z"},"content_sha256":"7099c5b6153e548a975f16880f91a4b3e90836f61cb2dd30134152280e739fc0","schema_version":"1.0","event_id":"sha256:7099c5b6153e548a975f16880f91a4b3e90836f61cb2dd30134152280e739fc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZCI24745RX2FCWPYEAHMDE5OFT/bundle.json","state_url":"https://pith.science/pith/ZCI24745RX2FCWPYEAHMDE5OFT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZCI24745RX2FCWPYEAHMDE5OFT/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":"2026-05-25T19:41:19Z","links":{"resolver":"https://pith.science/pith/ZCI24745RX2FCWPYEAHMDE5OFT","bundle":"https://pith.science/pith/ZCI24745RX2FCWPYEAHMDE5OFT/bundle.json","state":"https://pith.science/pith/ZCI24745RX2FCWPYEAHMDE5OFT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZCI24745RX2FCWPYEAHMDE5OFT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZCI24745RX2FCWPYEAHMDE5OFT","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":"38183b727a418582d4860aa688c01a16eddf441c97d42aec282063e4d7feea6a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T13:37:34Z","title_canon_sha256":"dbeb6bcde10065b73f58286aab9c95908f19e7d2131c90bad17604e81ee6e93d"},"schema_version":"1.0","source":{"id":"1806.05030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05030","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05030v1","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05030","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZCI24745RX2F","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZCI24745RX2FCWPY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZCI24745","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:7099c5b6153e548a975f16880f91a4b3e90836f61cb2dd30134152280e739fc0","target":"graph","created_at":"2026-05-18T00:13:20Z","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":"Recent work considered how images paired with speech can be used as supervision for building speech systems when transcriptions are not available. We ask whether visual grounding can be used for cross-lingual keyword spotting: given a text keyword in one language, the task is to retrieve spoken utterances containing that keyword in another language. This could enable searching through speech in a low-resource language using text queries in a high-resource language. As a proof-of-concept, we use English speech with German queries: we use a German visual tagger to add keyword labels to each trai","authors_text":"Herman Kamper, Michael Roth","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T13:37:34Z","title":"Visually grounded cross-lingual keyword spotting in speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05030","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":"sha256:3e736128d05d1ed425f80fbbed38ada7260cca37611f0caddcc623192069d445","target":"record","created_at":"2026-05-18T00:13:20Z","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":"38183b727a418582d4860aa688c01a16eddf441c97d42aec282063e4d7feea6a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T13:37:34Z","title_canon_sha256":"dbeb6bcde10065b73f58286aab9c95908f19e7d2131c90bad17604e81ee6e93d"},"schema_version":"1.0","source":{"id":"1806.05030","kind":"arxiv","version":1}},"canonical_sha256":"c891ae7f9d8df45159f8200ec193ae2cfc715d83fb21b63815ea85f927f8884e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c891ae7f9d8df45159f8200ec193ae2cfc715d83fb21b63815ea85f927f8884e","first_computed_at":"2026-05-18T00:13:20.304767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:20.304767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UjSLb9ObVuwXweV5dPuYamVZvglHx4FVyZ0G9q5l54CPFDetrQNQqt5p7j2ung0+BrBAxiTG1vMB8ntSNi75BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:20.305324Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e736128d05d1ed425f80fbbed38ada7260cca37611f0caddcc623192069d445","sha256:7099c5b6153e548a975f16880f91a4b3e90836f61cb2dd30134152280e739fc0"],"state_sha256":"7b0790970944acb6c76153df62a17065f34434cfd4235814881ee0d3a3067dc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UYJeDnUarN9/ywpPXNo7GMtlE+kN94FcXNDrGwpdJ2nTvXP83a0/peWAWc8B3EmzinD1ehwxONLkz1Qa0tp+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:41:19.925457Z","bundle_sha256":"9a9224d0809ee74b16590c0f63fa54822cabdaeb09c3789359be013e317ddda4"}}