{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VMHFRCQQJSC6J4OUDKUL6H5LDL","short_pith_number":"pith:VMHFRCQQ","canonical_record":{"source":{"id":"1811.03875","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T12:14:20Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"8b8207327e8e6b55157e847c7ef762b1e1b27fd913073aae0f149dbf46b879c0","abstract_canon_sha256":"7c83ee211d4270229e88952d946c60f2e427324db42022530b7ab78ef0ed9121"},"schema_version":"1.0"},"canonical_sha256":"ab0e588a104c85e4f1d41aa8bf1fab1af8a35d855269d0d67f3c4e475d19aa5c","source":{"kind":"arxiv","id":"1811.03875","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03875","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03875v2","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03875","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"VMHFRCQQJSC6","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VMHFRCQQJSC6J4OU","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VMHFRCQQ","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VMHFRCQQJSC6J4OUDKUL6H5LDL","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03875","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T12:14:20Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"8b8207327e8e6b55157e847c7ef762b1e1b27fd913073aae0f149dbf46b879c0","abstract_canon_sha256":"7c83ee211d4270229e88952d946c60f2e427324db42022530b7ab78ef0ed9121"},"schema_version":"1.0"},"canonical_sha256":"ab0e588a104c85e4f1d41aa8bf1fab1af8a35d855269d0d67f3c4e475d19aa5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:39.971497Z","signature_b64":"soaTfRQHvLk/j3HE+CExb72wQJfb1KWyMBmgRIvUmCn973ubIG7qUKV5M3APA/O0klys0fvYxd3EkiHMYOm7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab0e588a104c85e4f1d41aa8bf1fab1af8a35d855269d0d67f3c4e475d19aa5c","last_reissued_at":"2026-05-17T23:48:39.970935Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:39.970935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03875","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":"2026-05-17T23:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3ADQwmYnWPt64hFdsSAiQyLPHE9rV8TTrS7iNIHTbGl+sLL+rzjgHl12XlPNccCJ38NhMsPxZCp8P5Ik4gSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T15:59:15.035879Z"},"content_sha256":"4ca077cf5828b64c517de5cffc6b9893910ed8b60e2aa9d62f55b2332f9e6a83","schema_version":"1.0","event_id":"sha256:4ca077cf5828b64c517de5cffc6b9893910ed8b60e2aa9d62f55b2332f9e6a83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VMHFRCQQJSC6J4OUDKUL6H5LDL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal One-Shot Learning of Speech and Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Herman A. Engelbrecht, Herman Kamper, Ryan Eloff","submitted_at":"2018-11-09T12:14:20Z","abstract_excerpt":"Imagine a robot is shown new concepts visually together with spoken tags, e.g. \"milk\", \"eggs\", \"butter\". After seeing one paired audio-visual example per class, it is shown a new set of unseen instances of these objects, and asked to pick the \"milk\". Without receiving any hard labels, could it learn to match the new continuous speech input to the correct visual instance? Although unimodal one-shot learning has been studied, where one labelled example in a single modality is given per class, this example motivates multimodal one-shot learning. Our main contribution is to formally define this ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03875","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":"2026-05-17T23:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KR9TOCFayl8QO6b9Z+FQhmdBpJaRFbpN3PKlapZSYiJK3MiY0CwjrYnnOC911VJp6H6S9yv6F4Bh1PvJNtsRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T15:59:15.036518Z"},"content_sha256":"6fd4682e5d201fe8fb9636821ec20b1797d07dcea2a2946f310333049b972b0d","schema_version":"1.0","event_id":"sha256:6fd4682e5d201fe8fb9636821ec20b1797d07dcea2a2946f310333049b972b0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VMHFRCQQJSC6J4OUDKUL6H5LDL/bundle.json","state_url":"https://pith.science/pith/VMHFRCQQJSC6J4OUDKUL6H5LDL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VMHFRCQQJSC6J4OUDKUL6H5LDL/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":"2026-06-06T15:59:15Z","links":{"resolver":"https://pith.science/pith/VMHFRCQQJSC6J4OUDKUL6H5LDL","bundle":"https://pith.science/pith/VMHFRCQQJSC6J4OUDKUL6H5LDL/bundle.json","state":"https://pith.science/pith/VMHFRCQQJSC6J4OUDKUL6H5LDL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VMHFRCQQJSC6J4OUDKUL6H5LDL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VMHFRCQQJSC6J4OUDKUL6H5LDL","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":"7c83ee211d4270229e88952d946c60f2e427324db42022530b7ab78ef0ed9121","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T12:14:20Z","title_canon_sha256":"8b8207327e8e6b55157e847c7ef762b1e1b27fd913073aae0f149dbf46b879c0"},"schema_version":"1.0","source":{"id":"1811.03875","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03875","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03875v2","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03875","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"VMHFRCQQJSC6","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VMHFRCQQJSC6J4OU","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VMHFRCQQ","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:6fd4682e5d201fe8fb9636821ec20b1797d07dcea2a2946f310333049b972b0d","target":"graph","created_at":"2026-05-17T23:48:39Z","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":"Imagine a robot is shown new concepts visually together with spoken tags, e.g. \"milk\", \"eggs\", \"butter\". After seeing one paired audio-visual example per class, it is shown a new set of unseen instances of these objects, and asked to pick the \"milk\". Without receiving any hard labels, could it learn to match the new continuous speech input to the correct visual instance? Although unimodal one-shot learning has been studied, where one labelled example in a single modality is given per class, this example motivates multimodal one-shot learning. Our main contribution is to formally define this ta","authors_text":"Herman A. Engelbrecht, Herman Kamper, Ryan Eloff","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T12:14:20Z","title":"Multimodal One-Shot Learning of Speech and Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03875","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":"sha256:4ca077cf5828b64c517de5cffc6b9893910ed8b60e2aa9d62f55b2332f9e6a83","target":"record","created_at":"2026-05-17T23:48:39Z","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":"7c83ee211d4270229e88952d946c60f2e427324db42022530b7ab78ef0ed9121","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T12:14:20Z","title_canon_sha256":"8b8207327e8e6b55157e847c7ef762b1e1b27fd913073aae0f149dbf46b879c0"},"schema_version":"1.0","source":{"id":"1811.03875","kind":"arxiv","version":2}},"canonical_sha256":"ab0e588a104c85e4f1d41aa8bf1fab1af8a35d855269d0d67f3c4e475d19aa5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab0e588a104c85e4f1d41aa8bf1fab1af8a35d855269d0d67f3c4e475d19aa5c","first_computed_at":"2026-05-17T23:48:39.970935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:39.970935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"soaTfRQHvLk/j3HE+CExb72wQJfb1KWyMBmgRIvUmCn973ubIG7qUKV5M3APA/O0klys0fvYxd3EkiHMYOm7Dg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:39.971497Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03875","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ca077cf5828b64c517de5cffc6b9893910ed8b60e2aa9d62f55b2332f9e6a83","sha256:6fd4682e5d201fe8fb9636821ec20b1797d07dcea2a2946f310333049b972b0d"],"state_sha256":"32344c93215a35608e5edea3750a1c315ef19e134633d5e776f62544c701134b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YO2t0FWmfCn+aMRD1aqJibJgbngGVmoLfFAY6/b9oDSZd/c5EgT9JoZ0In6uc5s5b4esxRgFRZ++nWm51opKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T15:59:15.039094Z","bundle_sha256":"7043908034547889169356b433ef6c345e4856b41d4584bfbe1000c40df46a74"}}