{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7B5UJFXDLAYS5CKUQ35VXQ5OOJ","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":"edf699948e470cf428b59794a315ca04a4d17d5c914e2c8c7f7ea11cd69511c2","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T17:18:34Z","title_canon_sha256":"ae3efb83795b1c49dfcc831baab3f005cd09aed792f606f8b9ee6f3785a1a4b2"},"schema_version":"1.0","source":{"id":"1712.03897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03897","created_at":"2026-05-18T00:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03897v1","created_at":"2026-05-18T00:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03897","created_at":"2026-05-18T00:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"7B5UJFXDLAYS","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"7B5UJFXDLAYS5CKU","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"7B5UJFXD","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:b9aa7d9bde76d6d245805bc47676618590128d713ae3b3aed1ccc836031f23bc","target":"graph","created_at":"2026-05-18T00:28:19Z","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":"In this paper, we explore the unsupervised learning of a semantic embedding space for co-occurring sensory inputs. Specifically, we focus on the task of learning a semantic vector space for both spoken and handwritten digits using the TIDIGITs and MNIST datasets. Current techniques encode image and audio/textual inputs directly to semantic embeddings. In contrast, our technique maps an input to the mean and log variance vectors of a diagonal Gaussian from which sample semantic embeddings are drawn. In addition to encouraging semantic similarity between co-occurring inputs,our loss function inc","authors_text":"David Harwath, James Glass, Kenneth Leidal","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T17:18:34Z","title":"Learning Modality-Invariant Representations for Speech and Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03897","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":"sha256:7c2d0b86a66941c3b878cf55a1b5dfa7571cab71f3a0e91c5e75b16f84f6d534","target":"record","created_at":"2026-05-18T00:28:19Z","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":"edf699948e470cf428b59794a315ca04a4d17d5c914e2c8c7f7ea11cd69511c2","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T17:18:34Z","title_canon_sha256":"ae3efb83795b1c49dfcc831baab3f005cd09aed792f606f8b9ee6f3785a1a4b2"},"schema_version":"1.0","source":{"id":"1712.03897","kind":"arxiv","version":1}},"canonical_sha256":"f87b4496e358312e895486fb5bc3ae7260492a6d6e5e2a74b6e677f442ed4935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f87b4496e358312e895486fb5bc3ae7260492a6d6e5e2a74b6e677f442ed4935","first_computed_at":"2026-05-18T00:28:19.629342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:19.629342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"arZcFgTLcF/shFDN6aEvhvHa2GsHs2w0/C51aVsUzgvJmU9hvAGYGeQJIDg8vQjhZx4gFIfFQ6EVvxUObr4bCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:19.630194Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.03897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c2d0b86a66941c3b878cf55a1b5dfa7571cab71f3a0e91c5e75b16f84f6d534","sha256:b9aa7d9bde76d6d245805bc47676618590128d713ae3b3aed1ccc836031f23bc"],"state_sha256":"ea8e683ac221079ce58640119d014edd544d27797a5f28617f7211cefacd300d"}