{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7B5UJFXDLAYS5CKUQ35VXQ5OOJ","short_pith_number":"pith:7B5UJFXD","schema_version":"1.0","canonical_sha256":"f87b4496e358312e895486fb5bc3ae7260492a6d6e5e2a74b6e677f442ed4935","source":{"kind":"arxiv","id":"1712.03897","version":1},"attestation_state":"computed","paper":{"title":"Learning Modality-Invariant Representations for Speech and Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"David Harwath, James Glass, Kenneth Leidal","submitted_at":"2017-12-11T17:18:34Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1712.03897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T17:18:34Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"ae3efb83795b1c49dfcc831baab3f005cd09aed792f606f8b9ee6f3785a1a4b2","abstract_canon_sha256":"edf699948e470cf428b59794a315ca04a4d17d5c914e2c8c7f7ea11cd69511c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:19.630194Z","signature_b64":"arZcFgTLcF/shFDN6aEvhvHa2GsHs2w0/C51aVsUzgvJmU9hvAGYGeQJIDg8vQjhZx4gFIfFQ6EVvxUObr4bCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f87b4496e358312e895486fb5bc3ae7260492a6d6e5e2a74b6e677f442ed4935","last_reissued_at":"2026-05-18T00:28:19.629342Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:19.629342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Modality-Invariant Representations for Speech and Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"David Harwath, James Glass, Kenneth Leidal","submitted_at":"2017-12-11T17:18:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03897","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.03897","created_at":"2026-05-18T00:28:19.629465+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.03897v1","created_at":"2026-05-18T00:28:19.629465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03897","created_at":"2026-05-18T00:28:19.629465+00:00"},{"alias_kind":"pith_short_12","alias_value":"7B5UJFXDLAYS","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"7B5UJFXDLAYS5CKU","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"7B5UJFXD","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ","json":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ.json","graph_json":"https://pith.science/api/pith-number/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/graph.json","events_json":"https://pith.science/api/pith-number/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/events.json","paper":"https://pith.science/paper/7B5UJFXD"},"agent_actions":{"view_html":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ","download_json":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ.json","view_paper":"https://pith.science/paper/7B5UJFXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.03897&json=true","fetch_graph":"https://pith.science/api/pith-number/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/action/storage_attestation","attest_author":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/action/author_attestation","sign_citation":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/action/citation_signature","submit_replication":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/action/replication_record"}},"created_at":"2026-05-18T00:28:19.629465+00:00","updated_at":"2026-05-18T00:28:19.629465+00:00"}