{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7B5UJFXDLAYS5CKUQ35VXQ5OOJ","short_pith_number":"pith:7B5UJFXD","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"},"canonical_sha256":"f87b4496e358312e895486fb5bc3ae7260492a6d6e5e2a74b6e677f442ed4935","source":{"kind":"arxiv","id":"1712.03897","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7B5UJFXDLAYS5CKUQ35VXQ5OOJ","target":"record","payload":{"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"},"canonical_sha256":"f87b4496e358312e895486fb5bc3ae7260492a6d6e5e2a74b6e677f442ed4935","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"},"source_kind":"arxiv","source_id":"1712.03897","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":"2026-05-18T00:28:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9eOOfoz0Y4rDKw4+0d+SOBIOFlKGkeTR26m94SkNPPkgGDjORNXiCpnGmHt1/aUx8rRB7lET05fHMBcAIijoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:54:05.111309Z"},"content_sha256":"7c2d0b86a66941c3b878cf55a1b5dfa7571cab71f3a0e91c5e75b16f84f6d534","schema_version":"1.0","event_id":"sha256:7c2d0b86a66941c3b878cf55a1b5dfa7571cab71f3a0e91c5e75b16f84f6d534"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7B5UJFXDLAYS5CKUQ35VXQ5OOJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:28:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KXttE7EghNt9/D1bkRQEwZxQrcCxop5y90YkWtym8jz3TSFCHqq6hUXIAXBMR1RFNyHdJXd92Il6TyvkADDHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:54:05.112611Z"},"content_sha256":"b9aa7d9bde76d6d245805bc47676618590128d713ae3b3aed1ccc836031f23bc","schema_version":"1.0","event_id":"sha256:b9aa7d9bde76d6d245805bc47676618590128d713ae3b3aed1ccc836031f23bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/bundle.json","state_url":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/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":"2026-08-13T05:54:05Z","links":{"resolver":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ","bundle":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/bundle.json","state":"https://pith.science/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7B5UJFXDLAYS5CKUQ35VXQ5OOJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BW3dFZv7fv0gvbATI6FFwVoWDxM4jU4sTY38ov20h37Rhex3T5TmJx/9Q0khQOS+6WcMyJ5r+Ml/1DLvvUfcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T05:54:05.121252Z","bundle_sha256":"ff5bf70e440b9ccd3a83546b3fc7b4823ce23ac0e80109e8ec2e3216c2b802a4"}}