{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:45O4EMZXXXNFOQRIXWIFQA47WO","short_pith_number":"pith:45O4EMZX","canonical_record":{"source":{"id":"1806.02199","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T14:11:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d636321172625e35be33c947f3fdaa8959574ae3c15de0170557e7ecd9d6461","abstract_canon_sha256":"8514442e2045e1efb92f03e0f669d2b342ef78bf84d64a718107e8fc8fb122c9"},"schema_version":"1.0"},"canonical_sha256":"e75dc23337bdda574228bd9058039fb39ec4eae6b40911e4faa2513958018643","source":{"kind":"arxiv","id":"1806.02199","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02199","created_at":"2026-05-17T23:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02199v7","created_at":"2026-05-17T23:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02199","created_at":"2026-05-17T23:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"45O4EMZXXXNF","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"45O4EMZXXXNFOQRI","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"45O4EMZX","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:45O4EMZXXXNFOQRIXWIFQA47WO","target":"record","payload":{"canonical_record":{"source":{"id":"1806.02199","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T14:11:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d636321172625e35be33c947f3fdaa8959574ae3c15de0170557e7ecd9d6461","abstract_canon_sha256":"8514442e2045e1efb92f03e0f669d2b342ef78bf84d64a718107e8fc8fb122c9"},"schema_version":"1.0"},"canonical_sha256":"e75dc23337bdda574228bd9058039fb39ec4eae6b40911e4faa2513958018643","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:58.464724Z","signature_b64":"EOySrcmXn7/EBwnfirGcsuadQF8AHzlK2rvgjG9v/oCU4Bsz4W+J6nkv2nCtM/Dn187qYSeJUr0vycBXuKDnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e75dc23337bdda574228bd9058039fb39ec4eae6b40911e4faa2513958018643","last_reissued_at":"2026-05-17T23:56:58.464040Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:58.464040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.02199","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jF1P9h6H1YiIyfg1g9e/N8RitLq1zI0CNDyquvqR3Re0+AIYY+A0EejfLFso4RrCUS/9KjYonLVKlo1Qb4edCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:07:45.197377Z"},"content_sha256":"25c638e80cf4da177f342d03ab97261ec7b5ea40d47183e195eafd94acba2d58","schema_version":"1.0","event_id":"sha256:25c638e80cf4da177f342d03ab97261ec7b5ea40d47183e195eafd94acba2d58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:45O4EMZXXXNFOQRIXWIFQA47WO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SOM-VAE: Interpretable Discrete Representation Learning on Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francesco Locatello, Gunnar R\\\"atsch, Heiko Strathmann, Matthias H\\\"user, Vincent Fortuin","submitted_at":"2018-06-06T14:11:30Z","abstract_excerpt":"High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most representation learning algorithms for time series data are difficult to interpret. This is due to non-intuitive mappings from data features to salient properties of the representation and non-smoothness over time. To address this problem, we propose a new representation learning framework building on ideas from interpretable discrete dimensionality reduction and deep "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02199","kind":"arxiv","version":7},"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":"2026-05-17T23:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E+FN8vlgzyLQmImOWUshaQ6byytzL9q32u6ju0ybEWxQtTRV8zgWrPUuAJq5Nl/XKuFbg9OoLHLA3x3yQUHTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:07:45.198063Z"},"content_sha256":"09aca8a3aee801586b0df3867517291db4db25bd84c2319ca1e1f8bed1456cc5","schema_version":"1.0","event_id":"sha256:09aca8a3aee801586b0df3867517291db4db25bd84c2319ca1e1f8bed1456cc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/45O4EMZXXXNFOQRIXWIFQA47WO/bundle.json","state_url":"https://pith.science/pith/45O4EMZXXXNFOQRIXWIFQA47WO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/45O4EMZXXXNFOQRIXWIFQA47WO/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":"2026-05-26T00:07:45Z","links":{"resolver":"https://pith.science/pith/45O4EMZXXXNFOQRIXWIFQA47WO","bundle":"https://pith.science/pith/45O4EMZXXXNFOQRIXWIFQA47WO/bundle.json","state":"https://pith.science/pith/45O4EMZXXXNFOQRIXWIFQA47WO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/45O4EMZXXXNFOQRIXWIFQA47WO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:45O4EMZXXXNFOQRIXWIFQA47WO","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":"8514442e2045e1efb92f03e0f669d2b342ef78bf84d64a718107e8fc8fb122c9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T14:11:30Z","title_canon_sha256":"1d636321172625e35be33c947f3fdaa8959574ae3c15de0170557e7ecd9d6461"},"schema_version":"1.0","source":{"id":"1806.02199","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02199","created_at":"2026-05-17T23:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02199v7","created_at":"2026-05-17T23:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02199","created_at":"2026-05-17T23:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"45O4EMZXXXNF","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"45O4EMZXXXNFOQRI","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"45O4EMZX","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:09aca8a3aee801586b0df3867517291db4db25bd84c2319ca1e1f8bed1456cc5","target":"graph","created_at":"2026-05-17T23:56:58Z","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":"High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most representation learning algorithms for time series data are difficult to interpret. This is due to non-intuitive mappings from data features to salient properties of the representation and non-smoothness over time. To address this problem, we propose a new representation learning framework building on ideas from interpretable discrete dimensionality reduction and deep ","authors_text":"Francesco Locatello, Gunnar R\\\"atsch, Heiko Strathmann, Matthias H\\\"user, Vincent Fortuin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T14:11:30Z","title":"SOM-VAE: Interpretable Discrete Representation Learning on Time Series"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02199","kind":"arxiv","version":7},"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":"sha256:25c638e80cf4da177f342d03ab97261ec7b5ea40d47183e195eafd94acba2d58","target":"record","created_at":"2026-05-17T23:56:58Z","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":"8514442e2045e1efb92f03e0f669d2b342ef78bf84d64a718107e8fc8fb122c9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T14:11:30Z","title_canon_sha256":"1d636321172625e35be33c947f3fdaa8959574ae3c15de0170557e7ecd9d6461"},"schema_version":"1.0","source":{"id":"1806.02199","kind":"arxiv","version":7}},"canonical_sha256":"e75dc23337bdda574228bd9058039fb39ec4eae6b40911e4faa2513958018643","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e75dc23337bdda574228bd9058039fb39ec4eae6b40911e4faa2513958018643","first_computed_at":"2026-05-17T23:56:58.464040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:58.464040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EOySrcmXn7/EBwnfirGcsuadQF8AHzlK2rvgjG9v/oCU4Bsz4W+J6nkv2nCtM/Dn187qYSeJUr0vycBXuKDnDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:58.464724Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.02199","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25c638e80cf4da177f342d03ab97261ec7b5ea40d47183e195eafd94acba2d58","sha256:09aca8a3aee801586b0df3867517291db4db25bd84c2319ca1e1f8bed1456cc5"],"state_sha256":"dbb72af1faa334aef8f30d0ab5acf0c2baf01a9d2e1fec44b5246e5905354c73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+lCzthKlPmevzi/jlLzW0DXgOgXURQMHlQ/INejGU8qcoovqsJ4iPyF1VRTMWYwe2zwfvaEGe6abpwr0/MtDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:07:45.201429Z","bundle_sha256":"525908088dd7b6ab438aa1cebc08d44e8e78ca31faa1e3eedd1a0e86c19519cf"}}