{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IEYB6NW7DWVVVEEEJWKHSKSIWT","short_pith_number":"pith:IEYB6NW7","canonical_record":{"source":{"id":"1705.08695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-24T10:52:19Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4044462b4bb2e6c267babe7b317c7964c64ab1aec864ebb24fe8d711b0027c31","abstract_canon_sha256":"932ef9fa634167ddfaa4c56faf1fa4f1014467d6a0f95f04442bfb9532f7d519"},"schema_version":"1.0"},"canonical_sha256":"41301f36df1dab5a90844d94792a48b4f26a5129b1fd3bad4a27730445cfbe18","source":{"kind":"arxiv","id":"1705.08695","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08695","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08695v1","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08695","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"IEYB6NW7DWVV","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IEYB6NW7DWVVVEEE","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IEYB6NW7","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IEYB6NW7DWVVVEEEJWKHSKSIWT","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-24T10:52:19Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4044462b4bb2e6c267babe7b317c7964c64ab1aec864ebb24fe8d711b0027c31","abstract_canon_sha256":"932ef9fa634167ddfaa4c56faf1fa4f1014467d6a0f95f04442bfb9532f7d519"},"schema_version":"1.0"},"canonical_sha256":"41301f36df1dab5a90844d94792a48b4f26a5129b1fd3bad4a27730445cfbe18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:44.559780Z","signature_b64":"WCgaTB+P9pyrROAiGW6YoSuD6YLDIDl+i1UORg2322dwNRTa4WO/h0B/SU+NHxEPxp6G6GhbWU+hwGfbyVFWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41301f36df1dab5a90844d94792a48b4f26a5129b1fd3bad4a27730445cfbe18","last_reissued_at":"2026-05-18T00:43:44.559275Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:44.559275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08695","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":"2026-05-18T00:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZbF6lVXy/MIJ18WOL/ICh7cHtsIPQdBi1KJEHQ63NN+FMgTC6LPNSyacy53cgX1+buwZLKFfEEtfv0gKazzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:24:09.722526Z"},"content_sha256":"83be050996763ad68a66c2fd803543a76d801e710431761200a36c20cbcc7bf8","schema_version":"1.0","event_id":"sha256:83be050996763ad68a66c2fd803543a76d801e710431761200a36c20cbcc7bf8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IEYB6NW7DWVVVEEEJWKHSKSIWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Sequential Neural Networks with Structured Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Haoli Bai, Hao Liu, Lirong He, Zenglin Xu","submitted_at":"2017-05-24T10:52:19Z","abstract_excerpt":"Unsupervised structure learning in high-dimensional time series data has attracted a lot of research interests. For example, segmenting and labelling high dimensional time series can be helpful in behavior understanding and medical diagnosis. Recent advances in generative sequential modeling have suggested to combine recurrent neural networks with state space models (e.g., Hidden Markov Models). This combination can model not only the long term dependency in sequential data, but also the uncertainty included in the hidden states. Inheriting these advantages of stochastic neural sequential mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08695","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":"2026-05-18T00:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MhqR5zBVGyOukV+3I8Va9nuC0hHhaa7p3ImHTCED433eEQKyR5KrzwC7JiEFLIoYRx4ThKwEaVNthC4a180xBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:24:09.722882Z"},"content_sha256":"bf452a0ae449e7cf54c10a6c8eb34112a3a8e94be191be6ec32469866632cc17","schema_version":"1.0","event_id":"sha256:bf452a0ae449e7cf54c10a6c8eb34112a3a8e94be191be6ec32469866632cc17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEYB6NW7DWVVVEEEJWKHSKSIWT/bundle.json","state_url":"https://pith.science/pith/IEYB6NW7DWVVVEEEJWKHSKSIWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEYB6NW7DWVVVEEEJWKHSKSIWT/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":"2026-06-04T18:24:09Z","links":{"resolver":"https://pith.science/pith/IEYB6NW7DWVVVEEEJWKHSKSIWT","bundle":"https://pith.science/pith/IEYB6NW7DWVVVEEEJWKHSKSIWT/bundle.json","state":"https://pith.science/pith/IEYB6NW7DWVVVEEEJWKHSKSIWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEYB6NW7DWVVVEEEJWKHSKSIWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IEYB6NW7DWVVVEEEJWKHSKSIWT","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":"932ef9fa634167ddfaa4c56faf1fa4f1014467d6a0f95f04442bfb9532f7d519","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-24T10:52:19Z","title_canon_sha256":"4044462b4bb2e6c267babe7b317c7964c64ab1aec864ebb24fe8d711b0027c31"},"schema_version":"1.0","source":{"id":"1705.08695","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08695","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08695v1","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08695","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"IEYB6NW7DWVV","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IEYB6NW7DWVVVEEE","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IEYB6NW7","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:bf452a0ae449e7cf54c10a6c8eb34112a3a8e94be191be6ec32469866632cc17","target":"graph","created_at":"2026-05-18T00:43:44Z","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":"Unsupervised structure learning in high-dimensional time series data has attracted a lot of research interests. For example, segmenting and labelling high dimensional time series can be helpful in behavior understanding and medical diagnosis. Recent advances in generative sequential modeling have suggested to combine recurrent neural networks with state space models (e.g., Hidden Markov Models). This combination can model not only the long term dependency in sequential data, but also the uncertainty included in the hidden states. Inheriting these advantages of stochastic neural sequential mode","authors_text":"Haoli Bai, Hao Liu, Lirong He, Zenglin Xu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-24T10:52:19Z","title":"Stochastic Sequential Neural Networks with Structured Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08695","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":"sha256:83be050996763ad68a66c2fd803543a76d801e710431761200a36c20cbcc7bf8","target":"record","created_at":"2026-05-18T00:43:44Z","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":"932ef9fa634167ddfaa4c56faf1fa4f1014467d6a0f95f04442bfb9532f7d519","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-24T10:52:19Z","title_canon_sha256":"4044462b4bb2e6c267babe7b317c7964c64ab1aec864ebb24fe8d711b0027c31"},"schema_version":"1.0","source":{"id":"1705.08695","kind":"arxiv","version":1}},"canonical_sha256":"41301f36df1dab5a90844d94792a48b4f26a5129b1fd3bad4a27730445cfbe18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41301f36df1dab5a90844d94792a48b4f26a5129b1fd3bad4a27730445cfbe18","first_computed_at":"2026-05-18T00:43:44.559275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:44.559275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WCgaTB+P9pyrROAiGW6YoSuD6YLDIDl+i1UORg2322dwNRTa4WO/h0B/SU+NHxEPxp6G6GhbWU+hwGfbyVFWCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:44.559780Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08695","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83be050996763ad68a66c2fd803543a76d801e710431761200a36c20cbcc7bf8","sha256:bf452a0ae449e7cf54c10a6c8eb34112a3a8e94be191be6ec32469866632cc17"],"state_sha256":"d7ca5f866c85cc28dff403a9b4e3fa9b91b4ce86fd35b106d2f2374cd5c31343"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aa/vsUDItdgF6gWr1pnqdtZNsDym2rqYTtQHK1IPdpYcFIy03RZd6cgGzoMloaqmmI+5GVidITWAPQzG8vX3CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T18:24:09.724846Z","bundle_sha256":"22af9d8c68df1add9b3c5757922c8e4f20ec3647f46ae0492b73996a61a3688b"}}