{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:7S5M46QU6CXWZTUOXAF5LTGDCV","short_pith_number":"pith:7S5M46QU","canonical_record":{"source":{"id":"1606.05320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-16T19:13:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5db02bf400f20feb99cf3cfe6fa3e8f73087e0b53cb093008e12a0a81a7c0701","abstract_canon_sha256":"da30a020ea3738a833db0f9307ce71b43666192f3850a01af96f4f3dddc7fbc1"},"schema_version":"1.0"},"canonical_sha256":"fcbace7a14f0af6cce8eb80bd5ccc31569ae24f80b1be345683a23a603c58c01","source":{"kind":"arxiv","id":"1606.05320","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05320","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05320v2","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05320","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"7S5M46QU6CXW","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7S5M46QU6CXWZTUO","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7S5M46QU","created_at":"2026-05-18T12:30:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:7S5M46QU6CXWZTUOXAF5LTGDCV","target":"record","payload":{"canonical_record":{"source":{"id":"1606.05320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-16T19:13:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5db02bf400f20feb99cf3cfe6fa3e8f73087e0b53cb093008e12a0a81a7c0701","abstract_canon_sha256":"da30a020ea3738a833db0f9307ce71b43666192f3850a01af96f4f3dddc7fbc1"},"schema_version":"1.0"},"canonical_sha256":"fcbace7a14f0af6cce8eb80bd5ccc31569ae24f80b1be345683a23a603c58c01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:32.459211Z","signature_b64":"9B0HQLHLgWnjZyPwclzIWFKJFZBJ6RXsyDHoFOxN5yux4I1JlE2RwddUV0aYNw3Y6Ee8hPytoxDdAfnV2sCABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcbace7a14f0af6cce8eb80bd5ccc31569ae24f80b1be345683a23a603c58c01","last_reissued_at":"2026-05-18T01:03:32.458554Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:32.458554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.05320","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a7xSHiyQRSX9f77MNQ3F2sQBWGjyBTfsjDdtJfIqGLVML34sU9mpL8oL0l/q+2sc6Sl+1sqmLMmFSJOCZ1mNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:16:48.488399Z"},"content_sha256":"9c8fe49407c2c9a0c9eb3142cf6a064d981ee97c14e3aa9dc8d3a2ce09bd3963","schema_version":"1.0","event_id":"sha256:9c8fe49407c2c9a0c9eb3142cf6a064d981ee97c14e3aa9dc8d3a2ce09bd3963"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:7S5M46QU6CXWZTUOXAF5LTGDCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Finale Doshi-Velez, Viktoriya Krakovna","submitted_at":"2016-06-16T19:13:52Z","abstract_excerpt":"As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks (RNNs), state of the art models in speech recognition and translation. Our approach to increasing interpretability is by combining an RNN with a hidden Markov model (HMM), a simpler and more transparent model. We explore various combinations of RNNs and HMMs: an HMM trained on LSTM states; a hybrid model where an HMM is tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05320","kind":"arxiv","version":2},"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":"2026-05-18T01:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vkw7fJ3Zb6ogjjzVQzhoAmh6QOFiDuOncbkkgn9jaDWM7zOY4Q48F4Y3NjVS8ztH9MFnhLSRU9oWSRks6DDKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:16:48.488750Z"},"content_sha256":"efb5ec3100bcc9eb295811fd22ae14b4ddf8bd11127ccfde66d2ebbdcc5a394f","schema_version":"1.0","event_id":"sha256:efb5ec3100bcc9eb295811fd22ae14b4ddf8bd11127ccfde66d2ebbdcc5a394f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7S5M46QU6CXWZTUOXAF5LTGDCV/bundle.json","state_url":"https://pith.science/pith/7S5M46QU6CXWZTUOXAF5LTGDCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7S5M46QU6CXWZTUOXAF5LTGDCV/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":"2026-05-28T01:16:48Z","links":{"resolver":"https://pith.science/pith/7S5M46QU6CXWZTUOXAF5LTGDCV","bundle":"https://pith.science/pith/7S5M46QU6CXWZTUOXAF5LTGDCV/bundle.json","state":"https://pith.science/pith/7S5M46QU6CXWZTUOXAF5LTGDCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7S5M46QU6CXWZTUOXAF5LTGDCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:7S5M46QU6CXWZTUOXAF5LTGDCV","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":"da30a020ea3738a833db0f9307ce71b43666192f3850a01af96f4f3dddc7fbc1","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-16T19:13:52Z","title_canon_sha256":"5db02bf400f20feb99cf3cfe6fa3e8f73087e0b53cb093008e12a0a81a7c0701"},"schema_version":"1.0","source":{"id":"1606.05320","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05320","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05320v2","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05320","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"7S5M46QU6CXW","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7S5M46QU6CXWZTUO","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7S5M46QU","created_at":"2026-05-18T12:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:efb5ec3100bcc9eb295811fd22ae14b4ddf8bd11127ccfde66d2ebbdcc5a394f","target":"graph","created_at":"2026-05-18T01:03:32Z","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":"As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks (RNNs), state of the art models in speech recognition and translation. Our approach to increasing interpretability is by combining an RNN with a hidden Markov model (HMM), a simpler and more transparent model. We explore various combinations of RNNs and HMMs: an HMM trained on LSTM states; a hybrid model where an HMM is tr","authors_text":"Finale Doshi-Velez, Viktoriya Krakovna","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-16T19:13:52Z","title":"Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05320","kind":"arxiv","version":2},"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":"sha256:9c8fe49407c2c9a0c9eb3142cf6a064d981ee97c14e3aa9dc8d3a2ce09bd3963","target":"record","created_at":"2026-05-18T01:03:32Z","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":"da30a020ea3738a833db0f9307ce71b43666192f3850a01af96f4f3dddc7fbc1","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-16T19:13:52Z","title_canon_sha256":"5db02bf400f20feb99cf3cfe6fa3e8f73087e0b53cb093008e12a0a81a7c0701"},"schema_version":"1.0","source":{"id":"1606.05320","kind":"arxiv","version":2}},"canonical_sha256":"fcbace7a14f0af6cce8eb80bd5ccc31569ae24f80b1be345683a23a603c58c01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcbace7a14f0af6cce8eb80bd5ccc31569ae24f80b1be345683a23a603c58c01","first_computed_at":"2026-05-18T01:03:32.458554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:32.458554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9B0HQLHLgWnjZyPwclzIWFKJFZBJ6RXsyDHoFOxN5yux4I1JlE2RwddUV0aYNw3Y6Ee8hPytoxDdAfnV2sCABg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:32.459211Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.05320","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c8fe49407c2c9a0c9eb3142cf6a064d981ee97c14e3aa9dc8d3a2ce09bd3963","sha256:efb5ec3100bcc9eb295811fd22ae14b4ddf8bd11127ccfde66d2ebbdcc5a394f"],"state_sha256":"a7db3b1e92646b1a10bfbd4f97424fec780a7b31f91c3297c2c19e510e056a8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pb9mfsldKlsHpDpUmeIzl+kVjWVd3uysJWWNfz6NZncWG/f/5+dcnNaJ8Ojl1spJW20WJlHaSN7q9t7ZL312CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:16:48.490765Z","bundle_sha256":"c382f03a361746fb4f6a23a880ca5cbd109c6105fc7983743f8f36aedf6e0e5f"}}