{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:YIY2YKXV2YXNUPBNB3CUXXQTAT","short_pith_number":"pith:YIY2YKXV","canonical_record":{"source":{"id":"1606.07461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T20:20:39Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"256f9bf858499001f3b0c51732d39c39ba566599d8c4a1216e7dce364a68d277","abstract_canon_sha256":"f1781cafa95ec59b2295a25824fe5aad1a1d70b2d2aa91ad8d33a1f178ee8342"},"schema_version":"1.0"},"canonical_sha256":"c231ac2af5d62eda3c2d0ec54bde1304fba0bcee5de6ca259fdb21dbd935e8ac","source":{"kind":"arxiv","id":"1606.07461","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.07461","created_at":"2026-05-18T00:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"1606.07461v2","created_at":"2026-05-18T00:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07461","created_at":"2026-05-18T00:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"YIY2YKXV2YXN","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YIY2YKXV2YXNUPBN","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YIY2YKXV","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:YIY2YKXV2YXNUPBNB3CUXXQTAT","target":"record","payload":{"canonical_record":{"source":{"id":"1606.07461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T20:20:39Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"256f9bf858499001f3b0c51732d39c39ba566599d8c4a1216e7dce364a68d277","abstract_canon_sha256":"f1781cafa95ec59b2295a25824fe5aad1a1d70b2d2aa91ad8d33a1f178ee8342"},"schema_version":"1.0"},"canonical_sha256":"c231ac2af5d62eda3c2d0ec54bde1304fba0bcee5de6ca259fdb21dbd935e8ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:52.048029Z","signature_b64":"6OC05mNkK8v90bwIm3R5LiM4E9v32d/EiU1PCg7iqNF2Ap0YytVloNLfe3gfhIb5Kghb4kqoFGOWz0NSwZzxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c231ac2af5d62eda3c2d0ec54bde1304fba0bcee5de6ca259fdb21dbd935e8ac","last_reissued_at":"2026-05-18T00:31:52.047409Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:52.047409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.07461","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":"2026-05-18T00:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qTfXIZJm+uV8Vno9WAd0/IiNjGzRPeLapShyg9wtw/7ySbj9ZqId5nvy55xdnIUve8g0wkPpYFPCkD8kcbLkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:46:43.815987Z"},"content_sha256":"747507f25c7ff14d8ecd11bd7cd19a634f64ce3666e6035ac3d886df4159445d","schema_version":"1.0","event_id":"sha256:747507f25c7ff14d8ecd11bd7cd19a634f64ce3666e6035ac3d886df4159445d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:YIY2YKXV2YXNUPBNB3CUXXQTAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Hanspeter Pfister, Hendrik Strobelt, Sebastian Gehrmann","submitted_at":"2016-06-23T20:20:39Z","abstract_excerpt":"Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better understanding these models have studied the changes in hidden state representations over time and noticed some interpretable patterns but also significant noise. In this work, we present LSTMVIS, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics. The tool allows users to select a hypothes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07461","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":"2026-05-18T00:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XFRCH4uQT/ZUDPhWP5muk83N286qKjhN4kRMkhrmEuuAqP1aYVvS2+7Uka4AjMF4NMv5gFxvmdn4IWvugqb2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:46:43.816365Z"},"content_sha256":"6364fd178f7d7d70d6a7bcfe068751ca62645ce2ca1cc76d72460eefdec74303","schema_version":"1.0","event_id":"sha256:6364fd178f7d7d70d6a7bcfe068751ca62645ce2ca1cc76d72460eefdec74303"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIY2YKXV2YXNUPBNB3CUXXQTAT/bundle.json","state_url":"https://pith.science/pith/YIY2YKXV2YXNUPBNB3CUXXQTAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIY2YKXV2YXNUPBNB3CUXXQTAT/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":"2026-05-26T23:46:43Z","links":{"resolver":"https://pith.science/pith/YIY2YKXV2YXNUPBNB3CUXXQTAT","bundle":"https://pith.science/pith/YIY2YKXV2YXNUPBNB3CUXXQTAT/bundle.json","state":"https://pith.science/pith/YIY2YKXV2YXNUPBNB3CUXXQTAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIY2YKXV2YXNUPBNB3CUXXQTAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:YIY2YKXV2YXNUPBNB3CUXXQTAT","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":"f1781cafa95ec59b2295a25824fe5aad1a1d70b2d2aa91ad8d33a1f178ee8342","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T20:20:39Z","title_canon_sha256":"256f9bf858499001f3b0c51732d39c39ba566599d8c4a1216e7dce364a68d277"},"schema_version":"1.0","source":{"id":"1606.07461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.07461","created_at":"2026-05-18T00:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"1606.07461v2","created_at":"2026-05-18T00:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07461","created_at":"2026-05-18T00:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"YIY2YKXV2YXN","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YIY2YKXV2YXNUPBN","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YIY2YKXV","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:6364fd178f7d7d70d6a7bcfe068751ca62645ce2ca1cc76d72460eefdec74303","target":"graph","created_at":"2026-05-18T00:31:52Z","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":"Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better understanding these models have studied the changes in hidden state representations over time and noticed some interpretable patterns but also significant noise. In this work, we present LSTMVIS, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics. The tool allows users to select a hypothes","authors_text":"Alexander M. Rush, Hanspeter Pfister, Hendrik Strobelt, Sebastian Gehrmann","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T20:20:39Z","title":"LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07461","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":"sha256:747507f25c7ff14d8ecd11bd7cd19a634f64ce3666e6035ac3d886df4159445d","target":"record","created_at":"2026-05-18T00:31:52Z","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":"f1781cafa95ec59b2295a25824fe5aad1a1d70b2d2aa91ad8d33a1f178ee8342","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T20:20:39Z","title_canon_sha256":"256f9bf858499001f3b0c51732d39c39ba566599d8c4a1216e7dce364a68d277"},"schema_version":"1.0","source":{"id":"1606.07461","kind":"arxiv","version":2}},"canonical_sha256":"c231ac2af5d62eda3c2d0ec54bde1304fba0bcee5de6ca259fdb21dbd935e8ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c231ac2af5d62eda3c2d0ec54bde1304fba0bcee5de6ca259fdb21dbd935e8ac","first_computed_at":"2026-05-18T00:31:52.047409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:52.047409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6OC05mNkK8v90bwIm3R5LiM4E9v32d/EiU1PCg7iqNF2Ap0YytVloNLfe3gfhIb5Kghb4kqoFGOWz0NSwZzxBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:52.048029Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.07461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:747507f25c7ff14d8ecd11bd7cd19a634f64ce3666e6035ac3d886df4159445d","sha256:6364fd178f7d7d70d6a7bcfe068751ca62645ce2ca1cc76d72460eefdec74303"],"state_sha256":"c62f3837def8ef61a982a8a899f1a8a8f2eb92c4cddc24373f7d46776705d1b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wPAuKOYm2D/78bsl6EJ3KfejBRf774citGgKFYptPL0j0ujvTqtPoqBrtEtYNLS8reIdPGWGPjX/KPJPVj70Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T23:46:43.818616Z","bundle_sha256":"ccfd406cf8913b1837b551a29ff10a21c96bdd77e12e26d256d6730cf508231f"}}