{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:J7TOYVMKZ2RAEJ4UYHYCPIK6FC","short_pith_number":"pith:J7TOYVMK","canonical_record":{"source":{"id":"1708.06834","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T21:53:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d5cdf9a2eebaefee7dc92dfa152c9a58cdb742c0f0e89ec993145c83bee4e3b2","abstract_canon_sha256":"915416968c5160d1f65c1d92351678f1cd5d0c3757de38bf49686ed8736a8ce5"},"schema_version":"1.0"},"canonical_sha256":"4fe6ec558acea2022794c1f027a15e289aabcc623204787c1b5dffaad029ffe7","source":{"kind":"arxiv","id":"1708.06834","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.06834","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"1708.06834v3","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.06834","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"J7TOYVMKZ2RA","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"J7TOYVMKZ2RAEJ4U","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"J7TOYVMK","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:J7TOYVMKZ2RAEJ4UYHYCPIK6FC","target":"record","payload":{"canonical_record":{"source":{"id":"1708.06834","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T21:53:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d5cdf9a2eebaefee7dc92dfa152c9a58cdb742c0f0e89ec993145c83bee4e3b2","abstract_canon_sha256":"915416968c5160d1f65c1d92351678f1cd5d0c3757de38bf49686ed8736a8ce5"},"schema_version":"1.0"},"canonical_sha256":"4fe6ec558acea2022794c1f027a15e289aabcc623204787c1b5dffaad029ffe7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:30.800110Z","signature_b64":"TdN+6KGwJQrbnA49bCZjhWdUlnpjEaNpTRHRdPQiqqGGaPdJvbNc0XoxGbR/6EygA/o/UC5hc1X8P5MtiDHvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fe6ec558acea2022794c1f027a15e289aabcc623204787c1b5dffaad029ffe7","last_reissued_at":"2026-05-18T00:24:30.799626Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:30.799626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.06834","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:24:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGlNfUGWdS2dRd6vcPtCAa64SHeETEfRiWlNyfzYS0nG/kEnHKGzCdI8Jb2Sdke7KYOYhYwspz9T6IQ1FQwjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:36:47.581962Z"},"content_sha256":"a592ee4d8b24f9c49c56b8adec6233be74e4095eaae53fc392d8ee978ea2f388","schema_version":"1.0","event_id":"sha256:a592ee4d8b24f9c49c56b8adec6233be74e4095eaae53fc392d8ee978ea2f388"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:J7TOYVMKZ2RAEJ4UYHYCPIK6FC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Brendan Jou, Jordi Torres, Shih-Fu Chang, Victor Campos, Xavier Giro-i-Nieto","submitted_at":"2017-08-22T21:53:34Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty in capturing long term dependencies. In backpropagation through time settings, these issues are tightly coupled with the large, sequential computational graph resulting from unfolding the RNN in time. We introduce the Skip RNN model which extends existing RNN models by learning to skip state updates and shortens the effective size of the computational graph. This model can als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.06834","kind":"arxiv","version":3},"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":"2026-05-18T00:24:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"diVTl0VPvhSwsJvd2DFqagPCw9DhKN+SRRCfGGnE8v7A+RPl57rAFPtrrvNYuKUxxHqthjxcMP6Ch4vX5tKfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:36:47.583197Z"},"content_sha256":"a5b5801387f90f981bb050327049013a7b61fec3fb8a7d2862004aad127cacb8","schema_version":"1.0","event_id":"sha256:a5b5801387f90f981bb050327049013a7b61fec3fb8a7d2862004aad127cacb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J7TOYVMKZ2RAEJ4UYHYCPIK6FC/bundle.json","state_url":"https://pith.science/pith/J7TOYVMKZ2RAEJ4UYHYCPIK6FC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J7TOYVMKZ2RAEJ4UYHYCPIK6FC/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":"2026-05-27T21:36:47Z","links":{"resolver":"https://pith.science/pith/J7TOYVMKZ2RAEJ4UYHYCPIK6FC","bundle":"https://pith.science/pith/J7TOYVMKZ2RAEJ4UYHYCPIK6FC/bundle.json","state":"https://pith.science/pith/J7TOYVMKZ2RAEJ4UYHYCPIK6FC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J7TOYVMKZ2RAEJ4UYHYCPIK6FC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:J7TOYVMKZ2RAEJ4UYHYCPIK6FC","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":"915416968c5160d1f65c1d92351678f1cd5d0c3757de38bf49686ed8736a8ce5","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T21:53:34Z","title_canon_sha256":"d5cdf9a2eebaefee7dc92dfa152c9a58cdb742c0f0e89ec993145c83bee4e3b2"},"schema_version":"1.0","source":{"id":"1708.06834","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.06834","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"1708.06834v3","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.06834","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"J7TOYVMKZ2RA","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"J7TOYVMKZ2RAEJ4U","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"J7TOYVMK","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:a5b5801387f90f981bb050327049013a7b61fec3fb8a7d2862004aad127cacb8","target":"graph","created_at":"2026-05-18T00:24:30Z","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 (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty in capturing long term dependencies. In backpropagation through time settings, these issues are tightly coupled with the large, sequential computational graph resulting from unfolding the RNN in time. We introduce the Skip RNN model which extends existing RNN models by learning to skip state updates and shortens the effective size of the computational graph. This model can als","authors_text":"Brendan Jou, Jordi Torres, Shih-Fu Chang, Victor Campos, Xavier Giro-i-Nieto","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T21:53:34Z","title":"Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.06834","kind":"arxiv","version":3},"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:a592ee4d8b24f9c49c56b8adec6233be74e4095eaae53fc392d8ee978ea2f388","target":"record","created_at":"2026-05-18T00:24:30Z","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":"915416968c5160d1f65c1d92351678f1cd5d0c3757de38bf49686ed8736a8ce5","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T21:53:34Z","title_canon_sha256":"d5cdf9a2eebaefee7dc92dfa152c9a58cdb742c0f0e89ec993145c83bee4e3b2"},"schema_version":"1.0","source":{"id":"1708.06834","kind":"arxiv","version":3}},"canonical_sha256":"4fe6ec558acea2022794c1f027a15e289aabcc623204787c1b5dffaad029ffe7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fe6ec558acea2022794c1f027a15e289aabcc623204787c1b5dffaad029ffe7","first_computed_at":"2026-05-18T00:24:30.799626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:30.799626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TdN+6KGwJQrbnA49bCZjhWdUlnpjEaNpTRHRdPQiqqGGaPdJvbNc0XoxGbR/6EygA/o/UC5hc1X8P5MtiDHvCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:30.800110Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.06834","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a592ee4d8b24f9c49c56b8adec6233be74e4095eaae53fc392d8ee978ea2f388","sha256:a5b5801387f90f981bb050327049013a7b61fec3fb8a7d2862004aad127cacb8"],"state_sha256":"5b32453e34aa2d4919187c1ebb39a56d56784d7ab97197d961d7eb43282caad8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qWCteKNNwjDylU+y8wul5ux+D918TXPX9LyPznjeh0Hnk/0CAZhXSCOxWgUIiNSGccqUsdT/chqL+I6sdRs0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T21:36:47.587128Z","bundle_sha256":"7bde8180dab613f71261e497861d989edac2b15e6c1bbad57714f56154f8d371"}}