{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XJVR4DY3UKIIT2E3REILCRBP2C","short_pith_number":"pith:XJVR4DY3","canonical_record":{"source":{"id":"1709.03714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T07:39:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"787cf9a869ae1d2b94295937e5e9abc7981a7510b2d68200d1c0a3159a44612b","abstract_canon_sha256":"b1ec7206fcec763462d863b5e075942094abaaebbbc8866fa261e5b12d33b86b"},"schema_version":"1.0"},"canonical_sha256":"ba6b1e0f1ba29089e89b8910b1442fd08805e3b87d63dc336227e1bec244c7f9","source":{"kind":"arxiv","id":"1709.03714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03714","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03714v1","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03714","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"XJVR4DY3UKII","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XJVR4DY3UKIIT2E3","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XJVR4DY3","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XJVR4DY3UKIIT2E3REILCRBP2C","target":"record","payload":{"canonical_record":{"source":{"id":"1709.03714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T07:39:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"787cf9a869ae1d2b94295937e5e9abc7981a7510b2d68200d1c0a3159a44612b","abstract_canon_sha256":"b1ec7206fcec763462d863b5e075942094abaaebbbc8866fa261e5b12d33b86b"},"schema_version":"1.0"},"canonical_sha256":"ba6b1e0f1ba29089e89b8910b1442fd08805e3b87d63dc336227e1bec244c7f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:03.414659Z","signature_b64":"MW6G1ga3LZwiYcO1eFE+PY/9OS7ih7WsfAs6YZj0fQby5oa6217KTTXD30aNocQms3lWasv/K6uKkpwX/01nBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba6b1e0f1ba29089e89b8910b1442fd08805e3b87d63dc336227e1bec244c7f9","last_reissued_at":"2026-05-18T00:35:03.413885Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:03.413885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.03714","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":"2026-05-18T00:35:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"od5EY44AAsDVtot0Iqe/A57gx0qHBEPIz+i96JuUL4S0FM2wXBkoYwhktTrmoO4gOVPNa8K89fr4iq1eXcjUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T06:00:02.976352Z"},"content_sha256":"a2d82763631d22f1021bf9c73cb880ee2c447abad5de661a6832415b2c6e7a96","schema_version":"1.0","event_id":"sha256:a2d82763631d22f1021bf9c73cb880ee2c447abad5de661a6832415b2c6e7a96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XJVR4DY3UKIIT2E3REILCRBP2C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RRA: Recurrent Residual Attention for Sequence Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cheng Wang","submitted_at":"2017-09-12T07:39:43Z","abstract_excerpt":"In this paper, we propose a recurrent neural network (RNN) with residual attention (RRA) to learn long-range dependencies from sequential data. We propose to add residual connections across timesteps to RNN, which explicitly enhances the interaction between current state and hidden states that are several timesteps apart. This also allows training errors to be directly back-propagated through residual connections and effectively alleviates gradient vanishing problem. We further reformulate an attention mechanism over residual connections. An attention gate is defined to summarize the individua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03714","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":"2026-05-18T00:35:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yWtXj+fM3QLC1/3gtdi5YZakDjgDxcWfH4qfFjKhRR/tbqAeL0B78+jT3CUJbSS4cJUC6CHx5FEdiWvBb++HCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T06:00:02.976713Z"},"content_sha256":"8ef06e658031de84e461b3e63c86e1b3ec510fe021e99c87ff972e272d57d79e","schema_version":"1.0","event_id":"sha256:8ef06e658031de84e461b3e63c86e1b3ec510fe021e99c87ff972e272d57d79e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJVR4DY3UKIIT2E3REILCRBP2C/bundle.json","state_url":"https://pith.science/pith/XJVR4DY3UKIIT2E3REILCRBP2C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJVR4DY3UKIIT2E3REILCRBP2C/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":"2026-06-02T06:00:02Z","links":{"resolver":"https://pith.science/pith/XJVR4DY3UKIIT2E3REILCRBP2C","bundle":"https://pith.science/pith/XJVR4DY3UKIIT2E3REILCRBP2C/bundle.json","state":"https://pith.science/pith/XJVR4DY3UKIIT2E3REILCRBP2C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJVR4DY3UKIIT2E3REILCRBP2C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XJVR4DY3UKIIT2E3REILCRBP2C","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":"b1ec7206fcec763462d863b5e075942094abaaebbbc8866fa261e5b12d33b86b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T07:39:43Z","title_canon_sha256":"787cf9a869ae1d2b94295937e5e9abc7981a7510b2d68200d1c0a3159a44612b"},"schema_version":"1.0","source":{"id":"1709.03714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03714","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03714v1","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03714","created_at":"2026-05-18T00:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"XJVR4DY3UKII","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XJVR4DY3UKIIT2E3","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XJVR4DY3","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:8ef06e658031de84e461b3e63c86e1b3ec510fe021e99c87ff972e272d57d79e","target":"graph","created_at":"2026-05-18T00:35:03Z","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":"In this paper, we propose a recurrent neural network (RNN) with residual attention (RRA) to learn long-range dependencies from sequential data. We propose to add residual connections across timesteps to RNN, which explicitly enhances the interaction between current state and hidden states that are several timesteps apart. This also allows training errors to be directly back-propagated through residual connections and effectively alleviates gradient vanishing problem. We further reformulate an attention mechanism over residual connections. An attention gate is defined to summarize the individua","authors_text":"Cheng Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T07:39:43Z","title":"RRA: Recurrent Residual Attention for Sequence Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03714","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:a2d82763631d22f1021bf9c73cb880ee2c447abad5de661a6832415b2c6e7a96","target":"record","created_at":"2026-05-18T00:35:03Z","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":"b1ec7206fcec763462d863b5e075942094abaaebbbc8866fa261e5b12d33b86b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T07:39:43Z","title_canon_sha256":"787cf9a869ae1d2b94295937e5e9abc7981a7510b2d68200d1c0a3159a44612b"},"schema_version":"1.0","source":{"id":"1709.03714","kind":"arxiv","version":1}},"canonical_sha256":"ba6b1e0f1ba29089e89b8910b1442fd08805e3b87d63dc336227e1bec244c7f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba6b1e0f1ba29089e89b8910b1442fd08805e3b87d63dc336227e1bec244c7f9","first_computed_at":"2026-05-18T00:35:03.413885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:03.413885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MW6G1ga3LZwiYcO1eFE+PY/9OS7ih7WsfAs6YZj0fQby5oa6217KTTXD30aNocQms3lWasv/K6uKkpwX/01nBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:03.414659Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.03714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2d82763631d22f1021bf9c73cb880ee2c447abad5de661a6832415b2c6e7a96","sha256:8ef06e658031de84e461b3e63c86e1b3ec510fe021e99c87ff972e272d57d79e"],"state_sha256":"f8a9613ea044d92a88252c3cbaed01d2272aa7c30be47f552efd250d178f8d35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ZzORkvJnq1OEh3YI/X2BZYmcHGauuZWF+Ou786DdfJu0AczXOPgijt1p51K10lHqrYyZaIaffYBIspps56VDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T06:00:02.978981Z","bundle_sha256":"8480922b4b0f2def550f99f8d37c65b9f16438ec06e3277b412d5eba559a4c70"}}