{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4JPXGSRUBSQPCAWDEIWOONBX5P","short_pith_number":"pith:4JPXGSRU","canonical_record":{"source":{"id":"1709.06493","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T15:55:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f9076119d4d98fbc006ec416c97f7014718509a137ef99e563fb6560f0a886c4","abstract_canon_sha256":"90120d90eadac6364f4616f15e24ac0bc6b5025c7a71e00f4555e3ac3d099ccb"},"schema_version":"1.0"},"canonical_sha256":"e25f734a340ca0f102c3222ce73437ebeabc58b88dcdb08a749d2e30bea66246","source":{"kind":"arxiv","id":"1709.06493","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06493","created_at":"2026-05-18T00:33:48Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06493v3","created_at":"2026-05-18T00:33:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06493","created_at":"2026-05-18T00:33:48Z"},{"alias_kind":"pith_short_12","alias_value":"4JPXGSRUBSQP","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4JPXGSRUBSQPCAWD","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4JPXGSRU","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4JPXGSRUBSQPCAWDEIWOONBX5P","target":"record","payload":{"canonical_record":{"source":{"id":"1709.06493","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T15:55:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f9076119d4d98fbc006ec416c97f7014718509a137ef99e563fb6560f0a886c4","abstract_canon_sha256":"90120d90eadac6364f4616f15e24ac0bc6b5025c7a71e00f4555e3ac3d099ccb"},"schema_version":"1.0"},"canonical_sha256":"e25f734a340ca0f102c3222ce73437ebeabc58b88dcdb08a749d2e30bea66246","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:48.086600Z","signature_b64":"blRuKgpzWfJaZdTtErwXSTsa6kV7yDfufSXh0l5BaOJMiGHimGehD0+Ii3zzMilH6JhMnshdaRmrKK2qfdidBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e25f734a340ca0f102c3222ce73437ebeabc58b88dcdb08a749d2e30bea66246","last_reissued_at":"2026-05-18T00:33:48.085831Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:48.085831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.06493","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":"2026-05-18T00:33:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ToNmRtClfrNQtC67h7amT/rJc0fH2oE9OHRm8lhoHvToAvbAqAj2yd9DHBaDs0YjaTtlXd31wt5F3FvARGRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:25:32.959022Z"},"content_sha256":"df7ecdcc9a0effc7311e6ec116a4299dc479302a6477623cc891dc272e68cfcb","schema_version":"1.0","event_id":"sha256:df7ecdcc9a0effc7311e6ec116a4299dc479302a6477623cc891dc272e68cfcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4JPXGSRUBSQPCAWDEIWOONBX5P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Bowen Zhou, Wei Zhang","submitted_at":"2017-09-19T15:55:16Z","abstract_excerpt":"Learning to remember long sequences remains a challenging task for recurrent neural networks. Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning towards encoding shorter local contexts than encouraging long sequence encoding. Associative memory, which studies the compression of multiple patterns in a fixed size memory, were rarely considered in recent years. Although some recent work tries to introduce associative memory in RNN and mimic the en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06493","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":"2026-05-18T00:33:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zErPvP/z8O9qsmo7/fUci/wTyKReDnxgODpzl2FO2cFnN7yS1RSZOVK49+IjuvF104wx8U1SZ2ekjn80rkUQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:25:32.959846Z"},"content_sha256":"4141aa2b98410b3291213e0989125c4d0dd792ca7d0ffe843d049be351574fbc","schema_version":"1.0","event_id":"sha256:4141aa2b98410b3291213e0989125c4d0dd792ca7d0ffe843d049be351574fbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JPXGSRUBSQPCAWDEIWOONBX5P/bundle.json","state_url":"https://pith.science/pith/4JPXGSRUBSQPCAWDEIWOONBX5P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JPXGSRUBSQPCAWDEIWOONBX5P/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":"2026-08-09T08:25:32Z","links":{"resolver":"https://pith.science/pith/4JPXGSRUBSQPCAWDEIWOONBX5P","bundle":"https://pith.science/pith/4JPXGSRUBSQPCAWDEIWOONBX5P/bundle.json","state":"https://pith.science/pith/4JPXGSRUBSQPCAWDEIWOONBX5P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JPXGSRUBSQPCAWDEIWOONBX5P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4JPXGSRUBSQPCAWDEIWOONBX5P","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":"90120d90eadac6364f4616f15e24ac0bc6b5025c7a71e00f4555e3ac3d099ccb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T15:55:16Z","title_canon_sha256":"f9076119d4d98fbc006ec416c97f7014718509a137ef99e563fb6560f0a886c4"},"schema_version":"1.0","source":{"id":"1709.06493","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06493","created_at":"2026-05-18T00:33:48Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06493v3","created_at":"2026-05-18T00:33:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06493","created_at":"2026-05-18T00:33:48Z"},{"alias_kind":"pith_short_12","alias_value":"4JPXGSRUBSQP","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4JPXGSRUBSQPCAWD","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4JPXGSRU","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:4141aa2b98410b3291213e0989125c4d0dd792ca7d0ffe843d049be351574fbc","target":"graph","created_at":"2026-05-18T00:33:48Z","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":"Learning to remember long sequences remains a challenging task for recurrent neural networks. Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning towards encoding shorter local contexts than encouraging long sequence encoding. Associative memory, which studies the compression of multiple patterns in a fixed size memory, were rarely considered in recent years. Although some recent work tries to introduce associative memory in RNN and mimic the en","authors_text":"Bowen Zhou, Wei Zhang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T15:55:16Z","title":"Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06493","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:df7ecdcc9a0effc7311e6ec116a4299dc479302a6477623cc891dc272e68cfcb","target":"record","created_at":"2026-05-18T00:33:48Z","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":"90120d90eadac6364f4616f15e24ac0bc6b5025c7a71e00f4555e3ac3d099ccb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T15:55:16Z","title_canon_sha256":"f9076119d4d98fbc006ec416c97f7014718509a137ef99e563fb6560f0a886c4"},"schema_version":"1.0","source":{"id":"1709.06493","kind":"arxiv","version":3}},"canonical_sha256":"e25f734a340ca0f102c3222ce73437ebeabc58b88dcdb08a749d2e30bea66246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e25f734a340ca0f102c3222ce73437ebeabc58b88dcdb08a749d2e30bea66246","first_computed_at":"2026-05-18T00:33:48.085831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:48.085831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"blRuKgpzWfJaZdTtErwXSTsa6kV7yDfufSXh0l5BaOJMiGHimGehD0+Ii3zzMilH6JhMnshdaRmrKK2qfdidBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:48.086600Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06493","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df7ecdcc9a0effc7311e6ec116a4299dc479302a6477623cc891dc272e68cfcb","sha256:4141aa2b98410b3291213e0989125c4d0dd792ca7d0ffe843d049be351574fbc"],"state_sha256":"969c9af5390e1cc94056386d6af49ea1b6ff103ec15461f693944be9262ad23f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYEHmo41/YrUzxj415fH+cad54MX0EmonXTu6c9goQv2cgW0yFP+pPXGQ11zRDNSrfg1WxM4yEiclq3DA9uPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:25:32.964061Z","bundle_sha256":"0ab7284373d9510da4f0ed769d7cd6b733e9b1838ee2688c145909ccccc9bc5e"}}