{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4QB3MBVV4A3NW6ITUBHH4VEIEJ","short_pith_number":"pith:4QB3MBVV","canonical_record":{"source":{"id":"1710.04748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-12T23:41:02Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"f33118c5aecc0afe5e21fc65d634ba6014aac19a6969fb477504f614a4c58127","abstract_canon_sha256":"206d79c076f58f82c2ca57743243c700c52aec355c9aad1ba6eef3192c08ff4e"},"schema_version":"1.0"},"canonical_sha256":"e403b606b5e036db7913a04e7e5488224ed0dbf220be81fa998131041856f257","source":{"kind":"arxiv","id":"1710.04748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04748","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04748v1","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04748","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"pith_short_12","alias_value":"4QB3MBVV4A3N","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4QB3MBVV4A3NW6IT","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4QB3MBVV","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4QB3MBVV4A3NW6ITUBHH4VEIEJ","target":"record","payload":{"canonical_record":{"source":{"id":"1710.04748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-12T23:41:02Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"f33118c5aecc0afe5e21fc65d634ba6014aac19a6969fb477504f614a4c58127","abstract_canon_sha256":"206d79c076f58f82c2ca57743243c700c52aec355c9aad1ba6eef3192c08ff4e"},"schema_version":"1.0"},"canonical_sha256":"e403b606b5e036db7913a04e7e5488224ed0dbf220be81fa998131041856f257","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:56.843541Z","signature_b64":"dryBFB4d/Dek1OU77cAYiu0RBCvmTkFkpxwvu7LYGWg5GN02mVE/mW9Ay1MrdVMte25qSDdp1giL8+j+m0e5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e403b606b5e036db7913a04e7e5488224ed0dbf220be81fa998131041856f257","last_reissued_at":"2026-05-18T00:32:56.842846Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:56.842846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.04748","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":"2026-05-18T00:32:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XG9j0ShtKQRJZOTnKoAwJQM0KWCOd2r+j259JdBaHm2O1sAksphvLnC7xL3hcywsBnEGx/krgAnXOA3nYNISAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:49:57.475788Z"},"content_sha256":"20254829922e091422d83f85b531a98fa52e6251233f1c56b27e9f90bd6493ce","schema_version":"1.0","event_id":"sha256:20254829922e091422d83f85b531a98fa52e6251233f1c56b27e9f90bd6493ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4QB3MBVV4A3NW6ITUBHH4VEIEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HyperENTM: Evolving Scalable Neural Turing Machines through HyperNEAT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Jakob Merrild, Mikkel Angaju Rasmussen, Sebastian Risi","submitted_at":"2017-10-12T23:41:02Z","abstract_excerpt":"Recent developments within memory-augmented neural networks have solved sequential problems requiring long-term memory, which are intractable for traditional neural networks. However, current approaches still struggle to scale to large memory sizes and sequence lengths. In this paper we show how access to memory can be encoded geometrically through a HyperNEAT-based Neural Turing Machine (HyperENTM). We demonstrate that using the indirect HyperNEAT encoding allows for training on small memory vectors in a bit-vector copy task and then applying the knowledge gained from such training to speed u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04748","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":"2026-05-18T00:32:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"babmDWJIhUR4zbzRyOq/75wIqjdp9L3ZnlOl6yVeQkjG2Hrsw9pT95zlFPagfctlhAc3+FFMUWVgNHo82ZHfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:49:57.476121Z"},"content_sha256":"7d484f450ab1f43ca05fdc8ccfc5d5340a002b4dfbd33c8ca91799941fd22119","schema_version":"1.0","event_id":"sha256:7d484f450ab1f43ca05fdc8ccfc5d5340a002b4dfbd33c8ca91799941fd22119"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4QB3MBVV4A3NW6ITUBHH4VEIEJ/bundle.json","state_url":"https://pith.science/pith/4QB3MBVV4A3NW6ITUBHH4VEIEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4QB3MBVV4A3NW6ITUBHH4VEIEJ/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":"2026-05-30T07:49:57Z","links":{"resolver":"https://pith.science/pith/4QB3MBVV4A3NW6ITUBHH4VEIEJ","bundle":"https://pith.science/pith/4QB3MBVV4A3NW6ITUBHH4VEIEJ/bundle.json","state":"https://pith.science/pith/4QB3MBVV4A3NW6ITUBHH4VEIEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4QB3MBVV4A3NW6ITUBHH4VEIEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4QB3MBVV4A3NW6ITUBHH4VEIEJ","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":"206d79c076f58f82c2ca57743243c700c52aec355c9aad1ba6eef3192c08ff4e","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-12T23:41:02Z","title_canon_sha256":"f33118c5aecc0afe5e21fc65d634ba6014aac19a6969fb477504f614a4c58127"},"schema_version":"1.0","source":{"id":"1710.04748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04748","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04748v1","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04748","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"pith_short_12","alias_value":"4QB3MBVV4A3N","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4QB3MBVV4A3NW6IT","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4QB3MBVV","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:7d484f450ab1f43ca05fdc8ccfc5d5340a002b4dfbd33c8ca91799941fd22119","target":"graph","created_at":"2026-05-18T00:32:56Z","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":"Recent developments within memory-augmented neural networks have solved sequential problems requiring long-term memory, which are intractable for traditional neural networks. However, current approaches still struggle to scale to large memory sizes and sequence lengths. In this paper we show how access to memory can be encoded geometrically through a HyperNEAT-based Neural Turing Machine (HyperENTM). We demonstrate that using the indirect HyperNEAT encoding allows for training on small memory vectors in a bit-vector copy task and then applying the knowledge gained from such training to speed u","authors_text":"Jakob Merrild, Mikkel Angaju Rasmussen, Sebastian Risi","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-12T23:41:02Z","title":"HyperENTM: Evolving Scalable Neural Turing Machines through HyperNEAT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04748","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":"sha256:20254829922e091422d83f85b531a98fa52e6251233f1c56b27e9f90bd6493ce","target":"record","created_at":"2026-05-18T00:32:56Z","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":"206d79c076f58f82c2ca57743243c700c52aec355c9aad1ba6eef3192c08ff4e","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-12T23:41:02Z","title_canon_sha256":"f33118c5aecc0afe5e21fc65d634ba6014aac19a6969fb477504f614a4c58127"},"schema_version":"1.0","source":{"id":"1710.04748","kind":"arxiv","version":1}},"canonical_sha256":"e403b606b5e036db7913a04e7e5488224ed0dbf220be81fa998131041856f257","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e403b606b5e036db7913a04e7e5488224ed0dbf220be81fa998131041856f257","first_computed_at":"2026-05-18T00:32:56.842846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:56.842846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dryBFB4d/Dek1OU77cAYiu0RBCvmTkFkpxwvu7LYGWg5GN02mVE/mW9Ay1MrdVMte25qSDdp1giL8+j+m0e5Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:56.843541Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.04748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20254829922e091422d83f85b531a98fa52e6251233f1c56b27e9f90bd6493ce","sha256:7d484f450ab1f43ca05fdc8ccfc5d5340a002b4dfbd33c8ca91799941fd22119"],"state_sha256":"16a7ed768d457afdeb654218ec9bdefb49b0f5f29b3b171d56dd265c8c3c9565"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBVERibTUD90+O97buLT8uIxlDC5B3PPUM342kO1kfdS1TJcwB0maqZPCfWGcJP6jJhxdKXQkzPFU4BobsGJAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:49:57.478109Z","bundle_sha256":"17196491b9e3531a133359c9255469ba4509d9da7fff20110a403ba094eafc7e"}}