{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UYNAJ4VY6PR5OZNZUL6AHLKBKI","short_pith_number":"pith:UYNAJ4VY","canonical_record":{"source":{"id":"1906.04304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T22:23:14Z","cross_cats_sorted":["cs.DB","cs.DS","stat.ML"],"title_canon_sha256":"85a8fc765766ab62c06de0da0d8d53df108efcfe3d45e79fb75546bd3c0da103","abstract_canon_sha256":"c60b57afcea904dfa9fa38160212c2ccdde4f8fb6554830ac7e7b140ee8ae3c2"},"schema_version":"1.0"},"canonical_sha256":"a61a04f2b8f3e3d765b9a2fc03ad415221f575c85e572574a368cbfe76675fee","source":{"kind":"arxiv","id":"1906.04304","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04304","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04304v1","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04304","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"pith_short_12","alias_value":"UYNAJ4VY6PR5","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UYNAJ4VY6PR5OZNZ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UYNAJ4VY","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UYNAJ4VY6PR5OZNZUL6AHLKBKI","target":"record","payload":{"canonical_record":{"source":{"id":"1906.04304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T22:23:14Z","cross_cats_sorted":["cs.DB","cs.DS","stat.ML"],"title_canon_sha256":"85a8fc765766ab62c06de0da0d8d53df108efcfe3d45e79fb75546bd3c0da103","abstract_canon_sha256":"c60b57afcea904dfa9fa38160212c2ccdde4f8fb6554830ac7e7b140ee8ae3c2"},"schema_version":"1.0"},"canonical_sha256":"a61a04f2b8f3e3d765b9a2fc03ad415221f575c85e572574a368cbfe76675fee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:39.701078Z","signature_b64":"8Gt7hlXLgl8fJImTcsQcWeIFYoiaHO9t2N6b5VZwGssHyMmS88fHJlY0CmqLVjalEeAPTnpc08jogobXRn0tBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a61a04f2b8f3e3d765b9a2fc03ad415221f575c85e572574a368cbfe76675fee","last_reissued_at":"2026-05-17T23:43:39.700534Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:39.700534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.04304","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":"2026-05-17T23:43:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYV1vu45fauX1HaTu539c+LpxLT7LmGGhuDV6T29Mb6pbUaT7VmZTD2p3llNhbfsm4hOYV9iNYaZsTjo4vuzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:24:25.680838Z"},"content_sha256":"64066bd885707c2c981ffd2db02c1639e62b32bbf3fc739fb5dc35ea60758ab1","schema_version":"1.0","event_id":"sha256:64066bd885707c2c981ffd2db02c1639e62b32bbf3fc739fb5dc35ea60758ab1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UYNAJ4VY6PR5OZNZUL6AHLKBKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning Neural Bloom Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jack W Rae, Sergey Bartunov, Timothy P Lillicrap","submitted_at":"2019-06-10T22:23:14Z","abstract_excerpt":"There has been a recent trend in training neural networks to replace data structures that have been crafted by hand, with an aim for faster execution, better accuracy, or greater compression. In this setting, a neural data structure is instantiated by training a network over many epochs of its inputs until convergence. In applications where inputs arrive at high throughput, or are ephemeral, training a network from scratch is not practical. This motivates the need for few-shot neural data structures. In this paper we explore the learning of approximate set membership over a set of data in one-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04304","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":"2026-05-17T23:43:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vv4WQJuy+tGi4vaAAKcGfx28eerNlKfdPx+QtG2qN7LhvGba7WcUNWwPHv4Vc/E5LR8qEWNWX4uDjDWphv7EBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:24:25.681638Z"},"content_sha256":"5d7965305f522863a87c8db67ac21b86138c6d909735e72317024556a7ee2fd7","schema_version":"1.0","event_id":"sha256:5d7965305f522863a87c8db67ac21b86138c6d909735e72317024556a7ee2fd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYNAJ4VY6PR5OZNZUL6AHLKBKI/bundle.json","state_url":"https://pith.science/pith/UYNAJ4VY6PR5OZNZUL6AHLKBKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYNAJ4VY6PR5OZNZUL6AHLKBKI/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":"2026-06-05T22:24:25Z","links":{"resolver":"https://pith.science/pith/UYNAJ4VY6PR5OZNZUL6AHLKBKI","bundle":"https://pith.science/pith/UYNAJ4VY6PR5OZNZUL6AHLKBKI/bundle.json","state":"https://pith.science/pith/UYNAJ4VY6PR5OZNZUL6AHLKBKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYNAJ4VY6PR5OZNZUL6AHLKBKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UYNAJ4VY6PR5OZNZUL6AHLKBKI","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":"c60b57afcea904dfa9fa38160212c2ccdde4f8fb6554830ac7e7b140ee8ae3c2","cross_cats_sorted":["cs.DB","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T22:23:14Z","title_canon_sha256":"85a8fc765766ab62c06de0da0d8d53df108efcfe3d45e79fb75546bd3c0da103"},"schema_version":"1.0","source":{"id":"1906.04304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04304","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04304v1","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04304","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"pith_short_12","alias_value":"UYNAJ4VY6PR5","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UYNAJ4VY6PR5OZNZ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UYNAJ4VY","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:5d7965305f522863a87c8db67ac21b86138c6d909735e72317024556a7ee2fd7","target":"graph","created_at":"2026-05-17T23:43:39Z","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":"There has been a recent trend in training neural networks to replace data structures that have been crafted by hand, with an aim for faster execution, better accuracy, or greater compression. In this setting, a neural data structure is instantiated by training a network over many epochs of its inputs until convergence. In applications where inputs arrive at high throughput, or are ephemeral, training a network from scratch is not practical. This motivates the need for few-shot neural data structures. In this paper we explore the learning of approximate set membership over a set of data in one-","authors_text":"Jack W Rae, Sergey Bartunov, Timothy P Lillicrap","cross_cats":["cs.DB","cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T22:23:14Z","title":"Meta-Learning Neural Bloom Filters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04304","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":"sha256:64066bd885707c2c981ffd2db02c1639e62b32bbf3fc739fb5dc35ea60758ab1","target":"record","created_at":"2026-05-17T23:43:39Z","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":"c60b57afcea904dfa9fa38160212c2ccdde4f8fb6554830ac7e7b140ee8ae3c2","cross_cats_sorted":["cs.DB","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T22:23:14Z","title_canon_sha256":"85a8fc765766ab62c06de0da0d8d53df108efcfe3d45e79fb75546bd3c0da103"},"schema_version":"1.0","source":{"id":"1906.04304","kind":"arxiv","version":1}},"canonical_sha256":"a61a04f2b8f3e3d765b9a2fc03ad415221f575c85e572574a368cbfe76675fee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a61a04f2b8f3e3d765b9a2fc03ad415221f575c85e572574a368cbfe76675fee","first_computed_at":"2026-05-17T23:43:39.700534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:39.700534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Gt7hlXLgl8fJImTcsQcWeIFYoiaHO9t2N6b5VZwGssHyMmS88fHJlY0CmqLVjalEeAPTnpc08jogobXRn0tBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:39.701078Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64066bd885707c2c981ffd2db02c1639e62b32bbf3fc739fb5dc35ea60758ab1","sha256:5d7965305f522863a87c8db67ac21b86138c6d909735e72317024556a7ee2fd7"],"state_sha256":"5076cbe6494c22be04f40189988d31553c139eee1635ed59de4ef63504bc9eb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJ+2j+MOkQlVj2UDFyadP9KL+SD1XgIwVOfFxMscLG13SfeleQUXCi1+A5r9j7UkVpeBm7gR+PneHKrcAmW4BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T22:24:25.685476Z","bundle_sha256":"4d53970910aeb4b17a98ee64c7eec53d2468b024ed83bca6ef9ed2c8647d9a7d"}}