{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IRIAFAVK7P5HFWNWI3UZGOWGQU","short_pith_number":"pith:IRIAFAVK","canonical_record":{"source":{"id":"1708.04465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-15T11:52:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6995c69e4a14229e48051baced1006dce1d5e1959298c345d44c3065f8354c54","abstract_canon_sha256":"bdd0454a0600e28ac7a69a928e23ae9406ea5b121cb31b6a53ed3d810c6b0b83"},"schema_version":"1.0"},"canonical_sha256":"44500282aafbfa72d9b646e9933ac6851bf5eedff75e7feb0f475ce9b6916ca3","source":{"kind":"arxiv","id":"1708.04465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04465","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04465v1","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04465","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"pith_short_12","alias_value":"IRIAFAVK7P5H","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IRIAFAVK7P5HFWNW","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IRIAFAVK","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IRIAFAVK7P5HFWNWI3UZGOWGQU","target":"record","payload":{"canonical_record":{"source":{"id":"1708.04465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-15T11:52:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6995c69e4a14229e48051baced1006dce1d5e1959298c345d44c3065f8354c54","abstract_canon_sha256":"bdd0454a0600e28ac7a69a928e23ae9406ea5b121cb31b6a53ed3d810c6b0b83"},"schema_version":"1.0"},"canonical_sha256":"44500282aafbfa72d9b646e9933ac6851bf5eedff75e7feb0f475ce9b6916ca3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:59.259790Z","signature_b64":"YHab2uZ+BNCDcpkkrxNXyJg2BV6bZcHzpniGavetwlO4bjBEbKC9FmI8DwrBiQLUERjt1yh307R62xn0zujsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44500282aafbfa72d9b646e9933ac6851bf5eedff75e7feb0f475ce9b6916ca3","last_reissued_at":"2026-05-18T00:37:59.259355Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:59.259355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.04465","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":"2026-05-18T00:37:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xTkH0IlrNMb7lm61tpa7VGD1WQZIpohCXI2wTGqRsZBI15VTBjD5bybegL0F2c9MEmonYMZtyuCI+GQI0xXSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:25:29.544021Z"},"content_sha256":"91d83f0baa8a2c904a33d04b07a635eeea20f365391f5dad1308be7c86f347e1","schema_version":"1.0","event_id":"sha256:91d83f0baa8a2c904a33d04b07a635eeea20f365391f5dad1308be7c86f347e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IRIAFAVK7P5HFWNWI3UZGOWGQU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Actively Learning what makes a Discrete Sequence Valid","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David Janz, Jos\\'e Miguel Hern\\'andez-Lobato, Jos van der Westhuizen","submitted_at":"2017-08-15T11:52:35Z","abstract_excerpt":"Deep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensional discrete spaces. These methods work by representing discrete objects as sequences, for which powerful sequence-based deep models can be employed. Unfortunately, these techniques are significantly hindered by the fact that these generative models often produce invalid sequences."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04465","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":"2026-05-18T00:37:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D83hIjHYNXRzSNe8Ipse5SFE5y8dcQD7/zVYOWX21jfFv0FZF3PaQhc0SVxqUEcH9Jki319zXxAnZgeV9UeGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:25:29.544993Z"},"content_sha256":"d27bf5135df406afa705891ce19b6c71d15ad62de7465fb214d7367abf8840b5","schema_version":"1.0","event_id":"sha256:d27bf5135df406afa705891ce19b6c71d15ad62de7465fb214d7367abf8840b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IRIAFAVK7P5HFWNWI3UZGOWGQU/bundle.json","state_url":"https://pith.science/pith/IRIAFAVK7P5HFWNWI3UZGOWGQU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IRIAFAVK7P5HFWNWI3UZGOWGQU/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":"2026-06-05T22:25:29Z","links":{"resolver":"https://pith.science/pith/IRIAFAVK7P5HFWNWI3UZGOWGQU","bundle":"https://pith.science/pith/IRIAFAVK7P5HFWNWI3UZGOWGQU/bundle.json","state":"https://pith.science/pith/IRIAFAVK7P5HFWNWI3UZGOWGQU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IRIAFAVK7P5HFWNWI3UZGOWGQU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IRIAFAVK7P5HFWNWI3UZGOWGQU","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":"bdd0454a0600e28ac7a69a928e23ae9406ea5b121cb31b6a53ed3d810c6b0b83","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-15T11:52:35Z","title_canon_sha256":"6995c69e4a14229e48051baced1006dce1d5e1959298c345d44c3065f8354c54"},"schema_version":"1.0","source":{"id":"1708.04465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04465","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04465v1","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04465","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"pith_short_12","alias_value":"IRIAFAVK7P5H","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IRIAFAVK7P5HFWNW","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IRIAFAVK","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:d27bf5135df406afa705891ce19b6c71d15ad62de7465fb214d7367abf8840b5","target":"graph","created_at":"2026-05-18T00:37:59Z","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":"Deep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensional discrete spaces. These methods work by representing discrete objects as sequences, for which powerful sequence-based deep models can be employed. Unfortunately, these techniques are significantly hindered by the fact that these generative models often produce invalid sequences.","authors_text":"David Janz, Jos\\'e Miguel Hern\\'andez-Lobato, Jos van der Westhuizen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-15T11:52:35Z","title":"Actively Learning what makes a Discrete Sequence Valid"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04465","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":"sha256:91d83f0baa8a2c904a33d04b07a635eeea20f365391f5dad1308be7c86f347e1","target":"record","created_at":"2026-05-18T00:37:59Z","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":"bdd0454a0600e28ac7a69a928e23ae9406ea5b121cb31b6a53ed3d810c6b0b83","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-15T11:52:35Z","title_canon_sha256":"6995c69e4a14229e48051baced1006dce1d5e1959298c345d44c3065f8354c54"},"schema_version":"1.0","source":{"id":"1708.04465","kind":"arxiv","version":1}},"canonical_sha256":"44500282aafbfa72d9b646e9933ac6851bf5eedff75e7feb0f475ce9b6916ca3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44500282aafbfa72d9b646e9933ac6851bf5eedff75e7feb0f475ce9b6916ca3","first_computed_at":"2026-05-18T00:37:59.259355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:59.259355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YHab2uZ+BNCDcpkkrxNXyJg2BV6bZcHzpniGavetwlO4bjBEbKC9FmI8DwrBiQLUERjt1yh307R62xn0zujsCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:59.259790Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.04465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91d83f0baa8a2c904a33d04b07a635eeea20f365391f5dad1308be7c86f347e1","sha256:d27bf5135df406afa705891ce19b6c71d15ad62de7465fb214d7367abf8840b5"],"state_sha256":"45e3697280b25b51cc530a7fcc1087d16fb638d9f8be3d1d2b234a616e45fdd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X7K8IMga6+a4A3RB/sspkdFshfEI2vgGRcHiohm0kUE4im3SVfkCUhVxr0OmrBg2ynMxwdz+XZI11ao3b7jkDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T22:25:29.549093Z","bundle_sha256":"3fc2aef6d9ae8a50b70ac6fb95aedeaa35192784dda22c505e8c13017451a4ce"}}