{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:EVHL6SDWQZ7HX55S756ZMUF5BW","short_pith_number":"pith:EVHL6SDW","canonical_record":{"source":{"id":"1901.08437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T14:59:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fdc2489e66b9b8209fdc8d1f39a8d075f9b8038c65e3e78afad66a4dd5d4aed3","abstract_canon_sha256":"9b283e4255cee890464a107e55bced04d465cd66ea5749749fc451a23d0dbaf3"},"schema_version":"1.0"},"canonical_sha256":"254ebf4876867e7bf7b2ff7d9650bd0d92b79d6e561dbb58001b047cd1229b12","source":{"kind":"arxiv","id":"1901.08437","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08437","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08437v1","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08437","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"pith_short_12","alias_value":"EVHL6SDWQZ7H","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EVHL6SDWQZ7HX55S","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EVHL6SDW","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:EVHL6SDWQZ7HX55S756ZMUF5BW","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T14:59:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fdc2489e66b9b8209fdc8d1f39a8d075f9b8038c65e3e78afad66a4dd5d4aed3","abstract_canon_sha256":"9b283e4255cee890464a107e55bced04d465cd66ea5749749fc451a23d0dbaf3"},"schema_version":"1.0"},"canonical_sha256":"254ebf4876867e7bf7b2ff7d9650bd0d92b79d6e561dbb58001b047cd1229b12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:35.453791Z","signature_b64":"4os2eIfxJ599A1mHCZYVGjFRcTvdShJpZ4/kZsni1pMdF5HcumRNSFiXSMU/q65AED4xGnT5F+FINz6k1S7zBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"254ebf4876867e7bf7b2ff7d9650bd0d92b79d6e561dbb58001b047cd1229b12","last_reissued_at":"2026-05-17T23:55:35.453236Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:35.453236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08437","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":"2026-05-17T23:55:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qZlM9xhQIBaYfA7uy599A0HNxP8MVg/ZlDxHGBECZKiHSoetT84w56NPJwN1Bv2LhO5xhA05U1zRVVjfb042Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T08:23:47.166199Z"},"content_sha256":"dd13eec54f3928b87b58324e8af41b9401a5823d1c342e1ce2029bb00595016a","schema_version":"1.0","event_id":"sha256:dd13eec54f3928b87b58324e8af41b9401a5823d1c342e1ce2029bb00595016a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:EVHL6SDWQZ7HX55S756ZMUF5BW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to compress and search visual data in large-scale systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sohrab Ferdowsi","submitted_at":"2019-01-24T14:59:42Z","abstract_excerpt":"The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and hence the model capacity can be controlled. The algorithmic infrastructure is developed based on the synthesis and analysis prior models whose rate-distortion properties, as well as capacity vs. sample complexity trade-offs are carefully optimized. These models are then extended to multi-layers, namely the RRQ and the ML-STC frameworks, where the latter is f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08437","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":"2026-05-17T23:55:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hq/u7W+YHmAT4oF4Y9ujT5gxL5ypTsZsgaSxLLD6j7UOx4yf//AzZ6uZqcht/BiNmZwhmofmWQ9xwltlTifxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T08:23:47.166568Z"},"content_sha256":"507b65947401f7f953e9c562b0bc522a79ebd0d7feb613f077317b191db4e66b","schema_version":"1.0","event_id":"sha256:507b65947401f7f953e9c562b0bc522a79ebd0d7feb613f077317b191db4e66b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EVHL6SDWQZ7HX55S756ZMUF5BW/bundle.json","state_url":"https://pith.science/pith/EVHL6SDWQZ7HX55S756ZMUF5BW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EVHL6SDWQZ7HX55S756ZMUF5BW/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":"2026-06-29T08:23:47Z","links":{"resolver":"https://pith.science/pith/EVHL6SDWQZ7HX55S756ZMUF5BW","bundle":"https://pith.science/pith/EVHL6SDWQZ7HX55S756ZMUF5BW/bundle.json","state":"https://pith.science/pith/EVHL6SDWQZ7HX55S756ZMUF5BW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EVHL6SDWQZ7HX55S756ZMUF5BW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EVHL6SDWQZ7HX55S756ZMUF5BW","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":"9b283e4255cee890464a107e55bced04d465cd66ea5749749fc451a23d0dbaf3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T14:59:42Z","title_canon_sha256":"fdc2489e66b9b8209fdc8d1f39a8d075f9b8038c65e3e78afad66a4dd5d4aed3"},"schema_version":"1.0","source":{"id":"1901.08437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08437","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08437v1","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08437","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"pith_short_12","alias_value":"EVHL6SDWQZ7H","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EVHL6SDWQZ7HX55S","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EVHL6SDW","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:507b65947401f7f953e9c562b0bc522a79ebd0d7feb613f077317b191db4e66b","target":"graph","created_at":"2026-05-17T23:55:35Z","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":"The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and hence the model capacity can be controlled. The algorithmic infrastructure is developed based on the synthesis and analysis prior models whose rate-distortion properties, as well as capacity vs. sample complexity trade-offs are carefully optimized. These models are then extended to multi-layers, namely the RRQ and the ML-STC frameworks, where the latter is f","authors_text":"Sohrab Ferdowsi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T14:59:42Z","title":"Learning to compress and search visual data in large-scale systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08437","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:dd13eec54f3928b87b58324e8af41b9401a5823d1c342e1ce2029bb00595016a","target":"record","created_at":"2026-05-17T23:55:35Z","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":"9b283e4255cee890464a107e55bced04d465cd66ea5749749fc451a23d0dbaf3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T14:59:42Z","title_canon_sha256":"fdc2489e66b9b8209fdc8d1f39a8d075f9b8038c65e3e78afad66a4dd5d4aed3"},"schema_version":"1.0","source":{"id":"1901.08437","kind":"arxiv","version":1}},"canonical_sha256":"254ebf4876867e7bf7b2ff7d9650bd0d92b79d6e561dbb58001b047cd1229b12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"254ebf4876867e7bf7b2ff7d9650bd0d92b79d6e561dbb58001b047cd1229b12","first_computed_at":"2026-05-17T23:55:35.453236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:35.453236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4os2eIfxJ599A1mHCZYVGjFRcTvdShJpZ4/kZsni1pMdF5HcumRNSFiXSMU/q65AED4xGnT5F+FINz6k1S7zBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:35.453791Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd13eec54f3928b87b58324e8af41b9401a5823d1c342e1ce2029bb00595016a","sha256:507b65947401f7f953e9c562b0bc522a79ebd0d7feb613f077317b191db4e66b"],"state_sha256":"6451186315233b065d6abcbae0a8e2541a61fe313e2026bdc15a4d542333c682"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zPcuzcn2jaeGPbkrE/80fLSnC7smffuXFeIK4s/fsg2LfJ+HQXEgp9pnGZ5pDE6Vce8DcPAUaahVjNG1m2WnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T08:23:47.168482Z","bundle_sha256":"1e87764ea36796fc1cae2318621365a7231cd3e190a37a77cb663bac8682bc93"}}