{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OMOPYDRXHWLMRUBUQCJK56NXBA","short_pith_number":"pith:OMOPYDRX","canonical_record":{"source":{"id":"1709.06171","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-18T21:26:43Z","cross_cats_sorted":[],"title_canon_sha256":"db2b1a9f471fd87ecdc77d9d5e57c7537c8a830b88f963a71665fbef4ab1a7d9","abstract_canon_sha256":"028870c398494ff91d92cd5a0f5fa0debb2af948b9d94c2486a043932dab2012"},"schema_version":"1.0"},"canonical_sha256":"731cfc0e373d96c8d0348092aef9b70820d8dd3a46234844abd7d2a276ef9a2d","source":{"kind":"arxiv","id":"1709.06171","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06171","created_at":"2026-05-18T00:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06171v2","created_at":"2026-05-18T00:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06171","created_at":"2026-05-18T00:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"OMOPYDRXHWLM","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OMOPYDRXHWLMRUBU","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OMOPYDRX","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OMOPYDRXHWLMRUBUQCJK56NXBA","target":"record","payload":{"canonical_record":{"source":{"id":"1709.06171","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-18T21:26:43Z","cross_cats_sorted":[],"title_canon_sha256":"db2b1a9f471fd87ecdc77d9d5e57c7537c8a830b88f963a71665fbef4ab1a7d9","abstract_canon_sha256":"028870c398494ff91d92cd5a0f5fa0debb2af948b9d94c2486a043932dab2012"},"schema_version":"1.0"},"canonical_sha256":"731cfc0e373d96c8d0348092aef9b70820d8dd3a46234844abd7d2a276ef9a2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:22.350689Z","signature_b64":"ly0jF9K6QdtUnpC1aHIoQIMrpT2yXMF4DauSsh2alcHhpp6Ooeyj2xL1M8jOA7iqo0VYPg7FQj//DIQkuMooDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"731cfc0e373d96c8d0348092aef9b70820d8dd3a46234844abd7d2a276ef9a2d","last_reissued_at":"2026-05-18T00:24:22.350100Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:22.350100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.06171","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:24:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qLcHUNLJOeVhQ033Zk1hNtInCZC7GFuaOy05tu2aU/1emLHMYV7I1+1g3CSfW8V0rPSk9F8Fx+uVFG2tiHjiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T04:21:33.118627Z"},"content_sha256":"09496bb1a738fdc140d550f7011ce60197ca71c97b76cb6384338a5599d4125e","schema_version":"1.0","event_id":"sha256:09496bb1a738fdc140d550f7011ce60197ca71c97b76cb6384338a5599d4125e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OMOPYDRXHWLMRUBUQCJK56NXBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Low-Dimensional Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Blake Mason, Lalit Jain, Robert Nowak","submitted_at":"2017-09-18T21:26:43Z","abstract_excerpt":"This paper investigates the theoretical foundations of metric learning, focused on three key questions that are not fully addressed in prior work: 1) we consider learning general low-dimensional (low-rank) metrics as well as sparse metrics; 2) we develop upper and lower (minimax)bounds on the generalization error; 3) we quantify the sample complexity of metric learning in terms of the dimension of the feature space and the dimension/rank of the underlying metric;4) we also bound the accuracy of the learned metric relative to the underlying true generative metric. All the results involve novel "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06171","kind":"arxiv","version":2},"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":"2026-05-18T00:24:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4BdRrFVkiiMCmjsbeFEQ/LWVxQ1p0VQxEH2sOmgNGbVHm5w8pbuFTFSC1HjcxbVT/loC/trLlBitJMgA43HBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T04:21:33.119299Z"},"content_sha256":"506d1247c4365344a720792efeb62e8994254ac28e0e34b93a7ac80377b9927f","schema_version":"1.0","event_id":"sha256:506d1247c4365344a720792efeb62e8994254ac28e0e34b93a7ac80377b9927f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMOPYDRXHWLMRUBUQCJK56NXBA/bundle.json","state_url":"https://pith.science/pith/OMOPYDRXHWLMRUBUQCJK56NXBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMOPYDRXHWLMRUBUQCJK56NXBA/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":"2026-05-31T04:21:33Z","links":{"resolver":"https://pith.science/pith/OMOPYDRXHWLMRUBUQCJK56NXBA","bundle":"https://pith.science/pith/OMOPYDRXHWLMRUBUQCJK56NXBA/bundle.json","state":"https://pith.science/pith/OMOPYDRXHWLMRUBUQCJK56NXBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMOPYDRXHWLMRUBUQCJK56NXBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OMOPYDRXHWLMRUBUQCJK56NXBA","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":"028870c398494ff91d92cd5a0f5fa0debb2af948b9d94c2486a043932dab2012","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-18T21:26:43Z","title_canon_sha256":"db2b1a9f471fd87ecdc77d9d5e57c7537c8a830b88f963a71665fbef4ab1a7d9"},"schema_version":"1.0","source":{"id":"1709.06171","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06171","created_at":"2026-05-18T00:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06171v2","created_at":"2026-05-18T00:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06171","created_at":"2026-05-18T00:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"OMOPYDRXHWLM","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OMOPYDRXHWLMRUBU","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OMOPYDRX","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:506d1247c4365344a720792efeb62e8994254ac28e0e34b93a7ac80377b9927f","target":"graph","created_at":"2026-05-18T00:24:22Z","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":"This paper investigates the theoretical foundations of metric learning, focused on three key questions that are not fully addressed in prior work: 1) we consider learning general low-dimensional (low-rank) metrics as well as sparse metrics; 2) we develop upper and lower (minimax)bounds on the generalization error; 3) we quantify the sample complexity of metric learning in terms of the dimension of the feature space and the dimension/rank of the underlying metric;4) we also bound the accuracy of the learned metric relative to the underlying true generative metric. All the results involve novel ","authors_text":"Blake Mason, Lalit Jain, Robert Nowak","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-18T21:26:43Z","title":"Learning Low-Dimensional Metrics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06171","kind":"arxiv","version":2},"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":"sha256:09496bb1a738fdc140d550f7011ce60197ca71c97b76cb6384338a5599d4125e","target":"record","created_at":"2026-05-18T00:24:22Z","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":"028870c398494ff91d92cd5a0f5fa0debb2af948b9d94c2486a043932dab2012","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-18T21:26:43Z","title_canon_sha256":"db2b1a9f471fd87ecdc77d9d5e57c7537c8a830b88f963a71665fbef4ab1a7d9"},"schema_version":"1.0","source":{"id":"1709.06171","kind":"arxiv","version":2}},"canonical_sha256":"731cfc0e373d96c8d0348092aef9b70820d8dd3a46234844abd7d2a276ef9a2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"731cfc0e373d96c8d0348092aef9b70820d8dd3a46234844abd7d2a276ef9a2d","first_computed_at":"2026-05-18T00:24:22.350100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:22.350100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ly0jF9K6QdtUnpC1aHIoQIMrpT2yXMF4DauSsh2alcHhpp6Ooeyj2xL1M8jOA7iqo0VYPg7FQj//DIQkuMooDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:22.350689Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06171","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09496bb1a738fdc140d550f7011ce60197ca71c97b76cb6384338a5599d4125e","sha256:506d1247c4365344a720792efeb62e8994254ac28e0e34b93a7ac80377b9927f"],"state_sha256":"4ef4606292c088542d63bd24b85bd9fcea8d063281ac697ff3a9527893e9df5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Xu0Ayhby3NddDL5ys6X5twpWnAL0YeLmejftaFr6YsRTj4oEUhTwfFoc9QK4WAZtj4DexgpTOkht3H4taxlDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T04:21:33.122697Z","bundle_sha256":"f0913f3780f06e8b7a30fee7c8b3eadae63ecd71396e6208cac19965ed2156af"}}