{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:FLTOQPYC5GW6OYDBFH24IHPAYY","short_pith_number":"pith:FLTOQPYC","canonical_record":{"source":{"id":"1511.05939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-11-18T20:41:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7556b475edd0cc5f90b3a1d8e490ebcf2d8f3b9ae1aa6dc35ed8ad752c8918ac","abstract_canon_sha256":"f6e901fdaddb77304abb04144250d6d167e9f10117ec23fd6da1585a87b3f40f"},"schema_version":"1.0"},"canonical_sha256":"2ae6e83f02e9ade7606129f5c41de0c617388409b94ccfaaea0eb860c1bf9e90","source":{"kind":"arxiv","id":"1511.05939","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05939","created_at":"2026-05-18T01:19:44Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05939v2","created_at":"2026-05-18T01:19:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05939","created_at":"2026-05-18T01:19:44Z"},{"alias_kind":"pith_short_12","alias_value":"FLTOQPYC5GW6","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"FLTOQPYC5GW6OYDB","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"FLTOQPYC","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:FLTOQPYC5GW6OYDBFH24IHPAYY","target":"record","payload":{"canonical_record":{"source":{"id":"1511.05939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-11-18T20:41:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7556b475edd0cc5f90b3a1d8e490ebcf2d8f3b9ae1aa6dc35ed8ad752c8918ac","abstract_canon_sha256":"f6e901fdaddb77304abb04144250d6d167e9f10117ec23fd6da1585a87b3f40f"},"schema_version":"1.0"},"canonical_sha256":"2ae6e83f02e9ade7606129f5c41de0c617388409b94ccfaaea0eb860c1bf9e90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:44.031887Z","signature_b64":"/wM/HKb8duWx5it5mOkieFN5tqglsnqdywIKWdInSvuhNTYU+xiCd1o3UuwS08xXy738j1h8RZWjF7BwIfVdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ae6e83f02e9ade7606129f5c41de0c617388409b94ccfaaea0eb860c1bf9e90","last_reissued_at":"2026-05-18T01:19:44.031467Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:44.031467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.05939","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":"2026-05-18T01:19:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"soACwtc00xJtZQYPOgmsQJ90yhz8TmmdX48XWFSpS6L4g/tUsbjO0bsxi59D9VKhZG6mp6O7g7xQ0ik98SmQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:05:54.410110Z"},"content_sha256":"9f8ca74a3298642d4fff3019e356a3ffa8ba249b8c8de1218e1611eccd96f378","schema_version":"1.0","event_id":"sha256:9f8ca74a3298642d4fff3019e356a3ffa8ba249b8c8de1218e1611eccd96f378"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:FLTOQPYC5GW6OYDBFH24IHPAYY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Metric Learning with Adaptive Density Discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lubomir Bourdev, Manohar Paluri, Oren Rippel, Piotr Dollar","submitted_at":"2015-11-18T20:41:05Z","abstract_excerpt":"Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been difficult for these to compete with modern classification algorithms in performance and even in feature extraction.\n  In this work, we propose a novel approach explicitly designed to address a number of subtle yet important issues which have stymied earlier DML algorithms. It maintains an explicit model of the distributions of the different classes in representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05939","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":"2026-05-18T01:19:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFsLgj9y6bvVkF/XOaIOCjEhgIvn73WZUc6OVVgW2CJmoHXTNr0YaIhjY/6bMRcxr2zeK5yY3ye661oJvnU8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:05:54.410830Z"},"content_sha256":"df46b4e5b2b7a2613c2374ead3f7f49bc1088258390eee1c3f20ff03b0b86e99","schema_version":"1.0","event_id":"sha256:df46b4e5b2b7a2613c2374ead3f7f49bc1088258390eee1c3f20ff03b0b86e99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FLTOQPYC5GW6OYDBFH24IHPAYY/bundle.json","state_url":"https://pith.science/pith/FLTOQPYC5GW6OYDBFH24IHPAYY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FLTOQPYC5GW6OYDBFH24IHPAYY/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":"2026-06-07T21:05:54Z","links":{"resolver":"https://pith.science/pith/FLTOQPYC5GW6OYDBFH24IHPAYY","bundle":"https://pith.science/pith/FLTOQPYC5GW6OYDBFH24IHPAYY/bundle.json","state":"https://pith.science/pith/FLTOQPYC5GW6OYDBFH24IHPAYY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FLTOQPYC5GW6OYDBFH24IHPAYY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:FLTOQPYC5GW6OYDBFH24IHPAYY","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":"f6e901fdaddb77304abb04144250d6d167e9f10117ec23fd6da1585a87b3f40f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-11-18T20:41:05Z","title_canon_sha256":"7556b475edd0cc5f90b3a1d8e490ebcf2d8f3b9ae1aa6dc35ed8ad752c8918ac"},"schema_version":"1.0","source":{"id":"1511.05939","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05939","created_at":"2026-05-18T01:19:44Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05939v2","created_at":"2026-05-18T01:19:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05939","created_at":"2026-05-18T01:19:44Z"},{"alias_kind":"pith_short_12","alias_value":"FLTOQPYC5GW6","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"FLTOQPYC5GW6OYDB","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"FLTOQPYC","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:df46b4e5b2b7a2613c2374ead3f7f49bc1088258390eee1c3f20ff03b0b86e99","target":"graph","created_at":"2026-05-18T01:19:44Z","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":"Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been difficult for these to compete with modern classification algorithms in performance and even in feature extraction.\n  In this work, we propose a novel approach explicitly designed to address a number of subtle yet important issues which have stymied earlier DML algorithms. It maintains an explicit model of the distributions of the different classes in representa","authors_text":"Lubomir Bourdev, Manohar Paluri, Oren Rippel, Piotr Dollar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-11-18T20:41:05Z","title":"Metric Learning with Adaptive Density Discrimination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05939","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":"sha256:9f8ca74a3298642d4fff3019e356a3ffa8ba249b8c8de1218e1611eccd96f378","target":"record","created_at":"2026-05-18T01:19:44Z","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":"f6e901fdaddb77304abb04144250d6d167e9f10117ec23fd6da1585a87b3f40f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-11-18T20:41:05Z","title_canon_sha256":"7556b475edd0cc5f90b3a1d8e490ebcf2d8f3b9ae1aa6dc35ed8ad752c8918ac"},"schema_version":"1.0","source":{"id":"1511.05939","kind":"arxiv","version":2}},"canonical_sha256":"2ae6e83f02e9ade7606129f5c41de0c617388409b94ccfaaea0eb860c1bf9e90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ae6e83f02e9ade7606129f5c41de0c617388409b94ccfaaea0eb860c1bf9e90","first_computed_at":"2026-05-18T01:19:44.031467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:19:44.031467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/wM/HKb8duWx5it5mOkieFN5tqglsnqdywIKWdInSvuhNTYU+xiCd1o3UuwS08xXy738j1h8RZWjF7BwIfVdCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:19:44.031887Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.05939","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f8ca74a3298642d4fff3019e356a3ffa8ba249b8c8de1218e1611eccd96f378","sha256:df46b4e5b2b7a2613c2374ead3f7f49bc1088258390eee1c3f20ff03b0b86e99"],"state_sha256":"231b3d22a216a27ba74cfa7d4da1e1411e738481ae31d563f4d947763bb07e5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jBwAP2wftm2V2e7UEnF2NEUthXGLl6ho8NW4yvAWkbVtWAAcJgaVHBbu8eVepVsOT4TzKJCH6sYrcSY0blEeAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T21:05:54.414421Z","bundle_sha256":"8455d9c28c2d81cea001df0f4089f1434f0fff8e7b854a531e010f2d957c8dbe"}}