{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RX4BZ2FDKEASBLMN5LDDIDBHER","short_pith_number":"pith:RX4BZ2FD","canonical_record":{"source":{"id":"2108.09335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-20T19:21:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"18368e02bc1a498aadb4f6ca3a35f08433782263d91580df8dea3c03db72792f","abstract_canon_sha256":"d6be34bff9d0a5d47377caaa935f74419a304af3823d7e99b46859f6853b22ba"},"schema_version":"1.0"},"canonical_sha256":"8df81ce8a3510120ad8deac6340c27246d13e167528d1c9500b3fc8fb682dacf","source":{"kind":"arxiv","id":"2108.09335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.09335","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"arxiv_version","alias_value":"2108.09335v1","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09335","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"pith_short_12","alias_value":"RX4BZ2FDKEAS","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"pith_short_16","alias_value":"RX4BZ2FDKEASBLMN","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"pith_short_8","alias_value":"RX4BZ2FD","created_at":"2026-07-05T03:07:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RX4BZ2FDKEASBLMN5LDDIDBHER","target":"record","payload":{"canonical_record":{"source":{"id":"2108.09335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-20T19:21:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"18368e02bc1a498aadb4f6ca3a35f08433782263d91580df8dea3c03db72792f","abstract_canon_sha256":"d6be34bff9d0a5d47377caaa935f74419a304af3823d7e99b46859f6853b22ba"},"schema_version":"1.0"},"canonical_sha256":"8df81ce8a3510120ad8deac6340c27246d13e167528d1c9500b3fc8fb682dacf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:53.475590Z","signature_b64":"4r1wzcVz/fHvUfLdRgzoSxgf/f3yVKdcPOVQBs+J7XXX96NdswW+bTaLppeYWvwYuGCuPYHKNiFsttuEa4mLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8df81ce8a3510120ad8deac6340c27246d13e167528d1c9500b3fc8fb682dacf","last_reissued_at":"2026-07-05T03:07:53.475195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:53.475195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.09335","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":"2026-07-05T03:07:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wxzi/CE3HwiIDEFuM3VWL1coeM9geA6/2yWsIOINvjhCv6mFJgERsQEcTiS52KyC/0PSS+jg0DaRCt4IMuljAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:11:12.390795Z"},"content_sha256":"97f6965c1c751a6c6b136337bc58f460571dc1b1164ec9ae0b2ecba1105e2ea7","schema_version":"1.0","event_id":"sha256:97f6965c1c751a6c6b136337bc58f460571dc1b1164ec9ae0b2ecba1105e2ea7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RX4BZ2FDKEASBLMN5LDDIDBHER","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bhavya Vasudeva, Puneesh Deora, Saumik Bhattacharya, Sukalpa Chanda, Umapada Pal","submitted_at":"2021-08-20T19:21:33Z","abstract_excerpt":"Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc. In order to aid the training process, existing methods either use a hard mining strategy to extract the most informative samples or seek to generate hard synthetics using an additional network. Such approaches face different challenges and can lead to biased embeddings in the former case, and (i) harder optimization (ii) slower training speed (iii) higher model complexity in the latter case. In order to overcome these challenges, we propose a novel approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09335","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.09335/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:07:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mlSmqP9uanSNZmKqjP5e1e8fjLCI+o/ktTSRq85LL7jw6ie2Q+U8j8i/Od/Wzku2/5tz5tOaKwA40ONGMYjrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:11:12.391294Z"},"content_sha256":"6c3275ce5ccd25c9091f35c590be712d5d40c6838b413b3c7ca5ddbf4b1acc4a","schema_version":"1.0","event_id":"sha256:6c3275ce5ccd25c9091f35c590be712d5d40c6838b413b3c7ca5ddbf4b1acc4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RX4BZ2FDKEASBLMN5LDDIDBHER/bundle.json","state_url":"https://pith.science/pith/RX4BZ2FDKEASBLMN5LDDIDBHER/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RX4BZ2FDKEASBLMN5LDDIDBHER/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":"2026-08-23T21:11:12Z","links":{"resolver":"https://pith.science/pith/RX4BZ2FDKEASBLMN5LDDIDBHER","bundle":"https://pith.science/pith/RX4BZ2FDKEASBLMN5LDDIDBHER/bundle.json","state":"https://pith.science/pith/RX4BZ2FDKEASBLMN5LDDIDBHER/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RX4BZ2FDKEASBLMN5LDDIDBHER/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RX4BZ2FDKEASBLMN5LDDIDBHER","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":"d6be34bff9d0a5d47377caaa935f74419a304af3823d7e99b46859f6853b22ba","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-20T19:21:33Z","title_canon_sha256":"18368e02bc1a498aadb4f6ca3a35f08433782263d91580df8dea3c03db72792f"},"schema_version":"1.0","source":{"id":"2108.09335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.09335","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"arxiv_version","alias_value":"2108.09335v1","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09335","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"pith_short_12","alias_value":"RX4BZ2FDKEAS","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"pith_short_16","alias_value":"RX4BZ2FDKEASBLMN","created_at":"2026-07-05T03:07:53Z"},{"alias_kind":"pith_short_8","alias_value":"RX4BZ2FD","created_at":"2026-07-05T03:07:53Z"}],"graph_snapshots":[{"event_id":"sha256:6c3275ce5ccd25c9091f35c590be712d5d40c6838b413b3c7ca5ddbf4b1acc4a","target":"graph","created_at":"2026-07-05T03:07:53Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.09335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc. In order to aid the training process, existing methods either use a hard mining strategy to extract the most informative samples or seek to generate hard synthetics using an additional network. Such approaches face different challenges and can lead to biased embeddings in the former case, and (i) harder optimization (ii) slower training speed (iii) higher model complexity in the latter case. In order to overcome these challenges, we propose a novel approach","authors_text":"Bhavya Vasudeva, Puneesh Deora, Saumik Bhattacharya, Sukalpa Chanda, Umapada Pal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-20T19:21:33Z","title":"LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09335","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":"sha256:97f6965c1c751a6c6b136337bc58f460571dc1b1164ec9ae0b2ecba1105e2ea7","target":"record","created_at":"2026-07-05T03:07:53Z","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":"d6be34bff9d0a5d47377caaa935f74419a304af3823d7e99b46859f6853b22ba","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-20T19:21:33Z","title_canon_sha256":"18368e02bc1a498aadb4f6ca3a35f08433782263d91580df8dea3c03db72792f"},"schema_version":"1.0","source":{"id":"2108.09335","kind":"arxiv","version":1}},"canonical_sha256":"8df81ce8a3510120ad8deac6340c27246d13e167528d1c9500b3fc8fb682dacf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8df81ce8a3510120ad8deac6340c27246d13e167528d1c9500b3fc8fb682dacf","first_computed_at":"2026-07-05T03:07:53.475195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:53.475195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4r1wzcVz/fHvUfLdRgzoSxgf/f3yVKdcPOVQBs+J7XXX96NdswW+bTaLppeYWvwYuGCuPYHKNiFsttuEa4mLCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:53.475590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.09335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97f6965c1c751a6c6b136337bc58f460571dc1b1164ec9ae0b2ecba1105e2ea7","sha256:6c3275ce5ccd25c9091f35c590be712d5d40c6838b413b3c7ca5ddbf4b1acc4a"],"state_sha256":"02f3d5314993c6bd7691f06735efdff547b1141df0003a097504d15012279399"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CTVx53jKlaxLZKCkjdwniiIPddAloplIoBamEISvGniVB5LJ5El0hOLj+kc76vnLxRzAFutNDAHyeWieydNCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T21:11:12.395061Z","bundle_sha256":"3f0e22f112155d2446a1baaafd771e23af253d8d2a0fa11e311b856df3aeb830"}}