{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JO5AOGGGZ4H43L43YQGKNFMHE5","short_pith_number":"pith:JO5AOGGG","canonical_record":{"source":{"id":"1807.09200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T16:01:00Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b72bd5034e9585e95d91557de291820f67265d28ee778c48bd1fe4cedbf7f667","abstract_canon_sha256":"e2d465f509dde79805a482f087c0f8c504730be6828a76e32c2be5430670cda6"},"schema_version":"1.0"},"canonical_sha256":"4bba0718c6cf0fcdaf9bc40ca695872773fa96134d7604f7eb778dc816f88453","source":{"kind":"arxiv","id":"1807.09200","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09200","created_at":"2026-05-18T00:09:56Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09200v1","created_at":"2026-05-18T00:09:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09200","created_at":"2026-05-18T00:09:56Z"},{"alias_kind":"pith_short_12","alias_value":"JO5AOGGGZ4H4","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JO5AOGGGZ4H43L43","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JO5AOGGG","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JO5AOGGGZ4H43L43YQGKNFMHE5","target":"record","payload":{"canonical_record":{"source":{"id":"1807.09200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T16:01:00Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b72bd5034e9585e95d91557de291820f67265d28ee778c48bd1fe4cedbf7f667","abstract_canon_sha256":"e2d465f509dde79805a482f087c0f8c504730be6828a76e32c2be5430670cda6"},"schema_version":"1.0"},"canonical_sha256":"4bba0718c6cf0fcdaf9bc40ca695872773fa96134d7604f7eb778dc816f88453","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:56.441069Z","signature_b64":"NHCcUJzjB1/kail0yk/7ko4VBArGvpfgGqkbZV6gBMGAn601sQjhYcnTNbWJyVsHci52O/45Ntlw9jYuWN2CDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bba0718c6cf0fcdaf9bc40ca695872773fa96134d7604f7eb778dc816f88453","last_reissued_at":"2026-05-18T00:09:56.440403Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:56.440403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.09200","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":"2026-05-18T00:09:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DdY+ihB4et7jt/I7HVwYJOhFcF+R/4cZ27TmPNfbanIoXE7gJxHWLbQECp45xz6DE8XPwko0zZwCXz1Q9N6GCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:24:39.493670Z"},"content_sha256":"8347c90973047c2e05ef3efe12fd621e47e320b27c56b0897084e2975638bbfa","schema_version":"1.0","event_id":"sha256:8347c90973047c2e05ef3efe12fd621e47e320b27c56b0897084e2975638bbfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JO5AOGGGZ4H43L43YQGKNFMHE5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Paced Learning with Adaptive Deep Visual Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Vithursan Thangarasa","submitted_at":"2018-07-24T16:01:00Z","abstract_excerpt":"Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performance. In this paper, we introduce Self-Paced Learning with Adaptive Deep Visual Embeddings (SPL-ADVisE), a novel end-to-end training protocol that unites self-paced learning (SPL) and deep metric learning (DML). We leverage the Magnet Loss to train an embedding convolutional neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09200","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":"2026-05-18T00:09:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4HSkXejwt4jO2SOYYoT5ZDF86CQQQolqfigu6yrpCssy1K1kUF8lvzf1COHTr3LyYuUgwK69wDgaz14cazjiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:24:39.494211Z"},"content_sha256":"a9e99f03c61c7bf7e95d1cfa05b0136e0d3ee8407389bf3a8b5028c35e3e305c","schema_version":"1.0","event_id":"sha256:a9e99f03c61c7bf7e95d1cfa05b0136e0d3ee8407389bf3a8b5028c35e3e305c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/bundle.json","state_url":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/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":"2026-05-26T15:24:39Z","links":{"resolver":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5","bundle":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/bundle.json","state":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JO5AOGGGZ4H43L43YQGKNFMHE5","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":"e2d465f509dde79805a482f087c0f8c504730be6828a76e32c2be5430670cda6","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T16:01:00Z","title_canon_sha256":"b72bd5034e9585e95d91557de291820f67265d28ee778c48bd1fe4cedbf7f667"},"schema_version":"1.0","source":{"id":"1807.09200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09200","created_at":"2026-05-18T00:09:56Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09200v1","created_at":"2026-05-18T00:09:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09200","created_at":"2026-05-18T00:09:56Z"},{"alias_kind":"pith_short_12","alias_value":"JO5AOGGGZ4H4","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JO5AOGGGZ4H43L43","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JO5AOGGG","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:a9e99f03c61c7bf7e95d1cfa05b0136e0d3ee8407389bf3a8b5028c35e3e305c","target":"graph","created_at":"2026-05-18T00:09:56Z","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":"Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performance. In this paper, we introduce Self-Paced Learning with Adaptive Deep Visual Embeddings (SPL-ADVisE), a novel end-to-end training protocol that unites self-paced learning (SPL) and deep metric learning (DML). We leverage the Magnet Loss to train an embedding convolutional neural ","authors_text":"Graham W. Taylor, Vithursan Thangarasa","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T16:01:00Z","title":"Self-Paced Learning with Adaptive Deep Visual Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09200","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":"sha256:8347c90973047c2e05ef3efe12fd621e47e320b27c56b0897084e2975638bbfa","target":"record","created_at":"2026-05-18T00:09:56Z","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":"e2d465f509dde79805a482f087c0f8c504730be6828a76e32c2be5430670cda6","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T16:01:00Z","title_canon_sha256":"b72bd5034e9585e95d91557de291820f67265d28ee778c48bd1fe4cedbf7f667"},"schema_version":"1.0","source":{"id":"1807.09200","kind":"arxiv","version":1}},"canonical_sha256":"4bba0718c6cf0fcdaf9bc40ca695872773fa96134d7604f7eb778dc816f88453","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bba0718c6cf0fcdaf9bc40ca695872773fa96134d7604f7eb778dc816f88453","first_computed_at":"2026-05-18T00:09:56.440403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:56.440403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NHCcUJzjB1/kail0yk/7ko4VBArGvpfgGqkbZV6gBMGAn601sQjhYcnTNbWJyVsHci52O/45Ntlw9jYuWN2CDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:56.441069Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.09200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8347c90973047c2e05ef3efe12fd621e47e320b27c56b0897084e2975638bbfa","sha256:a9e99f03c61c7bf7e95d1cfa05b0136e0d3ee8407389bf3a8b5028c35e3e305c"],"state_sha256":"0c1406ee532917bc0ff6a867f36708ceecf8c575932eed5d0da6d749556995fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AuL8gK5CMeQ2xdZ14uuTNM3kMmLW65U9/DfAeIAZbB/WBFRp25AV3qUKMJ5sn0GY6Xk8ENHw8rqGZndxxHnmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T15:24:39.497541Z","bundle_sha256":"dc08576fb267e784d603e8c04136afe89d63155b9dc51ca750d8ab0938ea5cb9"}}