{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DBS5YHKUVYPR7FVXBPEC6X5SFH","short_pith_number":"pith:DBS5YHKU","canonical_record":{"source":{"id":"1611.01449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-04T16:39:20Z","cross_cats_sorted":[],"title_canon_sha256":"89cb5fa4da20567372d59bdd277f8fd4a08feeda696c780501e97782ea4f568b","abstract_canon_sha256":"2cc2d79f741b7a1b971669eee673f43e28f54940faf8fbb3b2c8e01cee425c8b"},"schema_version":"1.0"},"canonical_sha256":"1865dc1d54ae1f1f96b70bc82f5fb229dc2c2300a8a4dd7ae743d3df6cbb1dd9","source":{"kind":"arxiv","id":"1611.01449","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01449","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01449v2","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01449","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"DBS5YHKUVYPR","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"DBS5YHKUVYPR7FVX","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"DBS5YHKU","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DBS5YHKUVYPR7FVXBPEC6X5SFH","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-04T16:39:20Z","cross_cats_sorted":[],"title_canon_sha256":"89cb5fa4da20567372d59bdd277f8fd4a08feeda696c780501e97782ea4f568b","abstract_canon_sha256":"2cc2d79f741b7a1b971669eee673f43e28f54940faf8fbb3b2c8e01cee425c8b"},"schema_version":"1.0"},"canonical_sha256":"1865dc1d54ae1f1f96b70bc82f5fb229dc2c2300a8a4dd7ae743d3df6cbb1dd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:18.226478Z","signature_b64":"UmiZcKK9pPYzXKeQ36PMBDn7JMFW6pCiv/sRnWaKvUZRiRpD8kWEj2DsM41cQjpvHQbDJ3XJMO5CRZ0wJznFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1865dc1d54ae1f1f96b70bc82f5fb229dc2c2300a8a4dd7ae743d3df6cbb1dd9","last_reissued_at":"2026-05-17T23:59:18.225906Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:18.225906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01449","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":"2026-05-17T23:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GcOBUKDQMk7R8nyDVOqYKV99GYEMcDz3+gl6uVXSI3nOlsLtc7BzxlH4sWkGUJOfQ6iXj0k0JGCsl2ptxiPBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:00:49.909435Z"},"content_sha256":"2f2d2ababe19fd234b88de10d6b4fb32794cc7558118f5c90bef793f0dff135d","schema_version":"1.0","event_id":"sha256:2f2d2ababe19fd234b88de10d6b4fb32794cc7558118f5c90bef793f0dff135d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DBS5YHKUVYPR7FVXBPEC6X5SFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised deep learning by metric embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elad Hoffer, Nir Ailon","submitted_at":"2016-11-04T16:39:20Z","abstract_excerpt":"Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of their tendency to overfit easily when trained on small amounts of data. In this work we will explore a new training objective that is targeting a semi-supervised regime with only a small subset of labeled data. This criterion is based on a deep metric embedding over distance relations within the set of labeled samples, together with constraints over the embedd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01449","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":"2026-05-17T23:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x2qW14fbtcMkgf7CJMOe5ThDtBA4bw2C1+yrJioNUAC56sOBQkhVnQAdiXjrYiN/WYe8ZUIEsGZHV5OXOxngBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:00:49.909788Z"},"content_sha256":"474bb6094b650801b7cae77ad4d50df45f1bc1cb70633b0bb21d5717a85a136e","schema_version":"1.0","event_id":"sha256:474bb6094b650801b7cae77ad4d50df45f1bc1cb70633b0bb21d5717a85a136e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBS5YHKUVYPR7FVXBPEC6X5SFH/bundle.json","state_url":"https://pith.science/pith/DBS5YHKUVYPR7FVXBPEC6X5SFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBS5YHKUVYPR7FVXBPEC6X5SFH/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":"2026-06-02T15:00:49Z","links":{"resolver":"https://pith.science/pith/DBS5YHKUVYPR7FVXBPEC6X5SFH","bundle":"https://pith.science/pith/DBS5YHKUVYPR7FVXBPEC6X5SFH/bundle.json","state":"https://pith.science/pith/DBS5YHKUVYPR7FVXBPEC6X5SFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBS5YHKUVYPR7FVXBPEC6X5SFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DBS5YHKUVYPR7FVXBPEC6X5SFH","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":"2cc2d79f741b7a1b971669eee673f43e28f54940faf8fbb3b2c8e01cee425c8b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-04T16:39:20Z","title_canon_sha256":"89cb5fa4da20567372d59bdd277f8fd4a08feeda696c780501e97782ea4f568b"},"schema_version":"1.0","source":{"id":"1611.01449","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01449","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01449v2","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01449","created_at":"2026-05-17T23:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"DBS5YHKUVYPR","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"DBS5YHKUVYPR7FVX","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"DBS5YHKU","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:474bb6094b650801b7cae77ad4d50df45f1bc1cb70633b0bb21d5717a85a136e","target":"graph","created_at":"2026-05-17T23:59:18Z","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":"Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of their tendency to overfit easily when trained on small amounts of data. In this work we will explore a new training objective that is targeting a semi-supervised regime with only a small subset of labeled data. This criterion is based on a deep metric embedding over distance relations within the set of labeled samples, together with constraints over the embedd","authors_text":"Elad Hoffer, Nir Ailon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-04T16:39:20Z","title":"Semi-supervised deep learning by metric embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01449","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":"sha256:2f2d2ababe19fd234b88de10d6b4fb32794cc7558118f5c90bef793f0dff135d","target":"record","created_at":"2026-05-17T23:59:18Z","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":"2cc2d79f741b7a1b971669eee673f43e28f54940faf8fbb3b2c8e01cee425c8b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-04T16:39:20Z","title_canon_sha256":"89cb5fa4da20567372d59bdd277f8fd4a08feeda696c780501e97782ea4f568b"},"schema_version":"1.0","source":{"id":"1611.01449","kind":"arxiv","version":2}},"canonical_sha256":"1865dc1d54ae1f1f96b70bc82f5fb229dc2c2300a8a4dd7ae743d3df6cbb1dd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1865dc1d54ae1f1f96b70bc82f5fb229dc2c2300a8a4dd7ae743d3df6cbb1dd9","first_computed_at":"2026-05-17T23:59:18.225906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:18.225906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UmiZcKK9pPYzXKeQ36PMBDn7JMFW6pCiv/sRnWaKvUZRiRpD8kWEj2DsM41cQjpvHQbDJ3XJMO5CRZ0wJznFCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:18.226478Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01449","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f2d2ababe19fd234b88de10d6b4fb32794cc7558118f5c90bef793f0dff135d","sha256:474bb6094b650801b7cae77ad4d50df45f1bc1cb70633b0bb21d5717a85a136e"],"state_sha256":"1bab0ab58d572796149766a45cccf1bfe5403d8252bfb2abf48ce0685c0d3be0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hE2/4ej5vRiN/PsFjT2ySEnJNrkNjKYBmU5HNl/w9lN3bz3wolLCn7d2Ik/umTvKqWleFaMwfqiyIdMP3faNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T15:00:49.911810Z","bundle_sha256":"0775030c2662faae4c345bd28357d8f3655167658400be26c1c105f91d933929"}}