{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EX65V44QNKO3LXE4ZIM2GHTFOO","short_pith_number":"pith:EX65V44Q","canonical_record":{"source":{"id":"2002.06979","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T14:35:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"67f639138523545ec7bcbf64bdd7c1649ad69f427a1f55436f522386e4c51610","abstract_canon_sha256":"10022267ad2ad146820dc1be482f1f26a3976f032299e94ef9d54bb971f8c6d7"},"schema_version":"1.0"},"canonical_sha256":"25fddaf3906a9db5dc9cca19a31e65738d4f73f1abbc76fbe35aed0f1e7b5ac7","source":{"kind":"arxiv","id":"2002.06979","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06979","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06979v3","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06979","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_12","alias_value":"EX65V44QNKO3","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_16","alias_value":"EX65V44QNKO3LXE4","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_8","alias_value":"EX65V44Q","created_at":"2026-07-05T02:44:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EX65V44QNKO3LXE4ZIM2GHTFOO","target":"record","payload":{"canonical_record":{"source":{"id":"2002.06979","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T14:35:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"67f639138523545ec7bcbf64bdd7c1649ad69f427a1f55436f522386e4c51610","abstract_canon_sha256":"10022267ad2ad146820dc1be482f1f26a3976f032299e94ef9d54bb971f8c6d7"},"schema_version":"1.0"},"canonical_sha256":"25fddaf3906a9db5dc9cca19a31e65738d4f73f1abbc76fbe35aed0f1e7b5ac7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:32.101885Z","signature_b64":"ZOT0tFvH8hCDcrVVwA4l63C+jPMImR1o+9/4JPoUUA2y/ybC0yi3QUglcjLkXlizzLakkhMx69dB3qQO5XQcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25fddaf3906a9db5dc9cca19a31e65738d4f73f1abbc76fbe35aed0f1e7b5ac7","last_reissued_at":"2026-07-05T02:44:32.101223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:32.101223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.06979","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrdLTzfyl9etmp5gl2Vj3cjMK6mZgBVcSl7H/OulbOJ0iuxae2jA7qnlTosAnlHtM4hmC7nVJyQ655kQAIJ0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:26:11.370629Z"},"content_sha256":"7583dc23fd26c0148d0bf00bb9b2e70274589bebb5474dacbb3656079e7387ce","schema_version":"1.0","event_id":"sha256:7583dc23fd26c0148d0bf00bb9b2e70274589bebb5474dacbb3656079e7387ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EX65V44QNKO3LXE4ZIM2GHTFOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergence of End-to-End Training in Deep Unsupervised Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Zixin Wen","submitted_at":"2020-02-17T14:35:21Z","abstract_excerpt":"Unsupervised contrastive learning has gained increasing attention in the latest research and has proven to be a powerful method for learning representations from unlabeled data. However, little theoretical analysis was known for this framework. In this paper, we study the optimization of deep unsupervised contrastive learning. We prove that, by applying end-to-end training that simultaneously updates two deep over-parameterized neural networks, one can find an approximate stationary solution for the non-convex contrastive loss. This result is inherently different from the existing over-paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06979","kind":"arxiv","version":3},"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/2002.06979/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":"2026-07-05T02:44:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ud9KlTqgA2zgfM84RVApzYgdHej1XhfzjvtC45hw1JI+qye5ZKYChnba2WPQbm4irZ4KpF7X3Bd/yWvVvHSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:26:11.371166Z"},"content_sha256":"4875e40da32c55b2d01bc2642b49f8c47462efa6b1441afd1843dd3e7007c5f6","schema_version":"1.0","event_id":"sha256:4875e40da32c55b2d01bc2642b49f8c47462efa6b1441afd1843dd3e7007c5f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EX65V44QNKO3LXE4ZIM2GHTFOO/bundle.json","state_url":"https://pith.science/pith/EX65V44QNKO3LXE4ZIM2GHTFOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EX65V44QNKO3LXE4ZIM2GHTFOO/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":"2026-08-15T11:26:11Z","links":{"resolver":"https://pith.science/pith/EX65V44QNKO3LXE4ZIM2GHTFOO","bundle":"https://pith.science/pith/EX65V44QNKO3LXE4ZIM2GHTFOO/bundle.json","state":"https://pith.science/pith/EX65V44QNKO3LXE4ZIM2GHTFOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EX65V44QNKO3LXE4ZIM2GHTFOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EX65V44QNKO3LXE4ZIM2GHTFOO","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":"10022267ad2ad146820dc1be482f1f26a3976f032299e94ef9d54bb971f8c6d7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T14:35:21Z","title_canon_sha256":"67f639138523545ec7bcbf64bdd7c1649ad69f427a1f55436f522386e4c51610"},"schema_version":"1.0","source":{"id":"2002.06979","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06979","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06979v3","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06979","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_12","alias_value":"EX65V44QNKO3","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_16","alias_value":"EX65V44QNKO3LXE4","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_8","alias_value":"EX65V44Q","created_at":"2026-07-05T02:44:32Z"}],"graph_snapshots":[{"event_id":"sha256:4875e40da32c55b2d01bc2642b49f8c47462efa6b1441afd1843dd3e7007c5f6","target":"graph","created_at":"2026-07-05T02:44:32Z","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/2002.06979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised contrastive learning has gained increasing attention in the latest research and has proven to be a powerful method for learning representations from unlabeled data. However, little theoretical analysis was known for this framework. In this paper, we study the optimization of deep unsupervised contrastive learning. We prove that, by applying end-to-end training that simultaneously updates two deep over-parameterized neural networks, one can find an approximate stationary solution for the non-convex contrastive loss. This result is inherently different from the existing over-paramet","authors_text":"Zixin Wen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T14:35:21Z","title":"Convergence of End-to-End Training in Deep Unsupervised Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06979","kind":"arxiv","version":3},"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":"sha256:7583dc23fd26c0148d0bf00bb9b2e70274589bebb5474dacbb3656079e7387ce","target":"record","created_at":"2026-07-05T02:44:32Z","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":"10022267ad2ad146820dc1be482f1f26a3976f032299e94ef9d54bb971f8c6d7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T14:35:21Z","title_canon_sha256":"67f639138523545ec7bcbf64bdd7c1649ad69f427a1f55436f522386e4c51610"},"schema_version":"1.0","source":{"id":"2002.06979","kind":"arxiv","version":3}},"canonical_sha256":"25fddaf3906a9db5dc9cca19a31e65738d4f73f1abbc76fbe35aed0f1e7b5ac7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25fddaf3906a9db5dc9cca19a31e65738d4f73f1abbc76fbe35aed0f1e7b5ac7","first_computed_at":"2026-07-05T02:44:32.101223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:32.101223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZOT0tFvH8hCDcrVVwA4l63C+jPMImR1o+9/4JPoUUA2y/ybC0yi3QUglcjLkXlizzLakkhMx69dB3qQO5XQcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:32.101885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06979","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7583dc23fd26c0148d0bf00bb9b2e70274589bebb5474dacbb3656079e7387ce","sha256:4875e40da32c55b2d01bc2642b49f8c47462efa6b1441afd1843dd3e7007c5f6"],"state_sha256":"db46a81bbfd896138db05ec385b21ed7abda4df8da246328a0ecb3aa2ab2d1cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kM9a7FI0oIl4K5t8Rw20yB/RwdBXXgNWQlWDVXA0Xe660a7wsmmeM1KRKscBHSJefsg+kzXpQr03JA1zO9PeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:26:11.378858Z","bundle_sha256":"23dd86353126cd30425c931605db31e5816f8d774eb6becf77ad70759f9ed313"}}