{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ML2SSWKITCFKSVDCAM52F6PB5W","short_pith_number":"pith:ML2SSWKI","canonical_record":{"source":{"id":"1906.00233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-06-01T14:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"43b261e52891207dfbc49e38bc4ff592783b584a542be0d1a4e021dc65868cd5","abstract_canon_sha256":"3bab5132e46a24d594cecaa3dfe81bdb45269c1175e32eaf4592841bf60e8874"},"schema_version":"1.0"},"canonical_sha256":"62f5295948988aa95462033ba2f9e1ed9bbf5bf2c3c690a2b4dce3e89146446d","source":{"kind":"arxiv","id":"1906.00233","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00233","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00233v1","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00233","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"ML2SSWKITCFK","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"ML2SSWKITCFKSVDC","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"ML2SSWKI","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ML2SSWKITCFKSVDCAM52F6PB5W","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-06-01T14:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"43b261e52891207dfbc49e38bc4ff592783b584a542be0d1a4e021dc65868cd5","abstract_canon_sha256":"3bab5132e46a24d594cecaa3dfe81bdb45269c1175e32eaf4592841bf60e8874"},"schema_version":"1.0"},"canonical_sha256":"62f5295948988aa95462033ba2f9e1ed9bbf5bf2c3c690a2b4dce3e89146446d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:27.781568Z","signature_b64":"DXLXOwP9p7/VxTpSh36mnYoZv5+kEpASwd7tU+4+nhvrAF7ott3/6opME8g9eHpAhUC2rU6MV3UJ97l3z466BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f5295948988aa95462033ba2f9e1ed9bbf5bf2c3c690a2b4dce3e89146446d","last_reissued_at":"2026-05-17T23:44:27.781066Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:27.781066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00233","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":"2026-05-17T23:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/ZsXC4xGJydxO2rel5QGArqJIJtPE2glkcj7vGA2dKq5XgNOCgGSRClPhGld4OuSS+Fa6J5XyxwvJqnnZ0lBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:56:50.662635Z"},"content_sha256":"8f80451ef5ec9ece4bc48dce9f6dcea89187b03635b8693664f37b564ae2addf","schema_version":"1.0","event_id":"sha256:8f80451ef5ec9ece4bc48dce9f6dcea89187b03635b8693664f37b564ae2addf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ML2SSWKITCFKSVDCAM52F6PB5W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An implicit gradient-descent procedure for minimax problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Esteban Tabak, Giulio Trigila, Montacer Essid","submitted_at":"2019-06-01T14:30:55Z","abstract_excerpt":"A game theory inspired methodology is proposed for finding a function's saddle points. While explicit descent methods are known to have severe convergence issues, implicit methods are natural in an adversarial setting, as they take the other player's optimal strategy into account. The implicit scheme proposed has an adaptive learning rate that makes it transition to Newton's method in the neighborhood of saddle points. Convergence is shown through local analysis and, in non convex-concave settings, thorough numerical examples in optimal transport and linear programming. An ad-hoc quasi Newton "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00233","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":"2026-05-17T23:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VZhyMar1WQjgs9YA8p2aw9zt/IoAPalaoIpGvBFZpLf6XpqbJXK6bIgBSJwDC1I/c5dPjxG4WUD5cR5eNU68Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:56:50.662978Z"},"content_sha256":"378086899576e9f2bbc164dde1dd6cf4d33158bc738e8b0a6c7303e741d6d9d7","schema_version":"1.0","event_id":"sha256:378086899576e9f2bbc164dde1dd6cf4d33158bc738e8b0a6c7303e741d6d9d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ML2SSWKITCFKSVDCAM52F6PB5W/bundle.json","state_url":"https://pith.science/pith/ML2SSWKITCFKSVDCAM52F6PB5W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ML2SSWKITCFKSVDCAM52F6PB5W/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":"2026-05-31T03:56:50Z","links":{"resolver":"https://pith.science/pith/ML2SSWKITCFKSVDCAM52F6PB5W","bundle":"https://pith.science/pith/ML2SSWKITCFKSVDCAM52F6PB5W/bundle.json","state":"https://pith.science/pith/ML2SSWKITCFKSVDCAM52F6PB5W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ML2SSWKITCFKSVDCAM52F6PB5W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ML2SSWKITCFKSVDCAM52F6PB5W","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":"3bab5132e46a24d594cecaa3dfe81bdb45269c1175e32eaf4592841bf60e8874","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-06-01T14:30:55Z","title_canon_sha256":"43b261e52891207dfbc49e38bc4ff592783b584a542be0d1a4e021dc65868cd5"},"schema_version":"1.0","source":{"id":"1906.00233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00233","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00233v1","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00233","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"ML2SSWKITCFK","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"ML2SSWKITCFKSVDC","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"ML2SSWKI","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:378086899576e9f2bbc164dde1dd6cf4d33158bc738e8b0a6c7303e741d6d9d7","target":"graph","created_at":"2026-05-17T23:44:27Z","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":"A game theory inspired methodology is proposed for finding a function's saddle points. While explicit descent methods are known to have severe convergence issues, implicit methods are natural in an adversarial setting, as they take the other player's optimal strategy into account. The implicit scheme proposed has an adaptive learning rate that makes it transition to Newton's method in the neighborhood of saddle points. Convergence is shown through local analysis and, in non convex-concave settings, thorough numerical examples in optimal transport and linear programming. An ad-hoc quasi Newton ","authors_text":"Esteban Tabak, Giulio Trigila, Montacer Essid","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-06-01T14:30:55Z","title":"An implicit gradient-descent procedure for minimax problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00233","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":"sha256:8f80451ef5ec9ece4bc48dce9f6dcea89187b03635b8693664f37b564ae2addf","target":"record","created_at":"2026-05-17T23:44:27Z","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":"3bab5132e46a24d594cecaa3dfe81bdb45269c1175e32eaf4592841bf60e8874","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-06-01T14:30:55Z","title_canon_sha256":"43b261e52891207dfbc49e38bc4ff592783b584a542be0d1a4e021dc65868cd5"},"schema_version":"1.0","source":{"id":"1906.00233","kind":"arxiv","version":1}},"canonical_sha256":"62f5295948988aa95462033ba2f9e1ed9bbf5bf2c3c690a2b4dce3e89146446d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62f5295948988aa95462033ba2f9e1ed9bbf5bf2c3c690a2b4dce3e89146446d","first_computed_at":"2026-05-17T23:44:27.781066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:27.781066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DXLXOwP9p7/VxTpSh36mnYoZv5+kEpASwd7tU+4+nhvrAF7ott3/6opME8g9eHpAhUC2rU6MV3UJ97l3z466BQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:27.781568Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f80451ef5ec9ece4bc48dce9f6dcea89187b03635b8693664f37b564ae2addf","sha256:378086899576e9f2bbc164dde1dd6cf4d33158bc738e8b0a6c7303e741d6d9d7"],"state_sha256":"39a019ab717bb996292dfc365127cad6dc83bebaa5d8b055598099e9758962e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"og7CjFi7nuoUc3UNB/QiKAmHbjv7IiI9pI1ZEH5fDCwnUoV3NrGgA2zYc94LZC6Wtb007KmwkT3nQWTWNi/ZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T03:56:50.664849Z","bundle_sha256":"dcb116f64bb4b4094064f1c351699b36d38887d34a5dee107e3114e567ceb6a2"}}