{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2SVBSXY3MI3GGWQUPB2OSOV26F","short_pith_number":"pith:2SVBSXY3","canonical_record":{"source":{"id":"1803.04300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-12T15:10:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"77c73228e4ff6b4a6aa431ee6638b9da4227372bba17e032606d07fd2ae67a83","abstract_canon_sha256":"ce8cb4099cce589a4b315d7a87ad9ac443872e1ff3d1113c211a9bb38797c4fb"},"schema_version":"1.0"},"canonical_sha256":"d4aa195f1b6236635a147874e93abaf167ba799d7a7b4a91a2f160eb7844df5f","source":{"kind":"arxiv","id":"1803.04300","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.04300","created_at":"2026-05-18T00:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"1803.04300v2","created_at":"2026-05-18T00:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04300","created_at":"2026-05-18T00:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"2SVBSXY3MI3G","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2SVBSXY3MI3GGWQU","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2SVBSXY3","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2SVBSXY3MI3GGWQUPB2OSOV26F","target":"record","payload":{"canonical_record":{"source":{"id":"1803.04300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-12T15:10:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"77c73228e4ff6b4a6aa431ee6638b9da4227372bba17e032606d07fd2ae67a83","abstract_canon_sha256":"ce8cb4099cce589a4b315d7a87ad9ac443872e1ff3d1113c211a9bb38797c4fb"},"schema_version":"1.0"},"canonical_sha256":"d4aa195f1b6236635a147874e93abaf167ba799d7a7b4a91a2f160eb7844df5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:35.898419Z","signature_b64":"0fw5ndD9vzCnblWojFCYoZtd8fjDFlxA86tK7SKVCdk0G2K4NXsBUKPputhuLOYpWdsW8KCS4teEWVw2a9RPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4aa195f1b6236635a147874e93abaf167ba799d7a7b4a91a2f160eb7844df5f","last_reissued_at":"2026-05-18T00:09:35.897954Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:35.897954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.04300","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":"2026-05-18T00:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lhkNlfiMl+mxQmLP4I1lWzn30Bnd2eSBLT2cTvCA428MlMHP9O7AT1lhahip8UE8NZjDzeq1M8zen6Kjh7DjDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:16:20.020687Z"},"content_sha256":"95aaabbcf4a6147b9f580c78cb07d62cdf344b6a7f0e3924cf94309fa348070d","schema_version":"1.0","event_id":"sha256:95aaabbcf4a6147b9f580c78cb07d62cdf344b6a7f0e3924cf94309fa348070d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2SVBSXY3MI3GGWQUPB2OSOV26F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Conditional Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Bauckhage, Kristian Kersting, Patrick Schramowski","submitted_at":"2018-03-12T15:10:45Z","abstract_excerpt":"The move from hand-designed to learned optimizers in machine learning has been quite successful for gradient-based and -free optimizers. When facing a constrained problem, however, maintaining feasibility typically requires a projection step, which might be computationally expensive and not differentiable. We show how the design of projection-free convex optimization algorithms can be cast as a learning problem based on Frank-Wolfe Networks: recurrent networks implementing the Frank-Wolfe algorithm aka. conditional gradients. This allows them to learn to exploit structure when, e.g., optimizin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04300","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":"2026-05-18T00:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z0izzA+uxJ449tdnpuAQKwSdav8Q0qi03wzO4/mff0cv6jhvZskXY/IjePQ1dvt1NZkZ9GzeT29ZfcFkLrHqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:16:20.021280Z"},"content_sha256":"b06452a144712e83c27fb3e7bf9671c30f0bc99bdfaa4e73767eff97c7614ca7","schema_version":"1.0","event_id":"sha256:b06452a144712e83c27fb3e7bf9671c30f0bc99bdfaa4e73767eff97c7614ca7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2SVBSXY3MI3GGWQUPB2OSOV26F/bundle.json","state_url":"https://pith.science/pith/2SVBSXY3MI3GGWQUPB2OSOV26F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2SVBSXY3MI3GGWQUPB2OSOV26F/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":"2026-05-27T22:16:20Z","links":{"resolver":"https://pith.science/pith/2SVBSXY3MI3GGWQUPB2OSOV26F","bundle":"https://pith.science/pith/2SVBSXY3MI3GGWQUPB2OSOV26F/bundle.json","state":"https://pith.science/pith/2SVBSXY3MI3GGWQUPB2OSOV26F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2SVBSXY3MI3GGWQUPB2OSOV26F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2SVBSXY3MI3GGWQUPB2OSOV26F","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":"ce8cb4099cce589a4b315d7a87ad9ac443872e1ff3d1113c211a9bb38797c4fb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-12T15:10:45Z","title_canon_sha256":"77c73228e4ff6b4a6aa431ee6638b9da4227372bba17e032606d07fd2ae67a83"},"schema_version":"1.0","source":{"id":"1803.04300","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.04300","created_at":"2026-05-18T00:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"1803.04300v2","created_at":"2026-05-18T00:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04300","created_at":"2026-05-18T00:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"2SVBSXY3MI3G","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2SVBSXY3MI3GGWQU","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2SVBSXY3","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:b06452a144712e83c27fb3e7bf9671c30f0bc99bdfaa4e73767eff97c7614ca7","target":"graph","created_at":"2026-05-18T00:09:35Z","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":"The move from hand-designed to learned optimizers in machine learning has been quite successful for gradient-based and -free optimizers. When facing a constrained problem, however, maintaining feasibility typically requires a projection step, which might be computationally expensive and not differentiable. We show how the design of projection-free convex optimization algorithms can be cast as a learning problem based on Frank-Wolfe Networks: recurrent networks implementing the Frank-Wolfe algorithm aka. conditional gradients. This allows them to learn to exploit structure when, e.g., optimizin","authors_text":"Christian Bauckhage, Kristian Kersting, Patrick Schramowski","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-12T15:10:45Z","title":"Neural Conditional Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04300","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":"sha256:95aaabbcf4a6147b9f580c78cb07d62cdf344b6a7f0e3924cf94309fa348070d","target":"record","created_at":"2026-05-18T00:09:35Z","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":"ce8cb4099cce589a4b315d7a87ad9ac443872e1ff3d1113c211a9bb38797c4fb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-12T15:10:45Z","title_canon_sha256":"77c73228e4ff6b4a6aa431ee6638b9da4227372bba17e032606d07fd2ae67a83"},"schema_version":"1.0","source":{"id":"1803.04300","kind":"arxiv","version":2}},"canonical_sha256":"d4aa195f1b6236635a147874e93abaf167ba799d7a7b4a91a2f160eb7844df5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4aa195f1b6236635a147874e93abaf167ba799d7a7b4a91a2f160eb7844df5f","first_computed_at":"2026-05-18T00:09:35.897954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:35.897954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0fw5ndD9vzCnblWojFCYoZtd8fjDFlxA86tK7SKVCdk0G2K4NXsBUKPputhuLOYpWdsW8KCS4teEWVw2a9RPBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:35.898419Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.04300","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95aaabbcf4a6147b9f580c78cb07d62cdf344b6a7f0e3924cf94309fa348070d","sha256:b06452a144712e83c27fb3e7bf9671c30f0bc99bdfaa4e73767eff97c7614ca7"],"state_sha256":"9ff5d325418f31dbb21560309e4109c7cdd176979f30906ea0bcfd07f616de43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4bhIOmTqhK5ap96douoYnqmejgiEk0eD83WFKGFxubLiMbP48aXcOhT2YBCj8wyYRkfPKq/Jv/3jAQjfZwaDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:16:20.023662Z","bundle_sha256":"a97db1369f1e18f08cacb7f7450c4f177e40410aab9a34ba671eedd93fe98252"}}