{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7DPMI5YGUMH352MTOHPLKDFG3E","short_pith_number":"pith:7DPMI5YG","canonical_record":{"source":{"id":"2211.09908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-11-17T21:44:33Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"175afc63b8349209334d23abb60d0799489ffa39669fc547f6d0e2ac2913a70a","abstract_canon_sha256":"688ecb7913c1bc28b253f807071c650dd2f6b58edd1f3840c524b0af44288551"},"schema_version":"1.0"},"canonical_sha256":"f8dec47706a30fbee99371deb50ca6d90167a8afbf6368c355932bfbfd3ef3c2","source":{"kind":"arxiv","id":"2211.09908","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09908","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09908v1","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09908","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"7DPMI5YGUMH3","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"pith_short_16","alias_value":"7DPMI5YGUMH352MT","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"pith_short_8","alias_value":"7DPMI5YG","created_at":"2026-07-05T05:17:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7DPMI5YGUMH352MTOHPLKDFG3E","target":"record","payload":{"canonical_record":{"source":{"id":"2211.09908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-11-17T21:44:33Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"175afc63b8349209334d23abb60d0799489ffa39669fc547f6d0e2ac2913a70a","abstract_canon_sha256":"688ecb7913c1bc28b253f807071c650dd2f6b58edd1f3840c524b0af44288551"},"schema_version":"1.0"},"canonical_sha256":"f8dec47706a30fbee99371deb50ca6d90167a8afbf6368c355932bfbfd3ef3c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:15.405270Z","signature_b64":"03bgIEMRUIGpcV8Dq4cP3/2ZHTWgMS90R1G2LVWQnuLPBPCaO65VB9UniwDZsrbJeNMrmd0a+IFIG3KZlD6vAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8dec47706a30fbee99371deb50ca6d90167a8afbf6368c355932bfbfd3ef3c2","last_reissued_at":"2026-07-05T05:17:15.404789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:15.404789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.09908","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":"2026-07-05T05:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uf9+ZaLT0gUq4ZJOBzwwwFwRjMh7JWZiP35TQNHSLi7tzd5bQs0nJfoqpLB2bHfkm+eG/sQ86ughGT48AzU9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:49:08.699828Z"},"content_sha256":"886c86d34adf05eac16b049df999d417ba9c9f07b9db227919eec6d068ebcfdd","schema_version":"1.0","event_id":"sha256:886c86d34adf05eac16b049df999d417ba9c9f07b9db227919eec6d068ebcfdd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7DPMI5YGUMH352MTOHPLKDFG3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Escaping From Saddle Points Using Asynchronous Coordinate Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"math.OC","authors_text":"Furong Huang, Jingling Li, Jin-Peng Liu, Marco Bornstein","submitted_at":"2022-11-17T21:44:33Z","abstract_excerpt":"Large-scale non-convex optimization problems are expensive to solve due to computational and memory costs. To reduce the costs, first-order (computationally efficient) and asynchronous-parallel (memory efficient) algorithms are necessary to minimize non-convex functions in machine learning. However, asynchronous-first-order methods applied within non-convex settings run into two difficulties: (i) parallelization delays, which affect convergence by disrupting the monotonicity of first-order methods, and (ii) sub-optimal saddle points where the gradient is zero. To solve these two difficulties, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09908","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.09908/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":"2026-07-05T05:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v9uL7am0sys2YsxmdsvScVVlt26eHfwdHyLqmT5tZ9Zh8X+LBZyE3Dcxs+AowyiEUbdnQFbafiw5ZX1Cr4VIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:49:08.700381Z"},"content_sha256":"c47a9524fc169a3d3b32776e99035f40df47f56a2d4e02cab4499e7314b5fea7","schema_version":"1.0","event_id":"sha256:c47a9524fc169a3d3b32776e99035f40df47f56a2d4e02cab4499e7314b5fea7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DPMI5YGUMH352MTOHPLKDFG3E/bundle.json","state_url":"https://pith.science/pith/7DPMI5YGUMH352MTOHPLKDFG3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DPMI5YGUMH352MTOHPLKDFG3E/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":"2026-08-06T10:49:08Z","links":{"resolver":"https://pith.science/pith/7DPMI5YGUMH352MTOHPLKDFG3E","bundle":"https://pith.science/pith/7DPMI5YGUMH352MTOHPLKDFG3E/bundle.json","state":"https://pith.science/pith/7DPMI5YGUMH352MTOHPLKDFG3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DPMI5YGUMH352MTOHPLKDFG3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7DPMI5YGUMH352MTOHPLKDFG3E","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":"688ecb7913c1bc28b253f807071c650dd2f6b58edd1f3840c524b0af44288551","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-11-17T21:44:33Z","title_canon_sha256":"175afc63b8349209334d23abb60d0799489ffa39669fc547f6d0e2ac2913a70a"},"schema_version":"1.0","source":{"id":"2211.09908","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09908","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09908v1","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09908","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"7DPMI5YGUMH3","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"pith_short_16","alias_value":"7DPMI5YGUMH352MT","created_at":"2026-07-05T05:17:15Z"},{"alias_kind":"pith_short_8","alias_value":"7DPMI5YG","created_at":"2026-07-05T05:17:15Z"}],"graph_snapshots":[{"event_id":"sha256:c47a9524fc169a3d3b32776e99035f40df47f56a2d4e02cab4499e7314b5fea7","target":"graph","created_at":"2026-07-05T05:17:15Z","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/2211.09908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale non-convex optimization problems are expensive to solve due to computational and memory costs. To reduce the costs, first-order (computationally efficient) and asynchronous-parallel (memory efficient) algorithms are necessary to minimize non-convex functions in machine learning. However, asynchronous-first-order methods applied within non-convex settings run into two difficulties: (i) parallelization delays, which affect convergence by disrupting the monotonicity of first-order methods, and (ii) sub-optimal saddle points where the gradient is zero. To solve these two difficulties, ","authors_text":"Furong Huang, Jingling Li, Jin-Peng Liu, Marco Bornstein","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-11-17T21:44:33Z","title":"Escaping From Saddle Points Using Asynchronous Coordinate Gradient Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09908","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":"sha256:886c86d34adf05eac16b049df999d417ba9c9f07b9db227919eec6d068ebcfdd","target":"record","created_at":"2026-07-05T05:17:15Z","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":"688ecb7913c1bc28b253f807071c650dd2f6b58edd1f3840c524b0af44288551","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-11-17T21:44:33Z","title_canon_sha256":"175afc63b8349209334d23abb60d0799489ffa39669fc547f6d0e2ac2913a70a"},"schema_version":"1.0","source":{"id":"2211.09908","kind":"arxiv","version":1}},"canonical_sha256":"f8dec47706a30fbee99371deb50ca6d90167a8afbf6368c355932bfbfd3ef3c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8dec47706a30fbee99371deb50ca6d90167a8afbf6368c355932bfbfd3ef3c2","first_computed_at":"2026-07-05T05:17:15.404789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:15.404789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"03bgIEMRUIGpcV8Dq4cP3/2ZHTWgMS90R1G2LVWQnuLPBPCaO65VB9UniwDZsrbJeNMrmd0a+IFIG3KZlD6vAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:15.405270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09908","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:886c86d34adf05eac16b049df999d417ba9c9f07b9db227919eec6d068ebcfdd","sha256:c47a9524fc169a3d3b32776e99035f40df47f56a2d4e02cab4499e7314b5fea7"],"state_sha256":"eb6ec6d5f162a131662df2f1ff66b8af648beffed1aa8f27225478f71bbbb049"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wn4vfmXwLmMMAbdiUIT1xZhPkv7BimbqCxfzrfauVqOOI7hQZ/ssGckZhmyNA53RJmhtCtAA1Ua/PC6SQYNQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:49:08.705190Z","bundle_sha256":"fa05d5ad329f1a1f1c3518cd14551fdc7a4a80b117a74e165a9cf58c3190d8cc"}}