{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:U3HENN44H2FUIL22YQDWLDKCHQ","short_pith_number":"pith:U3HENN44","canonical_record":{"source":{"id":"1901.11149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-30T23:47:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ecf33e76a90c2db44934fcaff23649666d1e064d943ea0015dd16ce2a2dc8a3f","abstract_canon_sha256":"3da7c204ed6abff87a970de7c937feb44388b0da410f2da436aa08865760d14a"},"schema_version":"1.0"},"canonical_sha256":"a6ce46b79c3e8b442f5ac407658d423c1ac5d316f68fd2197ca07c8857d67f3e","source":{"kind":"arxiv","id":"1901.11149","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11149","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11149v1","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11149","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"U3HENN44H2FU","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"U3HENN44H2FUIL22","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"U3HENN44","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:U3HENN44H2FUIL22YQDWLDKCHQ","target":"record","payload":{"canonical_record":{"source":{"id":"1901.11149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-30T23:47:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ecf33e76a90c2db44934fcaff23649666d1e064d943ea0015dd16ce2a2dc8a3f","abstract_canon_sha256":"3da7c204ed6abff87a970de7c937feb44388b0da410f2da436aa08865760d14a"},"schema_version":"1.0"},"canonical_sha256":"a6ce46b79c3e8b442f5ac407658d423c1ac5d316f68fd2197ca07c8857d67f3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:02.567765Z","signature_b64":"snARyZ3qSg7Ee02r96FvmqfKbvAJgz/fWrL3W9DffCigdf+cEhOBUJVl+JAzIyffqQXmTsjWE6+JyNtE1q24Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6ce46b79c3e8b442f5ac407658d423c1ac5d316f68fd2197ca07c8857d67f3e","last_reissued_at":"2026-05-17T23:55:02.567257Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:02.567257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.11149","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":"2026-05-17T23:55:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n5mYxCqK3ywJ/EhwXG0GQygBztnKdOe8JAU8KTNwcaXCS4ElaZtXGiIEcUtKFO2Z+aChbMbIIV2QzPvFnIZWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T06:17:41.467759Z"},"content_sha256":"2ae9da1591a5a8b78c264c2a95ffde01420f04221d7616af94abf8cf75289851","schema_version":"1.0","event_id":"sha256:2ae9da1591a5a8b78c264c2a95ffde01420f04221d7616af94abf8cf75289851"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:U3HENN44H2FUIL22YQDWLDKCHQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Which Factorization Machine Modeling is Better: A Theoretical Answer with Optimal Guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jieping Ye, Liang Sun, Ming Lin, Qi Qian, Rong Jin, Shenghuo Zhu, Shuang Qiu, Xiaomin Song","submitted_at":"2019-01-30T23:47:21Z","abstract_excerpt":"Factorization machine (FM) is a popular machine learning model to capture the second order feature interactions. The optimal learning guarantee of FM and its generalized version is not yet developed. For a rank $k$ generalized FM of $d$ dimensional input, the previous best known sampling complexity is $\\mathcal{O}[k^{3}d\\cdot\\mathrm{polylog}(kd)]$ under Gaussian distribution. This bound is sub-optimal comparing to the information theoretical lower bound $\\mathcal{O}(kd)$. In this work, we aim to tighten this bound towards optimal and generalize the analysis to sub-gaussian distribution. We pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11149","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":"2026-05-17T23:55:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ojqWPUT+2wFsX0R2mG2PA/lx05rYl29OqpkhsQptojw0j7ehVhrihxIfEoNrM6gR26+2pV3vP9pxSGLchNR2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T06:17:41.468375Z"},"content_sha256":"82cd95477137a73f3061ed07424154c9a9e0a417014f6f155321439fa9e9c2bb","schema_version":"1.0","event_id":"sha256:82cd95477137a73f3061ed07424154c9a9e0a417014f6f155321439fa9e9c2bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3HENN44H2FUIL22YQDWLDKCHQ/bundle.json","state_url":"https://pith.science/pith/U3HENN44H2FUIL22YQDWLDKCHQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3HENN44H2FUIL22YQDWLDKCHQ/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":"2026-05-28T06:17:41Z","links":{"resolver":"https://pith.science/pith/U3HENN44H2FUIL22YQDWLDKCHQ","bundle":"https://pith.science/pith/U3HENN44H2FUIL22YQDWLDKCHQ/bundle.json","state":"https://pith.science/pith/U3HENN44H2FUIL22YQDWLDKCHQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3HENN44H2FUIL22YQDWLDKCHQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:U3HENN44H2FUIL22YQDWLDKCHQ","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":"3da7c204ed6abff87a970de7c937feb44388b0da410f2da436aa08865760d14a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-30T23:47:21Z","title_canon_sha256":"ecf33e76a90c2db44934fcaff23649666d1e064d943ea0015dd16ce2a2dc8a3f"},"schema_version":"1.0","source":{"id":"1901.11149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11149","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11149v1","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11149","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"U3HENN44H2FU","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"U3HENN44H2FUIL22","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"U3HENN44","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:82cd95477137a73f3061ed07424154c9a9e0a417014f6f155321439fa9e9c2bb","target":"graph","created_at":"2026-05-17T23:55:02Z","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":"Factorization machine (FM) is a popular machine learning model to capture the second order feature interactions. The optimal learning guarantee of FM and its generalized version is not yet developed. For a rank $k$ generalized FM of $d$ dimensional input, the previous best known sampling complexity is $\\mathcal{O}[k^{3}d\\cdot\\mathrm{polylog}(kd)]$ under Gaussian distribution. This bound is sub-optimal comparing to the information theoretical lower bound $\\mathcal{O}(kd)$. In this work, we aim to tighten this bound towards optimal and generalize the analysis to sub-gaussian distribution. We pro","authors_text":"Jieping Ye, Liang Sun, Ming Lin, Qi Qian, Rong Jin, Shenghuo Zhu, Shuang Qiu, Xiaomin Song","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-30T23:47:21Z","title":"Which Factorization Machine Modeling is Better: A Theoretical Answer with Optimal Guarantee"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11149","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":"sha256:2ae9da1591a5a8b78c264c2a95ffde01420f04221d7616af94abf8cf75289851","target":"record","created_at":"2026-05-17T23:55:02Z","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":"3da7c204ed6abff87a970de7c937feb44388b0da410f2da436aa08865760d14a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-30T23:47:21Z","title_canon_sha256":"ecf33e76a90c2db44934fcaff23649666d1e064d943ea0015dd16ce2a2dc8a3f"},"schema_version":"1.0","source":{"id":"1901.11149","kind":"arxiv","version":1}},"canonical_sha256":"a6ce46b79c3e8b442f5ac407658d423c1ac5d316f68fd2197ca07c8857d67f3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6ce46b79c3e8b442f5ac407658d423c1ac5d316f68fd2197ca07c8857d67f3e","first_computed_at":"2026-05-17T23:55:02.567257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:02.567257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"snARyZ3qSg7Ee02r96FvmqfKbvAJgz/fWrL3W9DffCigdf+cEhOBUJVl+JAzIyffqQXmTsjWE6+JyNtE1q24Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:02.567765Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.11149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ae9da1591a5a8b78c264c2a95ffde01420f04221d7616af94abf8cf75289851","sha256:82cd95477137a73f3061ed07424154c9a9e0a417014f6f155321439fa9e9c2bb"],"state_sha256":"73f80509863da6eebbb73336d3e2c1cca29e1accf81ac1eb940224c00ef77e14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HO9xLxQocAXiiLERQshADLGEZjEIBW2TUTRMiNJEfYvhrsS95H9WKUNf1M0/jA/xmxN28jivhJ+05fx29RkWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T06:17:41.471234Z","bundle_sha256":"958ee548126b913084920b022ee064ffdc8d63d257b518c4494f4494bf63651f"}}