{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:L34HJQNOFI4AYOWM2IYMWDMLSJ","short_pith_number":"pith:L34HJQNO","canonical_record":{"source":{"id":"1902.10409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T09:39:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fbf46fdfd25d4fd44319216f41664540d87ce203bfd9e4a0365488d412993578","abstract_canon_sha256":"5df1e43f7c60261d43a910e96e85a71075e918aeca8f99348f7b994140d23d1d"},"schema_version":"1.0"},"canonical_sha256":"5ef874c1ae2a380c3accd230cb0d8b924fa53e3b558b33c09d9df318190fbb76","source":{"kind":"arxiv","id":"1902.10409","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10409","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10409v2","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10409","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"L34HJQNOFI4A","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"L34HJQNOFI4AYOWM","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"L34HJQNO","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:L34HJQNOFI4AYOWM2IYMWDMLSJ","target":"record","payload":{"canonical_record":{"source":{"id":"1902.10409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T09:39:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fbf46fdfd25d4fd44319216f41664540d87ce203bfd9e4a0365488d412993578","abstract_canon_sha256":"5df1e43f7c60261d43a910e96e85a71075e918aeca8f99348f7b994140d23d1d"},"schema_version":"1.0"},"canonical_sha256":"5ef874c1ae2a380c3accd230cb0d8b924fa53e3b558b33c09d9df318190fbb76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:29.262850Z","signature_b64":"NncKL/09U6qEenHvRXdI0odtYq4av9PbV+q1QrrBDvi9S7VENOkYdKXdhVo13VfORZQxEGeBeQtzuyQXI2GxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ef874c1ae2a380c3accd230cb0d8b924fa53e3b558b33c09d9df318190fbb76","last_reissued_at":"2026-05-17T23:44:29.262092Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:29.262092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.10409","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":"2026-05-17T23:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcPoAf1Ts12SAQ18NZ1CYms5oUNm+9271w3ae6eDUQydSNf38W5mJWeWFZYYUVQZh+lpP3PdZ748f+7A+YfJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T19:21:24.098181Z"},"content_sha256":"e62bd001477a51338c87044dba4f42e7fbf0d200c7b85004df706fb5476ad744","schema_version":"1.0","event_id":"sha256:e62bd001477a51338c87044dba4f42e7fbf0d200c7b85004df706fb5476ad744"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:L34HJQNOFI4AYOWM2IYMWDMLSJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira, Kazuki Fukui","submitted_at":"2019-02-27T09:39:18Z","abstract_excerpt":"We propose $\\textit{weighted inner product similarity}$ (WIPS) for neural network-based graph embedding. In addition to the parameters of neural networks, we optimize the weights of the inner product by allowing positive and negative values. Despite its simplicity, WIPS can approximate arbitrary general similarities including positive definite, conditionally positive definite, and indefinite kernels. WIPS is free from similarity model selection, since it can learn any similarity models such as cosine similarity, negative Poincar\\'e distance and negative Wasserstein distance. Our experiments sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10409","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":"2026-05-17T23:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uv8w8cmN/vtmMnaaasqBgbPH0GrQ50W7Ko4G/PNQ56+Kiae1hnXuVCXP0+1/KSrWbP8XMWtuGceY0uhdRHCpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T19:21:24.098907Z"},"content_sha256":"d42b77c3d085c7f22679332d681e0f0e572893e64257af2df8a2adddba2b5f66","schema_version":"1.0","event_id":"sha256:d42b77c3d085c7f22679332d681e0f0e572893e64257af2df8a2adddba2b5f66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L34HJQNOFI4AYOWM2IYMWDMLSJ/bundle.json","state_url":"https://pith.science/pith/L34HJQNOFI4AYOWM2IYMWDMLSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L34HJQNOFI4AYOWM2IYMWDMLSJ/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":"2026-06-09T19:21:24Z","links":{"resolver":"https://pith.science/pith/L34HJQNOFI4AYOWM2IYMWDMLSJ","bundle":"https://pith.science/pith/L34HJQNOFI4AYOWM2IYMWDMLSJ/bundle.json","state":"https://pith.science/pith/L34HJQNOFI4AYOWM2IYMWDMLSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L34HJQNOFI4AYOWM2IYMWDMLSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:L34HJQNOFI4AYOWM2IYMWDMLSJ","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":"5df1e43f7c60261d43a910e96e85a71075e918aeca8f99348f7b994140d23d1d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T09:39:18Z","title_canon_sha256":"fbf46fdfd25d4fd44319216f41664540d87ce203bfd9e4a0365488d412993578"},"schema_version":"1.0","source":{"id":"1902.10409","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10409","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10409v2","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10409","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"L34HJQNOFI4A","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"L34HJQNOFI4AYOWM","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"L34HJQNO","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:d42b77c3d085c7f22679332d681e0f0e572893e64257af2df8a2adddba2b5f66","target":"graph","created_at":"2026-05-17T23:44:29Z","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":"We propose $\\textit{weighted inner product similarity}$ (WIPS) for neural network-based graph embedding. In addition to the parameters of neural networks, we optimize the weights of the inner product by allowing positive and negative values. Despite its simplicity, WIPS can approximate arbitrary general similarities including positive definite, conditionally positive definite, and indefinite kernels. WIPS is free from similarity model selection, since it can learn any similarity models such as cosine similarity, negative Poincar\\'e distance and negative Wasserstein distance. Our experiments sh","authors_text":"Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira, Kazuki Fukui","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T09:39:18Z","title":"Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10409","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:e62bd001477a51338c87044dba4f42e7fbf0d200c7b85004df706fb5476ad744","target":"record","created_at":"2026-05-17T23:44:29Z","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":"5df1e43f7c60261d43a910e96e85a71075e918aeca8f99348f7b994140d23d1d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T09:39:18Z","title_canon_sha256":"fbf46fdfd25d4fd44319216f41664540d87ce203bfd9e4a0365488d412993578"},"schema_version":"1.0","source":{"id":"1902.10409","kind":"arxiv","version":2}},"canonical_sha256":"5ef874c1ae2a380c3accd230cb0d8b924fa53e3b558b33c09d9df318190fbb76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ef874c1ae2a380c3accd230cb0d8b924fa53e3b558b33c09d9df318190fbb76","first_computed_at":"2026-05-17T23:44:29.262092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:29.262092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NncKL/09U6qEenHvRXdI0odtYq4av9PbV+q1QrrBDvi9S7VENOkYdKXdhVo13VfORZQxEGeBeQtzuyQXI2GxCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:29.262850Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10409","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e62bd001477a51338c87044dba4f42e7fbf0d200c7b85004df706fb5476ad744","sha256:d42b77c3d085c7f22679332d681e0f0e572893e64257af2df8a2adddba2b5f66"],"state_sha256":"b1da8e27194885d9bb3b0af5454b7dfe64daa5508c2fbb0e030396d4a5efc990"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yUc53CtreUcMO9kzC9i1aFzPRO3qZCvL3ZzKETn1wKc+NpoiC+4v2sEeV9MEXETOfcHvW4lTyBhtR3uq7cu2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T19:21:24.102548Z","bundle_sha256":"3773279e3e42ece61a9a56e4b54c244387fedc7cb7f1c7dac4b97e7c0e990a67"}}