{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JIXWATEFOBYUQ3RMAG7C23OS5X","short_pith_number":"pith:JIXWATEF","canonical_record":{"source":{"id":"1910.03524","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T16:31:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b85637d8526d896d6570f23bbb1d654fc546ca02d26b44ff8f79dd1051fa611e","abstract_canon_sha256":"d6bb7ef3ca8cc0614a8a42f05e3252bb07bea62da70b43aa44b1b1d5af32c291"},"schema_version":"1.0"},"canonical_sha256":"4a2f604c857071486e2c01be2d6dd2edea60baf5a939b7ebc0ec1406558ad834","source":{"kind":"arxiv","id":"1910.03524","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.03524","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"arxiv_version","alias_value":"1910.03524v4","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03524","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"pith_short_12","alias_value":"JIXWATEFOBYU","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"pith_short_16","alias_value":"JIXWATEFOBYUQ3RM","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"pith_short_8","alias_value":"JIXWATEF","created_at":"2026-07-05T00:12:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JIXWATEFOBYUQ3RMAG7C23OS5X","target":"record","payload":{"canonical_record":{"source":{"id":"1910.03524","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T16:31:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b85637d8526d896d6570f23bbb1d654fc546ca02d26b44ff8f79dd1051fa611e","abstract_canon_sha256":"d6bb7ef3ca8cc0614a8a42f05e3252bb07bea62da70b43aa44b1b1d5af32c291"},"schema_version":"1.0"},"canonical_sha256":"4a2f604c857071486e2c01be2d6dd2edea60baf5a939b7ebc0ec1406558ad834","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:30.214224Z","signature_b64":"edShkwduowypKfCi6yMkoRhZx9VRkpt6LIC3fipTO1APe/aEfyLN1hv2/rA1UVC6TWfa59EQCQ6FbwQ3bUinCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a2f604c857071486e2c01be2d6dd2edea60baf5a939b7ebc0ec1406558ad834","last_reissued_at":"2026-07-05T00:12:30.213793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:30.213793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.03524","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:12:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hLIhEkZZjdJWmmtjzYrndqHRYNem4Pd3vtinvn/gIRmK1PLgNsepx9K4+cP4/qxj2o+mj+cnGqT5NQaP7IuCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:23:34.561911Z"},"content_sha256":"62844d58632fa02ecbe82a20b82631ec479d9d656a244a45da047f50dbad1748","schema_version":"1.0","event_id":"sha256:62844d58632fa02ecbe82a20b82631ec479d9d656a244a45da047f50dbad1748"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JIXWATEFOBYUQ3RMAG7C23OS5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Denis Mazur, Stanislav Morozov, Vage Egiazarian","submitted_at":"2019-10-08T16:31:11Z","abstract_excerpt":"Learning useful representations is a key ingredient to the success of modern machine learning. Currently, representation learning mostly relies on embedding data into Euclidean space. However, recent work has shown that data in some domains is better modeled by non-euclidean metric spaces, and inappropriate geometry can result in inferior performance. In this paper, we aim to eliminate the inductive bias imposed by the embedding space geometry. Namely, we propose to map data into more general non-vector metric spaces: a weighted graph with a shortest path distance. By design, such graphs can m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.03524","kind":"arxiv","version":4},"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/1910.03524/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":"2026-07-05T00:12:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t99DbLYRFiLbrGgEESajKpY3Fbf0x/AjOobvmaCnwGTj7UW0HGi3kA1WbTROcTplnKNhFPfahUYYOOreRt/8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:23:34.562289Z"},"content_sha256":"5558512b1c9fee0e2383bc656982176ed3d3856bfd022a792dea5b36f3d1e95e","schema_version":"1.0","event_id":"sha256:5558512b1c9fee0e2383bc656982176ed3d3856bfd022a792dea5b36f3d1e95e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JIXWATEFOBYUQ3RMAG7C23OS5X/bundle.json","state_url":"https://pith.science/pith/JIXWATEFOBYUQ3RMAG7C23OS5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JIXWATEFOBYUQ3RMAG7C23OS5X/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":"2026-07-08T12:23:34Z","links":{"resolver":"https://pith.science/pith/JIXWATEFOBYUQ3RMAG7C23OS5X","bundle":"https://pith.science/pith/JIXWATEFOBYUQ3RMAG7C23OS5X/bundle.json","state":"https://pith.science/pith/JIXWATEFOBYUQ3RMAG7C23OS5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JIXWATEFOBYUQ3RMAG7C23OS5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JIXWATEFOBYUQ3RMAG7C23OS5X","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":"d6bb7ef3ca8cc0614a8a42f05e3252bb07bea62da70b43aa44b1b1d5af32c291","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T16:31:11Z","title_canon_sha256":"b85637d8526d896d6570f23bbb1d654fc546ca02d26b44ff8f79dd1051fa611e"},"schema_version":"1.0","source":{"id":"1910.03524","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.03524","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"arxiv_version","alias_value":"1910.03524v4","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03524","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"pith_short_12","alias_value":"JIXWATEFOBYU","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"pith_short_16","alias_value":"JIXWATEFOBYUQ3RM","created_at":"2026-07-05T00:12:30Z"},{"alias_kind":"pith_short_8","alias_value":"JIXWATEF","created_at":"2026-07-05T00:12:30Z"}],"graph_snapshots":[{"event_id":"sha256:5558512b1c9fee0e2383bc656982176ed3d3856bfd022a792dea5b36f3d1e95e","target":"graph","created_at":"2026-07-05T00:12:30Z","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/1910.03524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning useful representations is a key ingredient to the success of modern machine learning. Currently, representation learning mostly relies on embedding data into Euclidean space. However, recent work has shown that data in some domains is better modeled by non-euclidean metric spaces, and inappropriate geometry can result in inferior performance. In this paper, we aim to eliminate the inductive bias imposed by the embedding space geometry. Namely, we propose to map data into more general non-vector metric spaces: a weighted graph with a shortest path distance. By design, such graphs can m","authors_text":"Artem Babenko, Denis Mazur, Stanislav Morozov, Vage Egiazarian","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T16:31:11Z","title":"Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.03524","kind":"arxiv","version":4},"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":"sha256:62844d58632fa02ecbe82a20b82631ec479d9d656a244a45da047f50dbad1748","target":"record","created_at":"2026-07-05T00:12:30Z","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":"d6bb7ef3ca8cc0614a8a42f05e3252bb07bea62da70b43aa44b1b1d5af32c291","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T16:31:11Z","title_canon_sha256":"b85637d8526d896d6570f23bbb1d654fc546ca02d26b44ff8f79dd1051fa611e"},"schema_version":"1.0","source":{"id":"1910.03524","kind":"arxiv","version":4}},"canonical_sha256":"4a2f604c857071486e2c01be2d6dd2edea60baf5a939b7ebc0ec1406558ad834","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a2f604c857071486e2c01be2d6dd2edea60baf5a939b7ebc0ec1406558ad834","first_computed_at":"2026-07-05T00:12:30.213793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:12:30.213793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"edShkwduowypKfCi6yMkoRhZx9VRkpt6LIC3fipTO1APe/aEfyLN1hv2/rA1UVC6TWfa59EQCQ6FbwQ3bUinCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:12:30.214224Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.03524","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62844d58632fa02ecbe82a20b82631ec479d9d656a244a45da047f50dbad1748","sha256:5558512b1c9fee0e2383bc656982176ed3d3856bfd022a792dea5b36f3d1e95e"],"state_sha256":"d11ddcb58ccd0f241814a19a8b3c1d0748f3f52af0b34ebd145b50ec14c55ffc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2E+or8Ixr0jaZeP4t4VAZkFKBz8yDM0sEWt+yNjD12AWQOmbobc2EKPWfMxZXwzvBhOoxDRKaUYYzpc5DKwmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T12:23:34.564597Z","bundle_sha256":"c46bd1d6f76aa1910a0fa93d3f7ce3f072aee7fc4a1868cb88f74595bc898e13"}}