{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YB4KZCA3SJMCLNLMUHZ3MXIHQ7","short_pith_number":"pith:YB4KZCA3","canonical_record":{"source":{"id":"2606.21434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T13:49:47Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"e54be16bf713e11c7e0fdcb3419783475da57f3143f92e3047daf3742005ee77","abstract_canon_sha256":"b196b7df0c8af41f2c8c3a385440bb7cd3a0b9a71f089a25e8f5278dafaa5e1c"},"schema_version":"1.0"},"canonical_sha256":"c078ac881b925825b56ca1f3b65d0787ca2128506b1b4fb2982c2349261f243e","source":{"kind":"arxiv","id":"2606.21434","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21434","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21434v1","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21434","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"YB4KZCA3SJMC","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"YB4KZCA3SJMCLNLM","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"YB4KZCA3","created_at":"2026-06-23T01:13:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YB4KZCA3SJMCLNLMUHZ3MXIHQ7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T13:49:47Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"e54be16bf713e11c7e0fdcb3419783475da57f3143f92e3047daf3742005ee77","abstract_canon_sha256":"b196b7df0c8af41f2c8c3a385440bb7cd3a0b9a71f089a25e8f5278dafaa5e1c"},"schema_version":"1.0"},"canonical_sha256":"c078ac881b925825b56ca1f3b65d0787ca2128506b1b4fb2982c2349261f243e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:10.039467Z","signature_b64":"oLS5TErmhm2pSHk+akXSq1hXWcHoDlpPZZIIIPTJCYD9px0oQLtvvRVkyFJ9++QNiSqYfbKYzVuo3UvSHoj0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c078ac881b925825b56ca1f3b65d0787ca2128506b1b4fb2982c2349261f243e","last_reissued_at":"2026-06-23T01:13:10.039018Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:10.039018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21434","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":"2026-06-23T01:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0OsdhS5L4I44/pVSOhU+rOWuuztdtNGsRz4eBhBmR4TeQ+Pf8UZhzw8kqDYRFCVZcbxHBhgK4FzqBAZwvxNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T14:57:29.757853Z"},"content_sha256":"ab525a409e2a02175cb4ec039ae81ba746b2334b1d999975f4668378493ea25d","schema_version":"1.0","event_id":"sha256:ab525a409e2a02175cb4ec039ae81ba746b2334b1d999975f4668378493ea25d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YB4KZCA3SJMCLNLMUHZ3MXIHQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal Encoders for Modular Relational Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Gustav \\v{S}\\'ir, Jakub Pele\\v{s}ka","submitted_at":"2026-06-19T13:49:47Z","abstract_excerpt":"Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs for end-to-end representation learning. While RDL is evolving rapidly, existing approaches face significant generalization obstacles. They are either schema-specific, requiring training from scratch for every new database, or they rely on monolithic architectures that entangle feature encoding with graph message-passing. Analyzing these limitations, we establish four core pillars for building foundational relational models: semantic granularity, structural topology, temporal causality, and unified op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21434","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/2606.21434/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":"2026-06-23T01:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Dl5XC4FLNaveNtbWQLgTGO/pZ0cloYCmrbPfzeBt02W8tH7xn+dUj3ZSXqA6l51zsQcz2E20DHvz9vnWTK/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T14:57:29.758227Z"},"content_sha256":"c9921c67e547d456622b8efb771788f44184b4f6db26f04265780bb27b1d6489","schema_version":"1.0","event_id":"sha256:c9921c67e547d456622b8efb771788f44184b4f6db26f04265780bb27b1d6489"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YB4KZCA3SJMCLNLMUHZ3MXIHQ7/bundle.json","state_url":"https://pith.science/pith/YB4KZCA3SJMCLNLMUHZ3MXIHQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YB4KZCA3SJMCLNLMUHZ3MXIHQ7/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":"2026-07-04T14:57:29Z","links":{"resolver":"https://pith.science/pith/YB4KZCA3SJMCLNLMUHZ3MXIHQ7","bundle":"https://pith.science/pith/YB4KZCA3SJMCLNLMUHZ3MXIHQ7/bundle.json","state":"https://pith.science/pith/YB4KZCA3SJMCLNLMUHZ3MXIHQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YB4KZCA3SJMCLNLMUHZ3MXIHQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YB4KZCA3SJMCLNLMUHZ3MXIHQ7","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":"b196b7df0c8af41f2c8c3a385440bb7cd3a0b9a71f089a25e8f5278dafaa5e1c","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T13:49:47Z","title_canon_sha256":"e54be16bf713e11c7e0fdcb3419783475da57f3143f92e3047daf3742005ee77"},"schema_version":"1.0","source":{"id":"2606.21434","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21434","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21434v1","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21434","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"YB4KZCA3SJMC","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"YB4KZCA3SJMCLNLM","created_at":"2026-06-23T01:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"YB4KZCA3","created_at":"2026-06-23T01:13:10Z"}],"graph_snapshots":[{"event_id":"sha256:c9921c67e547d456622b8efb771788f44184b4f6db26f04265780bb27b1d6489","target":"graph","created_at":"2026-06-23T01:13:10Z","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/2606.21434/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs for end-to-end representation learning. While RDL is evolving rapidly, existing approaches face significant generalization obstacles. They are either schema-specific, requiring training from scratch for every new database, or they rely on monolithic architectures that entangle feature encoding with graph message-passing. Analyzing these limitations, we establish four core pillars for building foundational relational models: semantic granularity, structural topology, temporal causality, and unified op","authors_text":"Gustav \\v{S}\\'ir, Jakub Pele\\v{s}ka","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T13:49:47Z","title":"Universal Encoders for Modular Relational Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21434","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:ab525a409e2a02175cb4ec039ae81ba746b2334b1d999975f4668378493ea25d","target":"record","created_at":"2026-06-23T01:13:10Z","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":"b196b7df0c8af41f2c8c3a385440bb7cd3a0b9a71f089a25e8f5278dafaa5e1c","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T13:49:47Z","title_canon_sha256":"e54be16bf713e11c7e0fdcb3419783475da57f3143f92e3047daf3742005ee77"},"schema_version":"1.0","source":{"id":"2606.21434","kind":"arxiv","version":1}},"canonical_sha256":"c078ac881b925825b56ca1f3b65d0787ca2128506b1b4fb2982c2349261f243e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c078ac881b925825b56ca1f3b65d0787ca2128506b1b4fb2982c2349261f243e","first_computed_at":"2026-06-23T01:13:10.039018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:10.039018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oLS5TErmhm2pSHk+akXSq1hXWcHoDlpPZZIIIPTJCYD9px0oQLtvvRVkyFJ9++QNiSqYfbKYzVuo3UvSHoj0DA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:10.039467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21434","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab525a409e2a02175cb4ec039ae81ba746b2334b1d999975f4668378493ea25d","sha256:c9921c67e547d456622b8efb771788f44184b4f6db26f04265780bb27b1d6489"],"state_sha256":"73ee8665a1407950952044787ea48a011ff5a2993392b22d7bfe7358d36bdde1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Phj6gfan3s8SM0aI9ifaq8+eu8QDUg4JEbu3r3Yq+M1h1k/Sr6YZ4g1eWOrsTQQilA1+UAS6cQfyeyAND2myBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T14:57:29.760250Z","bundle_sha256":"65961624e7520c86e68bb0a8a9273a17258bee61b2e95c4b9e63204a781f0e0a"}}