{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ELNIZIFLMVOCUO4FEWXF7YEMLB","short_pith_number":"pith:ELNIZIFL","canonical_record":{"source":{"id":"2608.13023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T09:46:29Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"3243b38f22c5b641a7c6f6c2bb8f2e8c3d72103fcb64af1c15e7268e7cae8f1f","abstract_canon_sha256":"437d1e6fda74806c1c2a4c1f74e99bdbc21023fd2400d4094041ad39d7ac309c"},"schema_version":"1.0"},"canonical_sha256":"22da8ca0ab655c2a3b8525ae5fe08c585b68be7a5b3a82a4eb4d6bbf510b7bec","source":{"kind":"arxiv","id":"2608.13023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13023","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13023v1","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13023","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"ELNIZIFLMVOC","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"ELNIZIFLMVOCUO4F","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"ELNIZIFL","created_at":"2026-08-14T01:00:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ELNIZIFLMVOCUO4FEWXF7YEMLB","target":"record","payload":{"canonical_record":{"source":{"id":"2608.13023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T09:46:29Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"3243b38f22c5b641a7c6f6c2bb8f2e8c3d72103fcb64af1c15e7268e7cae8f1f","abstract_canon_sha256":"437d1e6fda74806c1c2a4c1f74e99bdbc21023fd2400d4094041ad39d7ac309c"},"schema_version":"1.0"},"canonical_sha256":"22da8ca0ab655c2a3b8525ae5fe08c585b68be7a5b3a82a4eb4d6bbf510b7bec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:08.907224Z","signature_b64":"OjSdsFAsucZv29SypczD7bFk8liV8kW+bnc4N93Tebh5uuqZCM/ya8t16uZbeb/0KO0noXN77RY+12cAVoLZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22da8ca0ab655c2a3b8525ae5fe08c585b68be7a5b3a82a4eb4d6bbf510b7bec","last_reissued_at":"2026-08-14T01:00:08.905137Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:08.905137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.13023","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":"2026-08-14T01:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6urnRfAjDEsRcMXDOneK5vbtC1uYprBE8VfeXGbJOz3vt9zoin9FJWxGHff/Ia5Je4QqH+rru++tSH2JcuYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:16:23.797959Z"},"content_sha256":"39baa4b766e013bc781079a663759923795d31f1d88b72f78070d206b802d55f","schema_version":"1.0","event_id":"sha256:39baa4b766e013bc781079a663759923795d31f1d88b72f78070d206b802d55f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ELNIZIFLMVOCUO4FEWXF7YEMLB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incremental Evaluation and Training in 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":"2026-08-13T09:46:29Z","abstract_excerpt":"Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs to enable end-to-end representation learning. However, prevailing RDL evaluation practices rely on static, single-episode dataset snapshots, overlooking the continuous, time-evolving nature of real-world databases. Consequently, current RDL benchmarks fail to capture how model performance changes as new data accumulates over time. To address this limitation, we introduce an incremental, multi-episode evaluation and training paradigm to assess and improve the temporal robustness and adaptability of st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13023","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/2608.13023/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":"2026-08-14T01:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mLazGUnaw70TUjLmDzp8LfA5zxDbBZeBFKboeEPejMIt/5moWGIQ7Pq4lkl8qaqyWyfCdzMMBACm22zPJDAYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:16:23.798491Z"},"content_sha256":"956aafa16136ff939395f44d1f6a0a86807d93ece4a047e39678d6aefb213441","schema_version":"1.0","event_id":"sha256:956aafa16136ff939395f44d1f6a0a86807d93ece4a047e39678d6aefb213441"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ELNIZIFLMVOCUO4FEWXF7YEMLB/bundle.json","state_url":"https://pith.science/pith/ELNIZIFLMVOCUO4FEWXF7YEMLB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ELNIZIFLMVOCUO4FEWXF7YEMLB/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":"2026-08-16T07:16:23Z","links":{"resolver":"https://pith.science/pith/ELNIZIFLMVOCUO4FEWXF7YEMLB","bundle":"https://pith.science/pith/ELNIZIFLMVOCUO4FEWXF7YEMLB/bundle.json","state":"https://pith.science/pith/ELNIZIFLMVOCUO4FEWXF7YEMLB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ELNIZIFLMVOCUO4FEWXF7YEMLB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ELNIZIFLMVOCUO4FEWXF7YEMLB","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":"437d1e6fda74806c1c2a4c1f74e99bdbc21023fd2400d4094041ad39d7ac309c","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T09:46:29Z","title_canon_sha256":"3243b38f22c5b641a7c6f6c2bb8f2e8c3d72103fcb64af1c15e7268e7cae8f1f"},"schema_version":"1.0","source":{"id":"2608.13023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13023","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13023v1","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13023","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"ELNIZIFLMVOC","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"ELNIZIFLMVOCUO4F","created_at":"2026-08-14T01:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"ELNIZIFL","created_at":"2026-08-14T01:00:08Z"}],"graph_snapshots":[{"event_id":"sha256:956aafa16136ff939395f44d1f6a0a86807d93ece4a047e39678d6aefb213441","target":"graph","created_at":"2026-08-14T01:00:08Z","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/2608.13023/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 to enable end-to-end representation learning. However, prevailing RDL evaluation practices rely on static, single-episode dataset snapshots, overlooking the continuous, time-evolving nature of real-world databases. Consequently, current RDL benchmarks fail to capture how model performance changes as new data accumulates over time. To address this limitation, we introduce an incremental, multi-episode evaluation and training paradigm to assess and improve the temporal robustness and adaptability of st","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":"2026-08-13T09:46:29Z","title":"Incremental Evaluation and Training in Relational Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13023","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":"sha256:39baa4b766e013bc781079a663759923795d31f1d88b72f78070d206b802d55f","target":"record","created_at":"2026-08-14T01:00:08Z","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":"437d1e6fda74806c1c2a4c1f74e99bdbc21023fd2400d4094041ad39d7ac309c","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T09:46:29Z","title_canon_sha256":"3243b38f22c5b641a7c6f6c2bb8f2e8c3d72103fcb64af1c15e7268e7cae8f1f"},"schema_version":"1.0","source":{"id":"2608.13023","kind":"arxiv","version":1}},"canonical_sha256":"22da8ca0ab655c2a3b8525ae5fe08c585b68be7a5b3a82a4eb4d6bbf510b7bec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22da8ca0ab655c2a3b8525ae5fe08c585b68be7a5b3a82a4eb4d6bbf510b7bec","first_computed_at":"2026-08-14T01:00:08.905137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:08.905137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OjSdsFAsucZv29SypczD7bFk8liV8kW+bnc4N93Tebh5uuqZCM/ya8t16uZbeb/0KO0noXN77RY+12cAVoLZDQ==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:08.907224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39baa4b766e013bc781079a663759923795d31f1d88b72f78070d206b802d55f","sha256:956aafa16136ff939395f44d1f6a0a86807d93ece4a047e39678d6aefb213441"],"state_sha256":"8ad5980f4bb705f823145318be57eec58cad52070655030cbf034baec5c24927"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tIrSpflGV8zs0zpnIW5cgFl6z83QAmyvzOG/DHQ+Ft1PfKP7sxrrdexjh6zIxDmPs6ts6qK+y+rTnRndvkNqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:16:23.803304Z","bundle_sha256":"0180fb83bdc0c4b7b3d537688b55c5582d4336e67f0bc78125c1e10e81c898ca"}}