{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XBXLNLQB5ILPC7I57YLJZFMB6K","short_pith_number":"pith:XBXLNLQB","schema_version":"1.0","canonical_sha256":"b86eb6ae01ea16f17d1dfe169c9581f29cac098506289fb3fe6a0bd9224f46c6","source":{"kind":"arxiv","id":"2608.04381","version":1},"attestation_state":"computed","paper":{"title":"NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaheng Chen, Jian Xu, Jiaxing Li, Qiang Wang, Tinghe Zhang, Yucheng Xiao","submitted_at":"2026-08-05T02:39:28Z","abstract_excerpt":"Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attributes in the input space. Both paradigms can entangle representations with low-level input statistics rather than with relational structure. Joint-embedding predictive architectures (JEPA) instead learn by predicting latent targets rather than reconstructing inputs. Recent work has explored this idea for graph-level representation learning, but how to design JEPA-style objectives for node-level tasks, and which structu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.04381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T02:39:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33a5d2616da940b0f94b3b47fa4700744e0c1059041cae5428aaa8ac701a7060","abstract_canon_sha256":"4d03f6fab8a6cd0b9a3e2cd48222e74caa820e1d0b5c2773eb828b0a262b56a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:34:33.267182Z","signature_b64":"zAEndll/uvR0VoSeXC1gs8AO46W+GuCSgeuMXc5SaslWyISY3MskbHB7ajz045TA4TRv5F3cvIyX3fwOh3CZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b86eb6ae01ea16f17d1dfe169c9581f29cac098506289fb3fe6a0bd9224f46c6","last_reissued_at":"2026-08-06T01:34:33.265772Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:34:33.265772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaheng Chen, Jian Xu, Jiaxing Li, Qiang Wang, Tinghe Zhang, Yucheng Xiao","submitted_at":"2026-08-05T02:39:28Z","abstract_excerpt":"Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attributes in the input space. Both paradigms can entangle representations with low-level input statistics rather than with relational structure. Joint-embedding predictive architectures (JEPA) instead learn by predicting latent targets rather than reconstructing inputs. Recent work has explored this idea for graph-level representation learning, but how to design JEPA-style objectives for node-level tasks, and which structu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04381","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/2608.04381/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.04381","created_at":"2026-08-06T01:34:33.267568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04381v1","created_at":"2026-08-06T01:34:33.267568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04381","created_at":"2026-08-06T01:34:33.267568+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBXLNLQB5ILP","created_at":"2026-08-06T01:34:33.267568+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBXLNLQB5ILPC7I5","created_at":"2026-08-06T01:34:33.267568+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBXLNLQB","created_at":"2026-08-06T01:34:33.267568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K","json":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K.json","graph_json":"https://pith.science/api/pith-number/XBXLNLQB5ILPC7I57YLJZFMB6K/graph.json","events_json":"https://pith.science/api/pith-number/XBXLNLQB5ILPC7I57YLJZFMB6K/events.json","paper":"https://pith.science/paper/XBXLNLQB"},"agent_actions":{"view_html":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K","download_json":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K.json","view_paper":"https://pith.science/paper/XBXLNLQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04381&json=true","fetch_graph":"https://pith.science/api/pith-number/XBXLNLQB5ILPC7I57YLJZFMB6K/graph.json","fetch_events":"https://pith.science/api/pith-number/XBXLNLQB5ILPC7I57YLJZFMB6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K/action/storage_attestation","attest_author":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K/action/author_attestation","sign_citation":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K/action/citation_signature","submit_replication":"https://pith.science/pith/XBXLNLQB5ILPC7I57YLJZFMB6K/action/replication_record"}},"created_at":"2026-08-06T01:34:33.267568+00:00","updated_at":"2026-08-06T01:34:33.267568+00:00"}