{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TPJNMPH2SFXRFII2G7D5DADPSF","short_pith_number":"pith:TPJNMPH2","schema_version":"1.0","canonical_sha256":"9bd2d63cfa916f12a11a37c7d1806f9164a88c94749e53c49d2d49d719456005","source":{"kind":"arxiv","id":"2309.16014","version":3},"attestation_state":"computed","paper":{"title":"Graph-level Representation Learning with Joint-Embedding Predictive Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Geri Skenderi, Hang Li, Jiliang Tang, Marco Cristani","submitted_at":"2023-09-27T20:42:02Z","abstract_excerpt":"Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-based model by predicting the latent representation of a target signal y from the latent representation of a context signal x. JEPAs bypass the need for negative and positive samples, traditionally required by contrastive learning while avoiding the overfitting issues associated with generative pretraining. In this paper, we show that graph-level representations can be effectively modeled using this paradigm by proposi"},"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":"2309.16014","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T20:42:02Z","cross_cats_sorted":[],"title_canon_sha256":"6b3ba9895942fbbd25bcc982861d562ccfb12eb0ae17baf01db2c4dde40a7b08","abstract_canon_sha256":"0390eafc01c920c828a335ae1dcf4c3f3b3679ec650c2be7fe829d90329f3b95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:21.491069Z","signature_b64":"HIfTsyxgGj6GYlnD4gRiwj2Kg/Ond4C40N8P9BX15SaiHV+yqV8GQnG3PVzFJmct8SPosfpobkej6YP6VWo+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bd2d63cfa916f12a11a37c7d1806f9164a88c94749e53c49d2d49d719456005","last_reissued_at":"2026-07-05T10:02:21.490608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:21.490608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-level Representation Learning with Joint-Embedding Predictive Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Geri Skenderi, Hang Li, Jiliang Tang, Marco Cristani","submitted_at":"2023-09-27T20:42:02Z","abstract_excerpt":"Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-based model by predicting the latent representation of a target signal y from the latent representation of a context signal x. JEPAs bypass the need for negative and positive samples, traditionally required by contrastive learning while avoiding the overfitting issues associated with generative pretraining. In this paper, we show that graph-level representations can be effectively modeled using this paradigm by proposi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16014","kind":"arxiv","version":3},"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/2309.16014/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":"2309.16014","created_at":"2026-07-05T10:02:21.490666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16014v3","created_at":"2026-07-05T10:02:21.490666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16014","created_at":"2026-07-05T10:02:21.490666+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPJNMPH2SFXR","created_at":"2026-07-05T10:02:21.490666+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPJNMPH2SFXRFII2","created_at":"2026-07-05T10:02:21.490666+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPJNMPH2","created_at":"2026-07-05T10:02:21.490666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08869","citing_title":"A Low-Latency Semantic State Estimator using Latent Predictive Learning for Dynamic Network Monitoring and Orchestration","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05586","citing_title":"AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF","json":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF.json","graph_json":"https://pith.science/api/pith-number/TPJNMPH2SFXRFII2G7D5DADPSF/graph.json","events_json":"https://pith.science/api/pith-number/TPJNMPH2SFXRFII2G7D5DADPSF/events.json","paper":"https://pith.science/paper/TPJNMPH2"},"agent_actions":{"view_html":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF","download_json":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF.json","view_paper":"https://pith.science/paper/TPJNMPH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16014&json=true","fetch_graph":"https://pith.science/api/pith-number/TPJNMPH2SFXRFII2G7D5DADPSF/graph.json","fetch_events":"https://pith.science/api/pith-number/TPJNMPH2SFXRFII2G7D5DADPSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF/action/storage_attestation","attest_author":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF/action/author_attestation","sign_citation":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF/action/citation_signature","submit_replication":"https://pith.science/pith/TPJNMPH2SFXRFII2G7D5DADPSF/action/replication_record"}},"created_at":"2026-07-05T10:02:21.490666+00:00","updated_at":"2026-07-05T10:02:21.490666+00:00"}