{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4EO7JZQMPZADOQVKZZYDUV7DPM","short_pith_number":"pith:4EO7JZQM","schema_version":"1.0","canonical_sha256":"e11df4e60c7e403742aace703a57e37b15a8a00cd942349b3511d83afab4c250","source":{"kind":"arxiv","id":"2608.04060","version":1},"attestation_state":"computed","paper":{"title":"SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Yongchao Huang","submitted_at":"2026-08-04T13:08:07Z","abstract_excerpt":"Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural maps. We introduce SJEPA, a reconstruction-free JEPA framework that learns predictive representations whose induced dynamics admit compact symbolic descriptions. Its hybrid transition combines a symbolic law with a regularised neural correction for dynamics outside the selected grammar. The central principle is to learn the simplest adequate dynamics: representation constraints preserve informative, non-collapsed predict"},"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":"2608.04060","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T13:08:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"81d6b51407a7362cd8592403e7abdfd59143b6f7fbbcec81bf59257eca823c47","abstract_canon_sha256":"d98376e2cd6e35f6b5f78d42b524793d67b068e59f160c2153c19c8f87108549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:28:15.938296Z","signature_b64":"LZe2oAF3dRGBw2g4DckSYa5m/ATst6UorI8xQ/eFK1sqHKfo6q8f/VIRgjyBnT5e7RVaNiNN5DFkma7N4tCHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e11df4e60c7e403742aace703a57e37b15a8a00cd942349b3511d83afab4c250","last_reissued_at":"2026-08-06T01:28:15.936879Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:28:15.936879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Yongchao Huang","submitted_at":"2026-08-04T13:08:07Z","abstract_excerpt":"Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural maps. We introduce SJEPA, a reconstruction-free JEPA framework that learns predictive representations whose induced dynamics admit compact symbolic descriptions. Its hybrid transition combines a symbolic law with a regularised neural correction for dynamics outside the selected grammar. The central principle is to learn the simplest adequate dynamics: representation constraints preserve informative, non-collapsed predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04060","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/2608.04060/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":"2608.04060","created_at":"2026-08-06T01:28:15.938670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04060v1","created_at":"2026-08-06T01:28:15.938670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04060","created_at":"2026-08-06T01:28:15.938670+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EO7JZQMPZAD","created_at":"2026-08-06T01:28:15.938670+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EO7JZQMPZADOQVK","created_at":"2026-08-06T01:28:15.938670+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EO7JZQM","created_at":"2026-08-06T01:28:15.938670+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/4EO7JZQMPZADOQVKZZYDUV7DPM","json":"https://pith.science/pith/4EO7JZQMPZADOQVKZZYDUV7DPM.json","graph_json":"https://pith.science/api/pith-number/4EO7JZQMPZADOQVKZZYDUV7DPM/graph.json","events_json":"https://pith.science/api/pith-number/4EO7JZQMPZADOQVKZZYDUV7DPM/events.json","paper":"https://pith.science/paper/4EO7JZQM"},"agent_actions":{"view_html":"https://pith.science/pith/4EO7JZQMPZADOQVKZZYDUV7DPM","download_json":"https://pith.science/pith/4EO7JZQMPZADOQVKZZYDUV7DPM.json","view_paper":"https://pith.science/paper/4EO7JZQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04060&json=true","fetch_graph":"https://pith.science/api/pith-number/4EO7JZQMPZADOQVKZZYDUV7DPM/graph.json","fetch_events":"https://pith.science/api/pith-number/4EO7JZQMPZADOQVKZZYDUV7DPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EO7JZQMPZADOQVKZZYDUV7DPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EO7JZQMPZADOQVKZZYDUV7DPM/action/storage_attestation","attest_author":"https://pith.science/pith/4EO7JZQMPZADOQVKZZYDUV7DPM/action/author_attestation","sign_citation":"https://pith.science/pith/4EO7JZQMPZADOQVKZZYDUV7DPM/action/citation_signature","submit_replication":"https://pith.science/pith/4EO7JZQMPZADOQVKZZYDUV7DPM/action/replication_record"}},"created_at":"2026-08-06T01:28:15.938670+00:00","updated_at":"2026-08-06T01:28:15.938670+00:00"}