{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J3JPPAUKETCW3EI2AMCSF3CIHN","short_pith_number":"pith:J3JPPAUK","schema_version":"1.0","canonical_sha256":"4ed2f7828a24c56d911a030522ec483b4ed5bb57bd0d7e3d3c835e9fc070ff70","source":{"kind":"arxiv","id":"2606.11860","version":1},"attestation_state":"computed","paper":{"title":"RePAIR: Predictive Self-Supervised Representation Learning in Chess","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christoph Koller, Johannes F\\\"urnkranz, Timo Bertram","submitted_at":"2026-06-10T09:36:31Z","abstract_excerpt":"In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT). We demonstrate how it can be used to encode objects in sequential data like consecutive chess positions into compact yet meaningful representations. The basic principle of the architecture is to mask large portions of a sequence of latent states, similar to BERT and MA"},"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":"2606.11860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T09:36:31Z","cross_cats_sorted":[],"title_canon_sha256":"b8e0adbbc2da98fdaa72faf75b0be87039eaad52eec3b0215e30f5ab3dec8588","abstract_canon_sha256":"9bb77b024d9048687ee7b17344688bd5de79e451c32fc0b9aa0d9e620c65bd79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:12.190619Z","signature_b64":"ye8fYjlcnbZvRrAbLPt395BjTWkVlfJAUdBYJnwjfKRUOlVdtAmfx4Lyi1FdYI7zTHLXUUeXWTJBg81q/aapAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ed2f7828a24c56d911a030522ec483b4ed5bb57bd0d7e3d3c835e9fc070ff70","last_reissued_at":"2026-06-11T01:10:12.189694Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:12.189694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RePAIR: Predictive Self-Supervised Representation Learning in Chess","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christoph Koller, Johannes F\\\"urnkranz, Timo Bertram","submitted_at":"2026-06-10T09:36:31Z","abstract_excerpt":"In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT). We demonstrate how it can be used to encode objects in sequential data like consecutive chess positions into compact yet meaningful representations. The basic principle of the architecture is to mask large portions of a sequence of latent states, similar to BERT and MA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11860","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/2606.11860/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":"2606.11860","created_at":"2026-06-11T01:10:12.189818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11860v1","created_at":"2026-06-11T01:10:12.189818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11860","created_at":"2026-06-11T01:10:12.189818+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3JPPAUKETCW","created_at":"2026-06-11T01:10:12.189818+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3JPPAUKETCW3EI2","created_at":"2026-06-11T01:10:12.189818+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3JPPAUK","created_at":"2026-06-11T01:10:12.189818+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/J3JPPAUKETCW3EI2AMCSF3CIHN","json":"https://pith.science/pith/J3JPPAUKETCW3EI2AMCSF3CIHN.json","graph_json":"https://pith.science/api/pith-number/J3JPPAUKETCW3EI2AMCSF3CIHN/graph.json","events_json":"https://pith.science/api/pith-number/J3JPPAUKETCW3EI2AMCSF3CIHN/events.json","paper":"https://pith.science/paper/J3JPPAUK"},"agent_actions":{"view_html":"https://pith.science/pith/J3JPPAUKETCW3EI2AMCSF3CIHN","download_json":"https://pith.science/pith/J3JPPAUKETCW3EI2AMCSF3CIHN.json","view_paper":"https://pith.science/paper/J3JPPAUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11860&json=true","fetch_graph":"https://pith.science/api/pith-number/J3JPPAUKETCW3EI2AMCSF3CIHN/graph.json","fetch_events":"https://pith.science/api/pith-number/J3JPPAUKETCW3EI2AMCSF3CIHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3JPPAUKETCW3EI2AMCSF3CIHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3JPPAUKETCW3EI2AMCSF3CIHN/action/storage_attestation","attest_author":"https://pith.science/pith/J3JPPAUKETCW3EI2AMCSF3CIHN/action/author_attestation","sign_citation":"https://pith.science/pith/J3JPPAUKETCW3EI2AMCSF3CIHN/action/citation_signature","submit_replication":"https://pith.science/pith/J3JPPAUKETCW3EI2AMCSF3CIHN/action/replication_record"}},"created_at":"2026-06-11T01:10:12.189818+00:00","updated_at":"2026-06-11T01:10:12.189818+00:00"}