{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TRQCDQPQ334YCQN2POITDNRNVT","short_pith_number":"pith:TRQCDQPQ","schema_version":"1.0","canonical_sha256":"9c6021c1f0def98141ba7b9131b62dacd7618e3e3095ca0b39433e05933cab5c","source":{"kind":"arxiv","id":"2010.13146","version":2},"attestation_state":"computed","paper":{"title":"XLVIN: eXecuted Latent Value Iteration Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreea Deac, Jian Tang, Mladen Nikoli\\'c, Ognjen Milinkovi\\'c, Petar Veli\\v{c}kovi\\'c, Pierre-Luc Bacon","submitted_at":"2020-10-25T16:04:30Z","abstract_excerpt":"Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics. This came with several limitations, however: the model is not incentivised in any way to perform meaningful planning computations, the underlying state space is assumed to be discrete, and the Markov decision process (MDP) is assumed fixed and known. We propose eXecuted Latent Value Iteration Networks (XLVINs), which combine recent developments "},"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":"2010.13146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-25T16:04:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8d073d498bc7025f479be22c39ff835dfaecce82816251ce748b295b295bfe1b","abstract_canon_sha256":"eb3b16508002df28cd6fdfc36dbae7b32707ed039c380950f9b13cdb41e3a7d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:21.057386Z","signature_b64":"U8CwGn/+efMxhM1VF5OKMSASGZUz7Wgbg866BzT14fSHBDliOJ2JZMJy6dRD3ox1BP/bctt9M4X2h2og4+/7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c6021c1f0def98141ba7b9131b62dacd7618e3e3095ca0b39433e05933cab5c","last_reissued_at":"2026-07-05T01:57:21.056901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:21.056901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XLVIN: eXecuted Latent Value Iteration Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreea Deac, Jian Tang, Mladen Nikoli\\'c, Ognjen Milinkovi\\'c, Petar Veli\\v{c}kovi\\'c, Pierre-Luc Bacon","submitted_at":"2020-10-25T16:04:30Z","abstract_excerpt":"Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics. This came with several limitations, however: the model is not incentivised in any way to perform meaningful planning computations, the underlying state space is assumed to be discrete, and the Markov decision process (MDP) is assumed fixed and known. We propose eXecuted Latent Value Iteration Networks (XLVINs), which combine recent developments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13146","kind":"arxiv","version":2},"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/2010.13146/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":"2010.13146","created_at":"2026-07-05T01:57:21.056958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.13146v2","created_at":"2026-07-05T01:57:21.056958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13146","created_at":"2026-07-05T01:57:21.056958+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRQCDQPQ334Y","created_at":"2026-07-05T01:57:21.056958+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRQCDQPQ334YCQN2","created_at":"2026-07-05T01:57:21.056958+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRQCDQPQ","created_at":"2026-07-05T01:57:21.056958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23395","citing_title":"Convex Compositional Reasoning Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23395","citing_title":"Convex Compositional Reasoning Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT","json":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT.json","graph_json":"https://pith.science/api/pith-number/TRQCDQPQ334YCQN2POITDNRNVT/graph.json","events_json":"https://pith.science/api/pith-number/TRQCDQPQ334YCQN2POITDNRNVT/events.json","paper":"https://pith.science/paper/TRQCDQPQ"},"agent_actions":{"view_html":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT","download_json":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT.json","view_paper":"https://pith.science/paper/TRQCDQPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.13146&json=true","fetch_graph":"https://pith.science/api/pith-number/TRQCDQPQ334YCQN2POITDNRNVT/graph.json","fetch_events":"https://pith.science/api/pith-number/TRQCDQPQ334YCQN2POITDNRNVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT/action/storage_attestation","attest_author":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT/action/author_attestation","sign_citation":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT/action/citation_signature","submit_replication":"https://pith.science/pith/TRQCDQPQ334YCQN2POITDNRNVT/action/replication_record"}},"created_at":"2026-07-05T01:57:21.056958+00:00","updated_at":"2026-07-05T01:57:21.056958+00:00"}