{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G3ZMKT3AFZSXTL7YSGK6ZT7PKW","short_pith_number":"pith:G3ZMKT3A","schema_version":"1.0","canonical_sha256":"36f2c54f602e6579aff89195eccfef55a2c0070d85f4396874f8435e0c4d85ed","source":{"kind":"arxiv","id":"2406.08404","version":2},"attestation_state":"computed","paper":{"title":"Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Huang, Dylan R. Ashley, Francesco Faccio, J\\\"urgen Schmidhuber, Qingyuan Wu, Weida Li, Yuhui Wang","submitted_at":"2024-06-12T16:52:54Z","abstract_excerpt":"The Value Iteration Network (VIN) is an end-to-end differentiable neural network architecture for planning. It exhibits strong generalization to unseen domains by incorporating a differentiable planning module that operates on a latent Markov Decision Process (MDP). However, VINs struggle to scale to long-term and large-scale planning tasks, such as navigating a 100x100 maze -- a task that typically requires thousands of planning steps to solve. We observe that this deficiency is due to two issues: the representation capacity of the latent MDP and the planning module's depth. We address these "},"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":"2406.08404","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:52:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38184ddbce03a7bbc081de5419a13fdf1d32dad6d19e85b614b0d20e038bd191","abstract_canon_sha256":"f37efb9bdb8cc92a7880c23b0dce75afa4e5e162379884683c02ff2ba7e25ca8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:15.664684Z","signature_b64":"pjQfkKlCp7UdUZkvoPct17A4b9fiBeItefZbYVUrZUrG9SOTDsdkwCOIkMxYwe1Fanrg2hDcjAO4Mi7lsmB3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36f2c54f602e6579aff89195eccfef55a2c0070d85f4396874f8435e0c4d85ed","last_reissued_at":"2026-07-05T11:32:15.664148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:15.664148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Huang, Dylan R. Ashley, Francesco Faccio, J\\\"urgen Schmidhuber, Qingyuan Wu, Weida Li, Yuhui Wang","submitted_at":"2024-06-12T16:52:54Z","abstract_excerpt":"The Value Iteration Network (VIN) is an end-to-end differentiable neural network architecture for planning. It exhibits strong generalization to unseen domains by incorporating a differentiable planning module that operates on a latent Markov Decision Process (MDP). However, VINs struggle to scale to long-term and large-scale planning tasks, such as navigating a 100x100 maze -- a task that typically requires thousands of planning steps to solve. We observe that this deficiency is due to two issues: the representation capacity of the latent MDP and the planning module's depth. We address these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08404","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/2406.08404/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":"2406.08404","created_at":"2026-07-05T11:32:15.664209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08404v2","created_at":"2026-07-05T11:32:15.664209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08404","created_at":"2026-07-05T11:32:15.664209+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3ZMKT3AFZSX","created_at":"2026-07-05T11:32:15.664209+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3ZMKT3AFZSXTL7Y","created_at":"2026-07-05T11:32:15.664209+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3ZMKT3A","created_at":"2026-07-05T11:32:15.664209+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/G3ZMKT3AFZSXTL7YSGK6ZT7PKW","json":"https://pith.science/pith/G3ZMKT3AFZSXTL7YSGK6ZT7PKW.json","graph_json":"https://pith.science/api/pith-number/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/graph.json","events_json":"https://pith.science/api/pith-number/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/events.json","paper":"https://pith.science/paper/G3ZMKT3A"},"agent_actions":{"view_html":"https://pith.science/pith/G3ZMKT3AFZSXTL7YSGK6ZT7PKW","download_json":"https://pith.science/pith/G3ZMKT3AFZSXTL7YSGK6ZT7PKW.json","view_paper":"https://pith.science/paper/G3ZMKT3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08404&json=true","fetch_graph":"https://pith.science/api/pith-number/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/graph.json","fetch_events":"https://pith.science/api/pith-number/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/action/storage_attestation","attest_author":"https://pith.science/pith/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/action/author_attestation","sign_citation":"https://pith.science/pith/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/action/citation_signature","submit_replication":"https://pith.science/pith/G3ZMKT3AFZSXTL7YSGK6ZT7PKW/action/replication_record"}},"created_at":"2026-07-05T11:32:15.664209+00:00","updated_at":"2026-07-05T11:32:15.664209+00:00"}