{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OAHEUKHQA2K5IW4W7E23PPJC2V","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9c47742792ddfa1767b51e5a79434637544a4dbda4e1e763bc3c0d4e05a7aaff","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-28T17:51:10Z","title_canon_sha256":"e42a0ac82f9c520033f090211eef174cefb12f4e781f28196fe86301836f9cd1"},"schema_version":"1.0","source":{"id":"2406.20083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20083","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20083v1","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20083","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"pith_short_12","alias_value":"OAHEUKHQA2K5","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"pith_short_16","alias_value":"OAHEUKHQA2K5IW4W","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"pith_short_8","alias_value":"OAHEUKHQ","created_at":"2026-07-05T08:37:58Z"}],"graph_snapshots":[{"event_id":"sha256:40d8a3a34001f8179865b2d58a19fba0a6820899b12ded6ebd7cd677882552cf","target":"graph","created_at":"2026-07-05T08:37:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.20083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present PoliFormer (Policy Transformer), an RGB-only indoor navigation agent trained end-to-end with reinforcement learning at scale that generalizes to the real-world without adaptation despite being trained purely in simulation. PoliFormer uses a foundational vision transformer encoder with a causal transformer decoder enabling long-term memory and reasoning. It is trained for hundreds of millions of interactions across diverse environments, leveraging parallelized, multi-machine rollouts for efficient training with high throughput. PoliFormer is a masterful navigator, producing state-of-","authors_text":"Alvaro Herrasti, Aniruddha Kembhavi, Jordi Salvador, Kiana Ehsani, Kuo-Hao Zeng, Luca Weihs, Rose Hendrix, Ross Girshick, Zichen Zhang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-28T17:51:10Z","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20083","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:69699c0c410c3e631221a7756989e93ce0945d0a9c58cd48f6186644412d501a","target":"record","created_at":"2026-07-05T08:37:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9c47742792ddfa1767b51e5a79434637544a4dbda4e1e763bc3c0d4e05a7aaff","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-28T17:51:10Z","title_canon_sha256":"e42a0ac82f9c520033f090211eef174cefb12f4e781f28196fe86301836f9cd1"},"schema_version":"1.0","source":{"id":"2406.20083","kind":"arxiv","version":1}},"canonical_sha256":"700e4a28f00695d45b96f935b7bd22d560ee0168a8dab2c782eee1ab9b27358b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"700e4a28f00695d45b96f935b7bd22d560ee0168a8dab2c782eee1ab9b27358b","first_computed_at":"2026-07-05T08:37:58.936863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:58.936863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xxa5wXsOrTMjPKlN3tD6Vu2HrdEPTjvHclepf6x43PGnDCtpZheW2GB6TZ9iv3mVjkibZm/bGs1edbQR3aPNDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:58.937295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.20083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69699c0c410c3e631221a7756989e93ce0945d0a9c58cd48f6186644412d501a","sha256:40d8a3a34001f8179865b2d58a19fba0a6820899b12ded6ebd7cd677882552cf"],"state_sha256":"1af91322f7e1f06573c25ad7b02f513839c3478296191bfac569aee091d5a034"}