{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OAHEUKHQA2K5IW4W7E23PPJC2V","short_pith_number":"pith:OAHEUKHQ","schema_version":"1.0","canonical_sha256":"700e4a28f00695d45b96f935b7bd22d560ee0168a8dab2c782eee1ab9b27358b","source":{"kind":"arxiv","id":"2406.20083","version":1},"attestation_state":"computed","paper":{"title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Alvaro Herrasti, Aniruddha Kembhavi, Jordi Salvador, Kiana Ehsani, Kuo-Hao Zeng, Luca Weihs, Rose Hendrix, Ross Girshick, Zichen Zhang","submitted_at":"2024-06-28T17:51:10Z","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-"},"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":"2406.20083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-28T17:51:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e42a0ac82f9c520033f090211eef174cefb12f4e781f28196fe86301836f9cd1","abstract_canon_sha256":"9c47742792ddfa1767b51e5a79434637544a4dbda4e1e763bc3c0d4e05a7aaff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:58.937295Z","signature_b64":"Xxa5wXsOrTMjPKlN3tD6Vu2HrdEPTjvHclepf6x43PGnDCtpZheW2GB6TZ9iv3mVjkibZm/bGs1edbQR3aPNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"700e4a28f00695d45b96f935b7bd22d560ee0168a8dab2c782eee1ab9b27358b","last_reissued_at":"2026-07-05T08:37:58.936863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:58.936863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Alvaro Herrasti, Aniruddha Kembhavi, Jordi Salvador, Kiana Ehsani, Kuo-Hao Zeng, Luca Weihs, Rose Hendrix, Ross Girshick, Zichen Zhang","submitted_at":"2024-06-28T17:51:10Z","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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20083","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/2406.20083/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":"2406.20083","created_at":"2026-07-05T08:37:58.936930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.20083v1","created_at":"2026-07-05T08:37:58.936930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20083","created_at":"2026-07-05T08:37:58.936930+00:00"},{"alias_kind":"pith_short_12","alias_value":"OAHEUKHQA2K5","created_at":"2026-07-05T08:37:58.936930+00:00"},{"alias_kind":"pith_short_16","alias_value":"OAHEUKHQA2K5IW4W","created_at":"2026-07-05T08:37:58.936930+00:00"},{"alias_kind":"pith_short_8","alias_value":"OAHEUKHQ","created_at":"2026-07-05T08:37:58.936930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25119","citing_title":"SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18112","citing_title":"Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10927","citing_title":"AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18112","citing_title":"Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01247","citing_title":"Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2503.03480","citing_title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06224","citing_title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18719","citing_title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11762","citing_title":"NavOL: Navigation Policy with Online Imitation Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10118","citing_title":"Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09441","citing_title":"Beyond Isolation: A Unified Benchmark for General-Purpose Navigation","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V","json":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V.json","graph_json":"https://pith.science/api/pith-number/OAHEUKHQA2K5IW4W7E23PPJC2V/graph.json","events_json":"https://pith.science/api/pith-number/OAHEUKHQA2K5IW4W7E23PPJC2V/events.json","paper":"https://pith.science/paper/OAHEUKHQ"},"agent_actions":{"view_html":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V","download_json":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V.json","view_paper":"https://pith.science/paper/OAHEUKHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.20083&json=true","fetch_graph":"https://pith.science/api/pith-number/OAHEUKHQA2K5IW4W7E23PPJC2V/graph.json","fetch_events":"https://pith.science/api/pith-number/OAHEUKHQA2K5IW4W7E23PPJC2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V/action/storage_attestation","attest_author":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V/action/author_attestation","sign_citation":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V/action/citation_signature","submit_replication":"https://pith.science/pith/OAHEUKHQA2K5IW4W7E23PPJC2V/action/replication_record"}},"created_at":"2026-07-05T08:37:58.936930+00:00","updated_at":"2026-07-05T08:37:58.936930+00:00"}