{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J2A4HK3XWAJOBU2FNVVM6FSCTD","short_pith_number":"pith:J2A4HK3X","schema_version":"1.0","canonical_sha256":"4e81c3ab77b012e0d3456d6acf164298fe73a66fa1bb385856665748c18e1102","source":{"kind":"arxiv","id":"2606.29934","version":1},"attestation_state":"computed","paper":{"title":"RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Beichen Wang, Junjie Gao, Mir Feroskhan, Siyuan Song, Yongzhou Pan, Yuqi Chen, Zixuan Zhang","submitted_at":"2026-06-29T08:10:43Z","abstract_excerpt":"Image-goal navigation is a key challenge in embodied robotics, where an agent must reach a target specified solely by a goal image. While existing reinforcement learning approaches map perceptual observations directly to actions, they struggle to model long-horizon dependencies, often leading to suboptimal trajectories. To address this limitation, we propose RoamFlow, a generative navigation framework that leverages MeanFlow to predict the average velocity field for trajectory synthesis, enabling efficient few-step generation and reducing inference latency. We further adopt a two-stage trainin"},"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":"2606.29934","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T08:10:43Z","cross_cats_sorted":[],"title_canon_sha256":"d4c80ad44ccdcffedaf612afd33da20df63d8ed5d3ba8b72e51a7ffb74e7f58e","abstract_canon_sha256":"f29ec9aca20ea081573031d2946705f80d38191fc1cdb4ff48e7e80080720449"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:41.597784Z","signature_b64":"mSLipKWdc9KDgZcHkk6IfTCovxwhVDyXP8OfDhkbF8i1DAer5+M1WhuRyQcU1CeHpggNeOzHFLyrQz1CrIfbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e81c3ab77b012e0d3456d6acf164298fe73a66fa1bb385856665748c18e1102","last_reissued_at":"2026-06-30T02:17:41.597299Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:41.597299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Beichen Wang, Junjie Gao, Mir Feroskhan, Siyuan Song, Yongzhou Pan, Yuqi Chen, Zixuan Zhang","submitted_at":"2026-06-29T08:10:43Z","abstract_excerpt":"Image-goal navigation is a key challenge in embodied robotics, where an agent must reach a target specified solely by a goal image. While existing reinforcement learning approaches map perceptual observations directly to actions, they struggle to model long-horizon dependencies, often leading to suboptimal trajectories. To address this limitation, we propose RoamFlow, a generative navigation framework that leverages MeanFlow to predict the average velocity field for trajectory synthesis, enabling efficient few-step generation and reducing inference latency. We further adopt a two-stage trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29934","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/2606.29934/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":"2606.29934","created_at":"2026-06-30T02:17:41.597375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29934v1","created_at":"2026-06-30T02:17:41.597375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29934","created_at":"2026-06-30T02:17:41.597375+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2A4HK3XWAJO","created_at":"2026-06-30T02:17:41.597375+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2A4HK3XWAJOBU2F","created_at":"2026-06-30T02:17:41.597375+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2A4HK3X","created_at":"2026-06-30T02:17:41.597375+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/J2A4HK3XWAJOBU2FNVVM6FSCTD","json":"https://pith.science/pith/J2A4HK3XWAJOBU2FNVVM6FSCTD.json","graph_json":"https://pith.science/api/pith-number/J2A4HK3XWAJOBU2FNVVM6FSCTD/graph.json","events_json":"https://pith.science/api/pith-number/J2A4HK3XWAJOBU2FNVVM6FSCTD/events.json","paper":"https://pith.science/paper/J2A4HK3X"},"agent_actions":{"view_html":"https://pith.science/pith/J2A4HK3XWAJOBU2FNVVM6FSCTD","download_json":"https://pith.science/pith/J2A4HK3XWAJOBU2FNVVM6FSCTD.json","view_paper":"https://pith.science/paper/J2A4HK3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29934&json=true","fetch_graph":"https://pith.science/api/pith-number/J2A4HK3XWAJOBU2FNVVM6FSCTD/graph.json","fetch_events":"https://pith.science/api/pith-number/J2A4HK3XWAJOBU2FNVVM6FSCTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2A4HK3XWAJOBU2FNVVM6FSCTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2A4HK3XWAJOBU2FNVVM6FSCTD/action/storage_attestation","attest_author":"https://pith.science/pith/J2A4HK3XWAJOBU2FNVVM6FSCTD/action/author_attestation","sign_citation":"https://pith.science/pith/J2A4HK3XWAJOBU2FNVVM6FSCTD/action/citation_signature","submit_replication":"https://pith.science/pith/J2A4HK3XWAJOBU2FNVVM6FSCTD/action/replication_record"}},"created_at":"2026-06-30T02:17:41.597375+00:00","updated_at":"2026-06-30T02:17:41.597375+00:00"}