{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QV7OGNW62D64LPTQU5Y63YJ4Z7","short_pith_number":"pith:QV7OGNW6","canonical_record":{"source":{"id":"2509.06951","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:58:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e04e81df5783ed00b29047b3032c726b425d07d17604093f44c061e07afd9647","abstract_canon_sha256":"41f35daf8a35df3024efb59840a8f315be844de7c18c88f13397fd07cd437698"},"schema_version":"1.0"},"canonical_sha256":"857ee336ded0fdc5be70a771ede13ccff267282347663f2723706a7f3734a0e3","source":{"kind":"arxiv","id":"2509.06951","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06951","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06951v2","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06951","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"QV7OGNW62D64","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QV7OGNW62D64LPTQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QV7OGNW6","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QV7OGNW62D64LPTQU5Y63YJ4Z7","target":"record","payload":{"canonical_record":{"source":{"id":"2509.06951","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:58:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e04e81df5783ed00b29047b3032c726b425d07d17604093f44c061e07afd9647","abstract_canon_sha256":"41f35daf8a35df3024efb59840a8f315be844de7c18c88f13397fd07cd437698"},"schema_version":"1.0"},"canonical_sha256":"857ee336ded0fdc5be70a771ede13ccff267282347663f2723706a7f3734a0e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.846488Z","signature_b64":"DJ7Lpjsl4SpW9dRPzdYstjlzs8sEIbZJKjgj7NbpEkpUvYYxFzPTglJ9qUOkJGIQhFJL6OW1oXFt8yF9VorTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"857ee336ded0fdc5be70a771ede13ccff267282347663f2723706a7f3734a0e3","last_reissued_at":"2026-05-17T23:38:47.845674Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.845674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.06951","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+GXncfFKhwudKT5TJh8eZe4viJPeiL12rfrsi5pK1CFczWX0t/kDqcFZ7Bd686mpfX1DL3KV0TAGREwkkpMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:45:58.716867Z"},"content_sha256":"7aa2a830d2571c9f40cf9e210545f95e541c0b08edf175fc7abcdb016b131af9","schema_version":"1.0","event_id":"sha256:7aa2a830d2571c9f40cf9e210545f95e541c0b08edf175fc7abcdb016b131af9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QV7OGNW62D64LPTQU5Y63YJ4Z7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"F1 integrates visual foresight generation into vision-language-action models to create explicit planning targets for actions.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Delin Qu, Hao Li, Haoming Song, Jiangmiao Pang, Jia Zeng, Qi Lv, Qizhi Chen, Weijie Kong, Xiang Deng, Zherui Qiu","submitted_at":"2025-09-08T17:58:30Z","abstract_excerpt":"Executing language-conditioned tasks in dynamic visual environments remains a central challenge in embodied AI. Existing Vision-Language-Action (VLA) models predominantly adopt reactive state-to-action mappings, often leading to short-sighted behaviors and poor robustness in dynamic scenes. In this paper, we introduce F1, a pretrained VLA framework which integrates the visual foresight generation into decision-making pipeline. F1 adopts a Mixture-of-Transformer architecture with dedicated modules for perception, foresight generation, and control, thereby bridging understanding, generation, and"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"F1 employs a next-scale prediction mechanism to synthesize goal-conditioned visual foresight as explicit planning targets. By forecasting plausible future visual states, F1 reformulates action generation as a foresight-guided inverse dynamics problem, enabling actions that implicitly achieve visual goals.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the generated visual foresight accurately represents plausible future states that can reliably serve as planning targets for action generation in dynamic, real-world scenes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"F1 integrates next-scale visual foresight prediction into a Mixture-of-Transformer VLA architecture to reformulate action generation as foresight-guided inverse dynamics, achieving higher success rates on 136 tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"F1 integrates visual foresight generation into vision-language-action models to create explicit planning targets for actions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c94ccaec4b5a38f36675392258ddaeae8f33015ae3d56ddf9f0b4faf7a0bbe87"},"source":{"id":"2509.06951","kind":"arxiv","version":2},"verdict":{"id":"671be10c-2e2b-4e00-954b-a8899e7ff485","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T12:37:25.610411Z","strongest_claim":"F1 employs a next-scale prediction mechanism to synthesize goal-conditioned visual foresight as explicit planning targets. By forecasting plausible future visual states, F1 reformulates action generation as a foresight-guided inverse dynamics problem, enabling actions that implicitly achieve visual goals.","one_line_summary":"F1 integrates next-scale visual foresight prediction into a Mixture-of-Transformer VLA architecture to reformulate action generation as foresight-guided inverse dynamics, achieving higher success rates on 136 tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the generated visual foresight accurately represents plausible future states that can reliably serve as planning targets for action generation in dynamic, real-world scenes.","pith_extraction_headline":"F1 integrates visual foresight generation into vision-language-action models to create explicit planning targets for actions."},"references":{"count":34,"sample":[{"doi":"","year":null,"title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","work_id":"f797e9ec-510f-43a7-8a0c-18009ce332e5","ref_index":1,"cited_arxiv_id":"2503.06669","is_internal_anchor":true},{"doi":"","year":null,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":2,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":null,"title":"PaliGemma: A versatile 3B VLM for transfer","work_id":"df6f48b3-5792-47c7-9614-cb856ea31ad9","ref_index":3,"cited_arxiv_id":"2407.07726","is_internal_anchor":true},{"doi":"","year":null,"title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","work_id":"954b4359-f4ed-4c73-ae5b-f75d486b6fc8","ref_index":4,"cited_arxiv_id":"2310.10639","is_internal_anchor":true},{"doi":"","year":null,"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","ref_index":5,"cited_arxiv_id":"2212.06817","is_internal_anchor":true}],"resolved_work":34,"snapshot_sha256":"4e8d6306cd3101631a9dffa11c3791a4c0adfabbf7613792db7f102b962bbdb7","internal_anchors":26},"formal_canon":{"evidence_count":1,"snapshot_sha256":"8ae9aff743e82a61f9424dadb4f8d37e663780a8facb2a66b024b956306b0510"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"671be10c-2e2b-4e00-954b-a8899e7ff485"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/1KWToQw04lNFHM89lMbi3NScoq7yTTSCCYwGuzo1bwEPUDoAjPUobHobKvHV2Ip0xHZIqA9mbMo5dokswesAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:45:58.717419Z"},"content_sha256":"52233ee733b8ea01997dcf1b5926da157becd3e2af6dc13e2874bab906297f22","schema_version":"1.0","event_id":"sha256:52233ee733b8ea01997dcf1b5926da157becd3e2af6dc13e2874bab906297f22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QV7OGNW62D64LPTQU5Y63YJ4Z7/bundle.json","state_url":"https://pith.science/pith/QV7OGNW62D64LPTQU5Y63YJ4Z7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QV7OGNW62D64LPTQU5Y63YJ4Z7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T03:45:58Z","links":{"resolver":"https://pith.science/pith/QV7OGNW62D64LPTQU5Y63YJ4Z7","bundle":"https://pith.science/pith/QV7OGNW62D64LPTQU5Y63YJ4Z7/bundle.json","state":"https://pith.science/pith/QV7OGNW62D64LPTQU5Y63YJ4Z7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QV7OGNW62D64LPTQU5Y63YJ4Z7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QV7OGNW62D64LPTQU5Y63YJ4Z7","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":"41f35daf8a35df3024efb59840a8f315be844de7c18c88f13397fd07cd437698","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:58:30Z","title_canon_sha256":"e04e81df5783ed00b29047b3032c726b425d07d17604093f44c061e07afd9647"},"schema_version":"1.0","source":{"id":"2509.06951","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06951","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06951v2","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06951","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"QV7OGNW62D64","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QV7OGNW62D64LPTQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QV7OGNW6","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:52233ee733b8ea01997dcf1b5926da157becd3e2af6dc13e2874bab906297f22","target":"graph","created_at":"2026-05-17T23:38:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"F1 employs a next-scale prediction mechanism to synthesize goal-conditioned visual foresight as explicit planning targets. By forecasting plausible future visual states, F1 reformulates action generation as a foresight-guided inverse dynamics problem, enabling actions that implicitly achieve visual goals."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the generated visual foresight accurately represents plausible future states that can reliably serve as planning targets for action generation in dynamic, real-world scenes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"F1 integrates next-scale visual foresight prediction into a Mixture-of-Transformer VLA architecture to reformulate action generation as foresight-guided inverse dynamics, achieving higher success rates on 136 tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"F1 integrates visual foresight generation into vision-language-action models to create explicit planning targets for actions."}],"snapshot_sha256":"c94ccaec4b5a38f36675392258ddaeae8f33015ae3d56ddf9f0b4faf7a0bbe87"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"8ae9aff743e82a61f9424dadb4f8d37e663780a8facb2a66b024b956306b0510"},"paper":{"abstract_excerpt":"Executing language-conditioned tasks in dynamic visual environments remains a central challenge in embodied AI. Existing Vision-Language-Action (VLA) models predominantly adopt reactive state-to-action mappings, often leading to short-sighted behaviors and poor robustness in dynamic scenes. In this paper, we introduce F1, a pretrained VLA framework which integrates the visual foresight generation into decision-making pipeline. F1 adopts a Mixture-of-Transformer architecture with dedicated modules for perception, foresight generation, and control, thereby bridging understanding, generation, and","authors_text":"Delin Qu, Hao Li, Haoming Song, Jiangmiao Pang, Jia Zeng, Qi Lv, Qizhi Chen, Weijie Kong, Xiang Deng, Zherui Qiu","cross_cats":["cs.CV"],"headline":"F1 integrates visual foresight generation into vision-language-action models to create explicit planning targets for actions.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:58:30Z","title":"F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions"},"references":{"count":34,"internal_anchors":26,"resolved_work":34,"sample":[{"cited_arxiv_id":"2503.06669","doi":"","is_internal_anchor":true,"ref_index":1,"title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","work_id":"f797e9ec-510f-43a7-8a0c-18009ce332e5","year":null},{"cited_arxiv_id":"2502.13923","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":null},{"cited_arxiv_id":"2407.07726","doi":"","is_internal_anchor":true,"ref_index":3,"title":"PaliGemma: A versatile 3B VLM for transfer","work_id":"df6f48b3-5792-47c7-9614-cb856ea31ad9","year":null},{"cited_arxiv_id":"2310.10639","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","work_id":"954b4359-f4ed-4c73-ae5b-f75d486b6fc8","year":null},{"cited_arxiv_id":"2212.06817","doi":"","is_internal_anchor":true,"ref_index":5,"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","year":null}],"snapshot_sha256":"4e8d6306cd3101631a9dffa11c3791a4c0adfabbf7613792db7f102b962bbdb7"},"source":{"id":"2509.06951","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T12:37:25.610411Z","id":"671be10c-2e2b-4e00-954b-a8899e7ff485","model_set":{"reader":"grok-4.3"},"one_line_summary":"F1 integrates next-scale visual foresight prediction into a Mixture-of-Transformer VLA architecture to reformulate action generation as foresight-guided inverse dynamics, achieving higher success rates on 136 tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"F1 integrates visual foresight generation into vision-language-action models to create explicit planning targets for actions.","strongest_claim":"F1 employs a next-scale prediction mechanism to synthesize goal-conditioned visual foresight as explicit planning targets. By forecasting plausible future visual states, F1 reformulates action generation as a foresight-guided inverse dynamics problem, enabling actions that implicitly achieve visual goals.","weakest_assumption":"That the generated visual foresight accurately represents plausible future states that can reliably serve as planning targets for action generation in dynamic, real-world scenes."}},"verdict_id":"671be10c-2e2b-4e00-954b-a8899e7ff485"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7aa2a830d2571c9f40cf9e210545f95e541c0b08edf175fc7abcdb016b131af9","target":"record","created_at":"2026-05-17T23:38:47Z","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":"41f35daf8a35df3024efb59840a8f315be844de7c18c88f13397fd07cd437698","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:58:30Z","title_canon_sha256":"e04e81df5783ed00b29047b3032c726b425d07d17604093f44c061e07afd9647"},"schema_version":"1.0","source":{"id":"2509.06951","kind":"arxiv","version":2}},"canonical_sha256":"857ee336ded0fdc5be70a771ede13ccff267282347663f2723706a7f3734a0e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"857ee336ded0fdc5be70a771ede13ccff267282347663f2723706a7f3734a0e3","first_computed_at":"2026-05-17T23:38:47.845674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.845674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DJ7Lpjsl4SpW9dRPzdYstjlzs8sEIbZJKjgj7NbpEkpUvYYxFzPTglJ9qUOkJGIQhFJL6OW1oXFt8yF9VorTBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.846488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06951","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7aa2a830d2571c9f40cf9e210545f95e541c0b08edf175fc7abcdb016b131af9","sha256:52233ee733b8ea01997dcf1b5926da157becd3e2af6dc13e2874bab906297f22"],"state_sha256":"a650a352122cd040bf33962e393f3c1a2975385f232999f4d167ee7f9589dc2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ai5N+GW3/KtSmFvtO/koEPfhnjSTAuyz6So1AQMBvhiAUFLX+1rK5qNAJxzPS3nncSNXBHNiFf+FUNoTKDFoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T03:45:58.720025Z","bundle_sha256":"ca3a51a52390f153e2f6b6689030baf1a26121d502f39498bfae10dba1479909"}}