{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IRUIEZPOP42AMWJ3MZQ2F2KJ62","short_pith_number":"pith:IRUIEZPO","schema_version":"1.0","canonical_sha256":"44688265ee7f3406593b6661a2e949f69f994a2f7d078e5d2cb7529aba292489","source":{"kind":"arxiv","id":"2606.12987","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Transformer World-Action Model for AV Scene Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Benjamin Jiang, Kai Xi Chew, Ruslan Sharifullin","submitted_at":"2026-06-11T07:24:12Z","abstract_excerpt":"Action-conditioned world models let an autonomous vehicle predict future camera scenes from its own planned controls, enabling planning and simulation without real-world rollouts, but at compact, trainable scale the futures are ambiguous and the field's standard distortion metrics actively mislead: they reward a blurry regression mean over a realistic prediction. We confront this with a compact latent world model that, given the present front-camera latent and a sequence of ego-actions, predicts future scene latents a frozen decoder renders to $256 \\times 256$ frames up to 8 seconds ahead, eva"},"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":"2606.12987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T07:24:12Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"f15e60e93b787dafa4545e5f267c29a061e6add4ed06e6eadc7417f8a2c85722","abstract_canon_sha256":"2dc67464bd0a73594179012690b6c9aeb533c5d40b504e318f88cbcdb3024371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:36.223381Z","signature_b64":"MPfno7dDKJuI5pmU48VaqWUAyFObTP0FQuUdu4bdvD7C2OCXBWHxx+sYrsS4Iu09ppRGfSKtiJBdb8wNv+YcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44688265ee7f3406593b6661a2e949f69f994a2f7d078e5d2cb7529aba292489","last_reissued_at":"2026-06-12T01:09:36.222979Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:36.222979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Transformer World-Action Model for AV Scene Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Benjamin Jiang, Kai Xi Chew, Ruslan Sharifullin","submitted_at":"2026-06-11T07:24:12Z","abstract_excerpt":"Action-conditioned world models let an autonomous vehicle predict future camera scenes from its own planned controls, enabling planning and simulation without real-world rollouts, but at compact, trainable scale the futures are ambiguous and the field's standard distortion metrics actively mislead: they reward a blurry regression mean over a realistic prediction. We confront this with a compact latent world model that, given the present front-camera latent and a sequence of ego-actions, predicts future scene latents a frozen decoder renders to $256 \\times 256$ frames up to 8 seconds ahead, eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12987","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/2606.12987/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":"2606.12987","created_at":"2026-06-12T01:09:36.223036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12987v1","created_at":"2026-06-12T01:09:36.223036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12987","created_at":"2026-06-12T01:09:36.223036+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRUIEZPOP42A","created_at":"2026-06-12T01:09:36.223036+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRUIEZPOP42AMWJ3","created_at":"2026-06-12T01:09:36.223036+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRUIEZPO","created_at":"2026-06-12T01:09:36.223036+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/IRUIEZPOP42AMWJ3MZQ2F2KJ62","json":"https://pith.science/pith/IRUIEZPOP42AMWJ3MZQ2F2KJ62.json","graph_json":"https://pith.science/api/pith-number/IRUIEZPOP42AMWJ3MZQ2F2KJ62/graph.json","events_json":"https://pith.science/api/pith-number/IRUIEZPOP42AMWJ3MZQ2F2KJ62/events.json","paper":"https://pith.science/paper/IRUIEZPO"},"agent_actions":{"view_html":"https://pith.science/pith/IRUIEZPOP42AMWJ3MZQ2F2KJ62","download_json":"https://pith.science/pith/IRUIEZPOP42AMWJ3MZQ2F2KJ62.json","view_paper":"https://pith.science/paper/IRUIEZPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12987&json=true","fetch_graph":"https://pith.science/api/pith-number/IRUIEZPOP42AMWJ3MZQ2F2KJ62/graph.json","fetch_events":"https://pith.science/api/pith-number/IRUIEZPOP42AMWJ3MZQ2F2KJ62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRUIEZPOP42AMWJ3MZQ2F2KJ62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRUIEZPOP42AMWJ3MZQ2F2KJ62/action/storage_attestation","attest_author":"https://pith.science/pith/IRUIEZPOP42AMWJ3MZQ2F2KJ62/action/author_attestation","sign_citation":"https://pith.science/pith/IRUIEZPOP42AMWJ3MZQ2F2KJ62/action/citation_signature","submit_replication":"https://pith.science/pith/IRUIEZPOP42AMWJ3MZQ2F2KJ62/action/replication_record"}},"created_at":"2026-06-12T01:09:36.223036+00:00","updated_at":"2026-06-12T01:09:36.223036+00:00"}