{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D2TXS2QH3RXTVF2TZI3CCU4BMD","short_pith_number":"pith:D2TXS2QH","schema_version":"1.0","canonical_sha256":"1ea7796a07dc6f3a9753ca3621538160f167a3678ff78111741581b60941a45b","source":{"kind":"arxiv","id":"2312.04535","version":2},"attestation_state":"computed","paper":{"title":"Trajeglish: Traffic Modeling as Next-Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Jonah Philion, Sanja Fidler, Xue Bin Peng","submitted_at":"2023-12-07T18:53:27Z","abstract_excerpt":"A longstanding challenge for self-driving development is simulating dynamic driving scenarios seeded from recorded driving logs. In pursuit of this functionality, we apply tools from discrete sequence modeling to model how vehicles, pedestrians and cyclists interact in driving scenarios. Using a simple data-driven tokenization scheme, we discretize trajectories to centimeter-level resolution using a small vocabulary. We then model the multi-agent sequence of discrete motion tokens with a GPT-like encoder-decoder that is autoregressive in time and takes into account intra-timestep interaction b"},"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":"2312.04535","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T18:53:27Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1ae4cd452685d1745ab8f8ab1d52152258a851f8ae852ef2afb24241dcbed0be","abstract_canon_sha256":"7aa1adc3120b7e266076999abebd5f217fbf19f38d9b833a72b127b13d285994"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:00.337046Z","signature_b64":"b3jrRB/bzkr5s3MT2w80jpfRnE5EzYp33hUYawL/pM870UFcKlKL1n5k0Ophyzs7EKXurHp2w3OgNyusk1fUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ea7796a07dc6f3a9753ca3621538160f167a3678ff78111741581b60941a45b","last_reissued_at":"2026-07-05T08:08:00.336652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:00.336652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trajeglish: Traffic Modeling as Next-Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Jonah Philion, Sanja Fidler, Xue Bin Peng","submitted_at":"2023-12-07T18:53:27Z","abstract_excerpt":"A longstanding challenge for self-driving development is simulating dynamic driving scenarios seeded from recorded driving logs. In pursuit of this functionality, we apply tools from discrete sequence modeling to model how vehicles, pedestrians and cyclists interact in driving scenarios. Using a simple data-driven tokenization scheme, we discretize trajectories to centimeter-level resolution using a small vocabulary. We then model the multi-agent sequence of discrete motion tokens with a GPT-like encoder-decoder that is autoregressive in time and takes into account intra-timestep interaction b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04535","kind":"arxiv","version":2},"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/2312.04535/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":"2312.04535","created_at":"2026-07-05T08:08:00.336708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04535v2","created_at":"2026-07-05T08:08:00.336708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04535","created_at":"2026-07-05T08:08:00.336708+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2TXS2QH3RXT","created_at":"2026-07-05T08:08:00.336708+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2TXS2QH3RXTVF2T","created_at":"2026-07-05T08:08:00.336708+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2TXS2QH","created_at":"2026-07-05T08:08:00.336708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19370","citing_title":"Human-like autonomy emerges from self-play and a pinch of human data","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31844","citing_title":"Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13757","citing_title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD","json":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD.json","graph_json":"https://pith.science/api/pith-number/D2TXS2QH3RXTVF2TZI3CCU4BMD/graph.json","events_json":"https://pith.science/api/pith-number/D2TXS2QH3RXTVF2TZI3CCU4BMD/events.json","paper":"https://pith.science/paper/D2TXS2QH"},"agent_actions":{"view_html":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD","download_json":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD.json","view_paper":"https://pith.science/paper/D2TXS2QH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04535&json=true","fetch_graph":"https://pith.science/api/pith-number/D2TXS2QH3RXTVF2TZI3CCU4BMD/graph.json","fetch_events":"https://pith.science/api/pith-number/D2TXS2QH3RXTVF2TZI3CCU4BMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD/action/storage_attestation","attest_author":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD/action/author_attestation","sign_citation":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD/action/citation_signature","submit_replication":"https://pith.science/pith/D2TXS2QH3RXTVF2TZI3CCU4BMD/action/replication_record"}},"created_at":"2026-07-05T08:08:00.336708+00:00","updated_at":"2026-07-05T08:08:00.336708+00:00"}