{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7RVYTSECR5CO76WGRK5V4FGFJW","short_pith_number":"pith:7RVYTSEC","schema_version":"1.0","canonical_sha256":"fc6b89c8828f44effac68abb5e14c54da7f125f6da374d51f63b021f2eb48f26","source":{"kind":"arxiv","id":"2110.06607","version":3},"attestation_state":"computed","paper":{"title":"THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Bogdan Stanciulescu, Dzmitry Tsishkou, Fabien Moutarde, Stefano Sabatini, Thomas Gilles","submitted_at":"2021-10-13T10:05:47Z","abstract_excerpt":"In this paper, we propose THOMAS, a joint multi-agent trajectory prediction framework allowing for an efficient and consistent prediction of multi-agent multi-modal trajectories. We present a unified model architecture for simultaneous agent future heatmap estimation, in which we leverage hierarchical and sparse image generation for fast and memory-efficient inference. We propose a learnable trajectory recombination model that takes as input a set of predicted trajectories for each agent and outputs its consistent reordered recombination. This recombination module is able to realign the initia"},"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":"2110.06607","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-13T10:05:47Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"4a8cd4952345f2f47b4197aa4dd8276303e81a0a407b55bd32281644d612609e","abstract_canon_sha256":"b5335a600b0ae4cc02f5491a401949744f7ca6d7fc7d90c2f6c0ebe239092790"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:25.918147Z","signature_b64":"R7ky5hM5a1DoI3WlTQYPJXMsrcuA4hZ74Vgmx/RGx8Jtfz6jjRePHyqiIf2+hzMAkpIVDAoLHOxvuxVVUUXiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc6b89c8828f44effac68abb5e14c54da7f125f6da374d51f63b021f2eb48f26","last_reissued_at":"2026-07-05T03:50:25.917570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:25.917570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Bogdan Stanciulescu, Dzmitry Tsishkou, Fabien Moutarde, Stefano Sabatini, Thomas Gilles","submitted_at":"2021-10-13T10:05:47Z","abstract_excerpt":"In this paper, we propose THOMAS, a joint multi-agent trajectory prediction framework allowing for an efficient and consistent prediction of multi-agent multi-modal trajectories. We present a unified model architecture for simultaneous agent future heatmap estimation, in which we leverage hierarchical and sparse image generation for fast and memory-efficient inference. We propose a learnable trajectory recombination model that takes as input a set of predicted trajectories for each agent and outputs its consistent reordered recombination. This recombination module is able to realign the initia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06607","kind":"arxiv","version":3},"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/2110.06607/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":"2110.06607","created_at":"2026-07-05T03:50:25.917636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06607v3","created_at":"2026-07-05T03:50:25.917636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06607","created_at":"2026-07-05T03:50:25.917636+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RVYTSECR5CO","created_at":"2026-07-05T03:50:25.917636+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RVYTSECR5CO76WG","created_at":"2026-07-05T03:50:25.917636+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RVYTSEC","created_at":"2026-07-05T03:50:25.917636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.03262","citing_title":"Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions","ref_index":139,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW","json":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW.json","graph_json":"https://pith.science/api/pith-number/7RVYTSECR5CO76WGRK5V4FGFJW/graph.json","events_json":"https://pith.science/api/pith-number/7RVYTSECR5CO76WGRK5V4FGFJW/events.json","paper":"https://pith.science/paper/7RVYTSEC"},"agent_actions":{"view_html":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW","download_json":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW.json","view_paper":"https://pith.science/paper/7RVYTSEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06607&json=true","fetch_graph":"https://pith.science/api/pith-number/7RVYTSECR5CO76WGRK5V4FGFJW/graph.json","fetch_events":"https://pith.science/api/pith-number/7RVYTSECR5CO76WGRK5V4FGFJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW/action/storage_attestation","attest_author":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW/action/author_attestation","sign_citation":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW/action/citation_signature","submit_replication":"https://pith.science/pith/7RVYTSECR5CO76WGRK5V4FGFJW/action/replication_record"}},"created_at":"2026-07-05T03:50:25.917636+00:00","updated_at":"2026-07-05T03:50:25.917636+00:00"}