{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VMD5INELODZTOGCECQRAI33LD2","short_pith_number":"pith:VMD5INEL","schema_version":"1.0","canonical_sha256":"ab07d4348b70f33718441422046f6b1eb46a1a1eae6ad4b40b0a30cde0fd621c","source":{"kind":"arxiv","id":"2003.08111","version":3},"attestation_state":"computed","paper":{"title":"Transformer Networks for Trajectory Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabio Galasso, Francesco Giuliari, Irtiza Hasan, Marco Cristani","submitted_at":"2020-03-18T09:17:49Z","abstract_excerpt":"Most recent successes on forecasting the people motion are based on LSTM models and all most recent progress has been achieved by modelling the social interaction among people and the people interaction with the scene. We question the use of the LSTM models and propose the novel use of Transformer Networks for trajectory forecasting. This is a fundamental switch from the sequential step-by-step processing of LSTMs to the only-attention-based memory mechanisms of Transformers. In particular, we consider both the original Transformer Network (TF) and the larger Bidirectional Transformer (BERT), "},"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":"2003.08111","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-18T09:17:49Z","cross_cats_sorted":[],"title_canon_sha256":"519b7bf9bf49ac4e8129b3c5c56541c9b0d75e5bf7595bc5b9d1b4ff46fb6673","abstract_canon_sha256":"55e13c25830d9577019249f18d39d0890d756ee8816131795824cf06e946391f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:47.379728Z","signature_b64":"xbLWWRjb9SQXZ3V9O3/BDgN8b9yjWlmmxulw+fAhnIMQaBWqTDnR+zaEILl/Hd8q5DWOUfodpsW4FsmY+Ha+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab07d4348b70f33718441422046f6b1eb46a1a1eae6ad4b40b0a30cde0fd621c","last_reissued_at":"2026-07-05T01:44:47.379246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:47.379246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer Networks for Trajectory Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabio Galasso, Francesco Giuliari, Irtiza Hasan, Marco Cristani","submitted_at":"2020-03-18T09:17:49Z","abstract_excerpt":"Most recent successes on forecasting the people motion are based on LSTM models and all most recent progress has been achieved by modelling the social interaction among people and the people interaction with the scene. We question the use of the LSTM models and propose the novel use of Transformer Networks for trajectory forecasting. This is a fundamental switch from the sequential step-by-step processing of LSTMs to the only-attention-based memory mechanisms of Transformers. In particular, we consider both the original Transformer Network (TF) and the larger Bidirectional Transformer (BERT), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08111","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/2003.08111/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":"2003.08111","created_at":"2026-07-05T01:44:47.379299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.08111v3","created_at":"2026-07-05T01:44:47.379299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08111","created_at":"2026-07-05T01:44:47.379299+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMD5INELODZT","created_at":"2026-07-05T01:44:47.379299+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMD5INELODZTOGCE","created_at":"2026-07-05T01:44:47.379299+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMD5INEL","created_at":"2026-07-05T01:44:47.379299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14855","citing_title":"Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2","json":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2.json","graph_json":"https://pith.science/api/pith-number/VMD5INELODZTOGCECQRAI33LD2/graph.json","events_json":"https://pith.science/api/pith-number/VMD5INELODZTOGCECQRAI33LD2/events.json","paper":"https://pith.science/paper/VMD5INEL"},"agent_actions":{"view_html":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2","download_json":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2.json","view_paper":"https://pith.science/paper/VMD5INEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.08111&json=true","fetch_graph":"https://pith.science/api/pith-number/VMD5INELODZTOGCECQRAI33LD2/graph.json","fetch_events":"https://pith.science/api/pith-number/VMD5INELODZTOGCECQRAI33LD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2/action/storage_attestation","attest_author":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2/action/author_attestation","sign_citation":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2/action/citation_signature","submit_replication":"https://pith.science/pith/VMD5INELODZTOGCECQRAI33LD2/action/replication_record"}},"created_at":"2026-07-05T01:44:47.379299+00:00","updated_at":"2026-07-05T01:44:47.379299+00:00"}