{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PTQPE4BS5DPNJB5FTNM2AZWL5P","short_pith_number":"pith:PTQPE4BS","schema_version":"1.0","canonical_sha256":"7ce0f27032e8ded487a59b59a066cbebca9787fa19ffb5022216eeea5f88c77c","source":{"kind":"arxiv","id":"2407.19564","version":1},"attestation_state":"computed","paper":{"title":"Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Jifeng Wang, Juergen Gall, Kaouther Messaoud, Yuejiang Liu","submitted_at":"2024-07-28T19:18:59Z","abstract_excerpt":"Recent progress in motion forecasting has been substantially driven by self-supervised pre-training. However, adapting pre-trained models for specific downstream tasks, especially motion prediction, through extensive fine-tuning is often inefficient. This inefficiency arises because motion prediction closely aligns with the masked pre-training tasks, and traditional full fine-tuning methods fail to fully leverage this alignment. To address this, we introduce Forecast-PEFT, a fine-tuning strategy that freezes the majority of the model's parameters, focusing adjustments on newly introduced promp"},"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":"2407.19564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-28T19:18:59Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c7138d8c963c287c33e3064ed3ac1b85274ab6c0f0349a0f0e333922a361c81a","abstract_canon_sha256":"5671416c007d56a0736425e4e42f87afdd080a8493c1571b28e5dee1ec869e39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:41.514346Z","signature_b64":"rmwBuzP+dhnx4XMkUK+D1ijNe3x+RvQ8nVnJGosXKOIU7qkQn4v8noknrHRV3iuS0Y5+rjsykiPmghz8C57xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ce0f27032e8ded487a59b59a066cbebca9787fa19ffb5022216eeea5f88c77c","last_reissued_at":"2026-07-05T08:49:41.513958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:41.513958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Jifeng Wang, Juergen Gall, Kaouther Messaoud, Yuejiang Liu","submitted_at":"2024-07-28T19:18:59Z","abstract_excerpt":"Recent progress in motion forecasting has been substantially driven by self-supervised pre-training. However, adapting pre-trained models for specific downstream tasks, especially motion prediction, through extensive fine-tuning is often inefficient. This inefficiency arises because motion prediction closely aligns with the masked pre-training tasks, and traditional full fine-tuning methods fail to fully leverage this alignment. To address this, we introduce Forecast-PEFT, a fine-tuning strategy that freezes the majority of the model's parameters, focusing adjustments on newly introduced promp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19564","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/2407.19564/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":"2407.19564","created_at":"2026-07-05T08:49:41.514017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19564v1","created_at":"2026-07-05T08:49:41.514017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19564","created_at":"2026-07-05T08:49:41.514017+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTQPE4BS5DPN","created_at":"2026-07-05T08:49:41.514017+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTQPE4BS5DPNJB5F","created_at":"2026-07-05T08:49:41.514017+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTQPE4BS","created_at":"2026-07-05T08:49:41.514017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04790","citing_title":"Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P","json":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P.json","graph_json":"https://pith.science/api/pith-number/PTQPE4BS5DPNJB5FTNM2AZWL5P/graph.json","events_json":"https://pith.science/api/pith-number/PTQPE4BS5DPNJB5FTNM2AZWL5P/events.json","paper":"https://pith.science/paper/PTQPE4BS"},"agent_actions":{"view_html":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P","download_json":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P.json","view_paper":"https://pith.science/paper/PTQPE4BS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19564&json=true","fetch_graph":"https://pith.science/api/pith-number/PTQPE4BS5DPNJB5FTNM2AZWL5P/graph.json","fetch_events":"https://pith.science/api/pith-number/PTQPE4BS5DPNJB5FTNM2AZWL5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P/action/storage_attestation","attest_author":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P/action/author_attestation","sign_citation":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P/action/citation_signature","submit_replication":"https://pith.science/pith/PTQPE4BS5DPNJB5FTNM2AZWL5P/action/replication_record"}},"created_at":"2026-07-05T08:49:41.514017+00:00","updated_at":"2026-07-05T08:49:41.514017+00:00"}