{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZNCB4LCZBVFWSARH7XUDMG33WG","short_pith_number":"pith:ZNCB4LCZ","schema_version":"1.0","canonical_sha256":"cb441e2c590d4b690227fde8361b7bb1bb152c367ac78cd73c5ed137a88f839d","source":{"kind":"arxiv","id":"2606.25127","version":1},"attestation_state":"computed","paper":{"title":"Reward-Conditioned Attention: How Reward Design Shapes What Autonomous Driving Agents See","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Ahmed Djalal Hacini, Aissa Boulmerka, Mohamed Benabdelouahad, Nadir Farhi","submitted_at":"2026-06-23T20:02:51Z","abstract_excerpt":"We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving. Using three Perceiver-based agents that share identical architectures and training data but differ only in their reward configurations$\\unicode{x2014}$ranging from basic violation penalties to continuous proximity penalties$\\unicode{x2014}$we analyze cross-attention allocation across 50 real-world scenarios from the Waymo Open Motion Dataset. A central methodological finding is that na\\\"ive pooling of timesteps across episodes substantially underestimates the"},"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":"2606.25127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T20:02:51Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"10b7ec90a0ea9c730009d7d15905eb6d39855934db7e0c0bde4afd93e4997593","abstract_canon_sha256":"ee0f86293b9d42778d78c7e31332bcab425a89ee4701f320486b6e504757da68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:18.790818Z","signature_b64":"+3AVd5wTPA3cGfxQZm33+Rm1xoEL0uYFTa8TM8MmgxwnjKWraL9awCPd9h0MoKC4IIj9UpP2JjKoLsZZUbPCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb441e2c590d4b690227fde8361b7bb1bb152c367ac78cd73c5ed137a88f839d","last_reissued_at":"2026-06-25T00:18:18.790414Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:18.790414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-Conditioned Attention: How Reward Design Shapes What Autonomous Driving Agents See","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Ahmed Djalal Hacini, Aissa Boulmerka, Mohamed Benabdelouahad, Nadir Farhi","submitted_at":"2026-06-23T20:02:51Z","abstract_excerpt":"We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving. Using three Perceiver-based agents that share identical architectures and training data but differ only in their reward configurations$\\unicode{x2014}$ranging from basic violation penalties to continuous proximity penalties$\\unicode{x2014}$we analyze cross-attention allocation across 50 real-world scenarios from the Waymo Open Motion Dataset. A central methodological finding is that na\\\"ive pooling of timesteps across episodes substantially underestimates the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25127","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/2606.25127/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":"2606.25127","created_at":"2026-06-25T00:18:18.790478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25127v1","created_at":"2026-06-25T00:18:18.790478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25127","created_at":"2026-06-25T00:18:18.790478+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNCB4LCZBVFW","created_at":"2026-06-25T00:18:18.790478+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNCB4LCZBVFWSARH","created_at":"2026-06-25T00:18:18.790478+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNCB4LCZ","created_at":"2026-06-25T00:18:18.790478+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/ZNCB4LCZBVFWSARH7XUDMG33WG","json":"https://pith.science/pith/ZNCB4LCZBVFWSARH7XUDMG33WG.json","graph_json":"https://pith.science/api/pith-number/ZNCB4LCZBVFWSARH7XUDMG33WG/graph.json","events_json":"https://pith.science/api/pith-number/ZNCB4LCZBVFWSARH7XUDMG33WG/events.json","paper":"https://pith.science/paper/ZNCB4LCZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZNCB4LCZBVFWSARH7XUDMG33WG","download_json":"https://pith.science/pith/ZNCB4LCZBVFWSARH7XUDMG33WG.json","view_paper":"https://pith.science/paper/ZNCB4LCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25127&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNCB4LCZBVFWSARH7XUDMG33WG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNCB4LCZBVFWSARH7XUDMG33WG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNCB4LCZBVFWSARH7XUDMG33WG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNCB4LCZBVFWSARH7XUDMG33WG/action/storage_attestation","attest_author":"https://pith.science/pith/ZNCB4LCZBVFWSARH7XUDMG33WG/action/author_attestation","sign_citation":"https://pith.science/pith/ZNCB4LCZBVFWSARH7XUDMG33WG/action/citation_signature","submit_replication":"https://pith.science/pith/ZNCB4LCZBVFWSARH7XUDMG33WG/action/replication_record"}},"created_at":"2026-06-25T00:18:18.790478+00:00","updated_at":"2026-06-25T00:18:18.790478+00:00"}