{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HH6FGX25ZIMDUUYQCWPF2MZS6J","short_pith_number":"pith:HH6FGX25","schema_version":"1.0","canonical_sha256":"39fc535f5dca183a5310159e5d3332f24173dcf83da0d6cf8021c5768d7670fd","source":{"kind":"arxiv","id":"2607.18910","version":1},"attestation_state":"computed","paper":{"title":"Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daimin Chen, Shan Dai, Yuyang Shen","submitted_at":"2026-07-21T09:52:23Z","abstract_excerpt":"Sequential decision making in non-stationary and partially observable environments requires rapid adaptation to latent regime changes. However, existing Transformer decision models face a structural bottleneck in the retrieval mechanism: even when reward is used for training or exposed as an input token, attention retrieval remains primarily driven by observation-derived similarity. We formalize this limitation as feedback-blind retrieval, and formally show that, on feedback-informative tasks, observation-equivalent histories with different action-reward outcomes cannot be distinguished by any"},"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":"2607.18910","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T09:52:23Z","cross_cats_sorted":[],"title_canon_sha256":"71dea3ce0dbc1ad8d1164236f477d9a3655a3b2aac78bab3d679ea0668ce002b","abstract_canon_sha256":"084020fd2577eb42b1666d433dc45e031612dcc2f40ebdb647fde50775989a20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:19.372963Z","signature_b64":"rzivM8Rc50vt37XgL9T4UXgl8FM2XsBIzLN3D3PNMA65c7UjvLAQyiSD2zi8TyO1wwuWdRBFOA/NmDE17/FiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39fc535f5dca183a5310159e5d3332f24173dcf83da0d6cf8021c5768d7670fd","last_reissued_at":"2026-07-22T01:23:19.372160Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:19.372160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daimin Chen, Shan Dai, Yuyang Shen","submitted_at":"2026-07-21T09:52:23Z","abstract_excerpt":"Sequential decision making in non-stationary and partially observable environments requires rapid adaptation to latent regime changes. However, existing Transformer decision models face a structural bottleneck in the retrieval mechanism: even when reward is used for training or exposed as an input token, attention retrieval remains primarily driven by observation-derived similarity. We formalize this limitation as feedback-blind retrieval, and formally show that, on feedback-informative tasks, observation-equivalent histories with different action-reward outcomes cannot be distinguished by any"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18910","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/2607.18910/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":"2607.18910","created_at":"2026-07-22T01:23:19.372581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18910v1","created_at":"2026-07-22T01:23:19.372581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18910","created_at":"2026-07-22T01:23:19.372581+00:00"},{"alias_kind":"pith_short_12","alias_value":"HH6FGX25ZIMD","created_at":"2026-07-22T01:23:19.372581+00:00"},{"alias_kind":"pith_short_16","alias_value":"HH6FGX25ZIMDUUYQ","created_at":"2026-07-22T01:23:19.372581+00:00"},{"alias_kind":"pith_short_8","alias_value":"HH6FGX25","created_at":"2026-07-22T01:23:19.372581+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/HH6FGX25ZIMDUUYQCWPF2MZS6J","json":"https://pith.science/pith/HH6FGX25ZIMDUUYQCWPF2MZS6J.json","graph_json":"https://pith.science/api/pith-number/HH6FGX25ZIMDUUYQCWPF2MZS6J/graph.json","events_json":"https://pith.science/api/pith-number/HH6FGX25ZIMDUUYQCWPF2MZS6J/events.json","paper":"https://pith.science/paper/HH6FGX25"},"agent_actions":{"view_html":"https://pith.science/pith/HH6FGX25ZIMDUUYQCWPF2MZS6J","download_json":"https://pith.science/pith/HH6FGX25ZIMDUUYQCWPF2MZS6J.json","view_paper":"https://pith.science/paper/HH6FGX25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18910&json=true","fetch_graph":"https://pith.science/api/pith-number/HH6FGX25ZIMDUUYQCWPF2MZS6J/graph.json","fetch_events":"https://pith.science/api/pith-number/HH6FGX25ZIMDUUYQCWPF2MZS6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HH6FGX25ZIMDUUYQCWPF2MZS6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HH6FGX25ZIMDUUYQCWPF2MZS6J/action/storage_attestation","attest_author":"https://pith.science/pith/HH6FGX25ZIMDUUYQCWPF2MZS6J/action/author_attestation","sign_citation":"https://pith.science/pith/HH6FGX25ZIMDUUYQCWPF2MZS6J/action/citation_signature","submit_replication":"https://pith.science/pith/HH6FGX25ZIMDUUYQCWPF2MZS6J/action/replication_record"}},"created_at":"2026-07-22T01:23:19.372581+00:00","updated_at":"2026-07-22T01:23:19.372581+00:00"}