{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ATJL2MCI7D2HWVMP35S27LBN6E","short_pith_number":"pith:ATJL2MCI","schema_version":"1.0","canonical_sha256":"04d2bd3048f8f47b558fdf65afac2df122249d0c55293a613f769e73a6dd3ba8","source":{"kind":"arxiv","id":"2605.28849","version":1},"attestation_state":"computed","paper":{"title":"Behavior-Induced Mirror-Prox Temporal-Difference Learning for Faster Off-Policy Prediction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Li, Guang Yang, Shangdong Yang, Wenhao Wang, Xingguo Chen, Yuchen Shen","submitted_at":"2026-05-16T11:33:44Z","abstract_excerpt":"Gradient temporal-difference methods provide stable off-policy prediction with linear function approximation, but their practical performance is strongly affected by the geometry induced by the auxiliary-variable metric. Existing Mirror-Prox TD methods typically use the feature covariance metric, whereas hybrid TD methods suggest that behavior-policy transition information can provide a more informative update geometry. This paper proposes a behavior-induced Mirror-Prox temporal-difference method, called STHTD-MP, which replaces the covariance metric in the primal-dual saddle-point formulation"},"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":"2605.28849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T11:33:44Z","cross_cats_sorted":[],"title_canon_sha256":"fd9c62a9cf47e9b7f50df7999ab075de437074974218e89f92c9f85b375f7475","abstract_canon_sha256":"e2da6d58eae939e74cdff87ee10e90c418f3f24aaf7153a898b2fb3f41949517"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:14.027607Z","signature_b64":"k6cqlm51JpHuQmzzH6rcJAJ8v6/K3K+h6JZnRRLX0pA9OI7/W/RtiYEwer+gyXLODb2xpbU/kjBPS+3emaHyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04d2bd3048f8f47b558fdf65afac2df122249d0c55293a613f769e73a6dd3ba8","last_reissued_at":"2026-05-29T00:04:14.026996Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:14.026996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behavior-Induced Mirror-Prox Temporal-Difference Learning for Faster Off-Policy Prediction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Li, Guang Yang, Shangdong Yang, Wenhao Wang, Xingguo Chen, Yuchen Shen","submitted_at":"2026-05-16T11:33:44Z","abstract_excerpt":"Gradient temporal-difference methods provide stable off-policy prediction with linear function approximation, but their practical performance is strongly affected by the geometry induced by the auxiliary-variable metric. Existing Mirror-Prox TD methods typically use the feature covariance metric, whereas hybrid TD methods suggest that behavior-policy transition information can provide a more informative update geometry. This paper proposes a behavior-induced Mirror-Prox temporal-difference method, called STHTD-MP, which replaces the covariance metric in the primal-dual saddle-point formulation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28849","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/2605.28849/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":"2605.28849","created_at":"2026-05-29T00:04:14.027104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28849v1","created_at":"2026-05-29T00:04:14.027104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28849","created_at":"2026-05-29T00:04:14.027104+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATJL2MCI7D2H","created_at":"2026-05-29T00:04:14.027104+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATJL2MCI7D2HWVMP","created_at":"2026-05-29T00:04:14.027104+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATJL2MCI","created_at":"2026-05-29T00:04:14.027104+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/ATJL2MCI7D2HWVMP35S27LBN6E","json":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E.json","graph_json":"https://pith.science/api/pith-number/ATJL2MCI7D2HWVMP35S27LBN6E/graph.json","events_json":"https://pith.science/api/pith-number/ATJL2MCI7D2HWVMP35S27LBN6E/events.json","paper":"https://pith.science/paper/ATJL2MCI"},"agent_actions":{"view_html":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E","download_json":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E.json","view_paper":"https://pith.science/paper/ATJL2MCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28849&json=true","fetch_graph":"https://pith.science/api/pith-number/ATJL2MCI7D2HWVMP35S27LBN6E/graph.json","fetch_events":"https://pith.science/api/pith-number/ATJL2MCI7D2HWVMP35S27LBN6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/action/storage_attestation","attest_author":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/action/author_attestation","sign_citation":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/action/citation_signature","submit_replication":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/action/replication_record"}},"created_at":"2026-05-29T00:04:14.027104+00:00","updated_at":"2026-05-29T00:04:14.027104+00:00"}