{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ATJL2MCI7D2HWVMP35S27LBN6E","short_pith_number":"pith:ATJL2MCI","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"},"canonical_sha256":"04d2bd3048f8f47b558fdf65afac2df122249d0c55293a613f769e73a6dd3ba8","source":{"kind":"arxiv","id":"2605.28849","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28849","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28849v1","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28849","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"ATJL2MCI7D2H","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"ATJL2MCI7D2HWVMP","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"ATJL2MCI","created_at":"2026-05-29T00:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ATJL2MCI7D2HWVMP35S27LBN6E","target":"record","payload":{"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"},"canonical_sha256":"04d2bd3048f8f47b558fdf65afac2df122249d0c55293a613f769e73a6dd3ba8","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"},"source_kind":"arxiv","source_id":"2605.28849","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T00:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Se2VewtK4EMrl2kZQy80B5QKhkqcEHkrJvjBcfuyGT9IJefEwIpvm0xqFehAflp0h4m8TzQ0+3qtHu9MuCgSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T11:46:18.574346Z"},"content_sha256":"95203d698b1b7a9a1d98314c42b23e54985ca9317590387cc7ecca7211a07064","schema_version":"1.0","event_id":"sha256:95203d698b1b7a9a1d98314c42b23e54985ca9317590387cc7ecca7211a07064"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ATJL2MCI7D2HWVMP35S27LBN6E","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T00:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RmRJntAntXJjhngM/Wsn94PKs9sMitpiGdH2nvQc8qTTafVg1OnaTLc7bIe7DWO4cGdnFMcrQ1v83gArfCdGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T11:46:18.575087Z"},"content_sha256":"2025c85948eb3e2712c98deff12623d7e4ca821a52184eff3d72102f826181e8","schema_version":"1.0","event_id":"sha256:2025c85948eb3e2712c98deff12623d7e4ca821a52184eff3d72102f826181e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/bundle.json","state_url":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ATJL2MCI7D2HWVMP35S27LBN6E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T11:46:18Z","links":{"resolver":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E","bundle":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/bundle.json","state":"https://pith.science/pith/ATJL2MCI7D2HWVMP35S27LBN6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ATJL2MCI7D2HWVMP35S27LBN6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ATJL2MCI7D2HWVMP35S27LBN6E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e2da6d58eae939e74cdff87ee10e90c418f3f24aaf7153a898b2fb3f41949517","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T11:33:44Z","title_canon_sha256":"fd9c62a9cf47e9b7f50df7999ab075de437074974218e89f92c9f85b375f7475"},"schema_version":"1.0","source":{"id":"2605.28849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28849","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28849v1","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28849","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"ATJL2MCI7D2H","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"ATJL2MCI7D2HWVMP","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"ATJL2MCI","created_at":"2026-05-29T00:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:2025c85948eb3e2712c98deff12623d7e4ca821a52184eff3d72102f826181e8","target":"graph","created_at":"2026-05-29T00:04:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.28849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Li, Guang Yang, Shangdong Yang, Wenhao Wang, Xingguo Chen, Yuchen Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T11:33:44Z","title":"Behavior-Induced Mirror-Prox Temporal-Difference Learning for Faster Off-Policy Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28849","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:95203d698b1b7a9a1d98314c42b23e54985ca9317590387cc7ecca7211a07064","target":"record","created_at":"2026-05-29T00:04:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e2da6d58eae939e74cdff87ee10e90c418f3f24aaf7153a898b2fb3f41949517","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T11:33:44Z","title_canon_sha256":"fd9c62a9cf47e9b7f50df7999ab075de437074974218e89f92c9f85b375f7475"},"schema_version":"1.0","source":{"id":"2605.28849","kind":"arxiv","version":1}},"canonical_sha256":"04d2bd3048f8f47b558fdf65afac2df122249d0c55293a613f769e73a6dd3ba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04d2bd3048f8f47b558fdf65afac2df122249d0c55293a613f769e73a6dd3ba8","first_computed_at":"2026-05-29T00:04:14.026996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T00:04:14.026996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k6cqlm51JpHuQmzzH6rcJAJ8v6/K3K+h6JZnRRLX0pA9OI7/W/RtiYEwer+gyXLODb2xpbU/kjBPS+3emaHyAA==","signature_status":"signed_v1","signed_at":"2026-05-29T00:04:14.027607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95203d698b1b7a9a1d98314c42b23e54985ca9317590387cc7ecca7211a07064","sha256:2025c85948eb3e2712c98deff12623d7e4ca821a52184eff3d72102f826181e8"],"state_sha256":"9b877d0530284cd0f1ebb61acb3c5a1ac9c3b4fb26485c7c0611930e55216c2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uDxt2jV46L9z/Ky5dg5VXSTQrkNKMycvnndS5SizP/wJlOSx46e3bIKSW1jiuSK7KQMX9z4tRhooqozhjogLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T11:46:18.579079Z","bundle_sha256":"b029e510cf9e86ea4d1ab4fe7198343603b35345c2bd6b44f5ee43ba303ef2c3"}}