{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_c66f3f94b5fefe25cef998401d9b6eb018c497b0e139676d059a7c1e21cadab9","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_c66f3f94b5fefe25cef998401d9b6eb018c497b0e139676d059a7c1e21cadab9","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"0bf0f05b1fd4f216a3265640a83ac030098985b2a4fdc68e49426ded7e8b8df2","published":"Tue, 26 May 2026 00:00:00 -0400","receipt_hash":"0bf0f05b1fd4f216a3265640a83ac030098985b2a4fdc68e49426ded7e8b8df2","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"0bf0f05b1fd4f216a3265640a83ac030098985b2a4fdc68e49426ded7e8b8df2","observed_at":"2026-05-26T04:43:39.018238Z","parent_run_hash":"dca8dedd754ad6a1772113d6b97ee4f4ab9a0afbdeb44aaace5ff2d2446b164b","published":"Tue, 26 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2605.25749v1 Announce Type: cross \nAbstract: In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent studies have shifted towards end-to-end generative frameworks, which typically leverage list-wise rewards or preference alignment to guide generator training. However, these methods still face two critical issues. First is the heuristic label bias. Existing methods often construct training targets based on simple rules, such as promoting clicked items to the top, while ignoring causal dependencies within the list context. Second is the credit assignment problem. Sparse list-level posterior rewards fail to directly guide intermediate steps in sequence generation, leading to ambiguous optimization directions.\n  To address these issues, we propose DeGRe (Dense-supervised Generative Reranking), a generati","title":"DeGRe: Dense-supervised Generative Reranking for Recommendation","url":"https://arxiv.org/abs/2605.25749","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.25749v1 Announce Type: cross \nAbstract: In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent studies have shifted towards end-to-end generative frameworks, which typically leverage list-wise rewards or preference alignment to guide generator training. However, these methods still face two critical issues. First is the heuristic label bias. Existing methods often construct training targets based on simple rules, such as promoting clicked items to the top, while ignoring causal dependencies within the list context. Second is the credit assignment problem. Sparse list-level posterior rewards fail to directly guide intermediate steps in sequence generation, leading to ambiguous optimization directions.\n  To address these issues, we propose DeGRe (Dense-supervised Generative Reranking), a generati","title":"DeGRe: Dense-supervised Generative Reranking for Recommendation","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-26T04:43:39Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.25749"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ca2f7fdf10e46214213934ace968ed5ec613bfd06ecc13172f902e8443d05101ff4a491170002b2703c25331e07a28fa22f730fe4f4f625fab0845b0fdbdeb0d","signer":"crovia.substrate","subject":{"observed_at":"2026-05-26T04:43:39Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.25749"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"68d0047a6255f5d923b06a6ef0b7105c3c0ef0768d4aaad09c8b89f4c55a128a","leaf_index":151720,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"7238056c871a77549221aae6635271ba0113040a87a9dee3a8e723d4ce9fae77","side":"right"},{"sibling":"4e677529a13d4df777ad55337f7300d923b9869e41e5f9084f9f1b4feb6dae8c","side":"right"},{"sibling":"81d9baef1586f71d195fb2c056f81e628c6982f480817274c734b91b25b8b7b3","side":"right"},{"sibling":"d3e42249ee3fd632a08f1ceff531848a41e20504d5bc26c899f20850a583481d","side":"left"},{"sibling":"407b891d3da12cf74fa40ce1962a4cfd5e65de5213e830cf0164f8a665da6161","side":"right"},{"sibling":"1fdb62cc53d97a7f7a1438e1d514a795206e3fd636e208e00b18fba2519cd611","side":"left"},{"sibling":"59c025ecd2dec1777c83a364f63a0af602c1b8c1069e8b09513a2e68a6f64e32","side":"right"},{"sibling":"f9db7ff3c5db7011b2738b446bad7b165ec8fd162c800ba3bad08298201edaa3","side":"left"},{"sibling":"aff657821100efc777fe98abc63d25a13c2d813d2a00f85a278e295ee3a166b3","side":"right"},{"sibling":"879666fab72e779ab55d0564eaabd64b00534fd6bba7f18412c7f31f61ffd09f","side":"right"},{"sibling":"f40ccedd90c323817e961adc0a2e2db82b8aabe192b6c9d5a373ff988987b207","side":"right"},{"sibling":"b85ea61ae405eed84392a7b6b1eee5536f5a38d6b04070638e23ec7b71e3443a","side":"right"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"e5893793e3591ed7f5e58ca94ffcfba46bb30f69fb1c25d5ba8ef49eb99f9126","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e3eecaf996dbe7229a7bb1d234c97aea97a252c5f7c89f8547b6d091db0f0e40","side":"right"},{"sibling":"55bcbd4da3e20d93931f7e58673f10232e81a5b1514d7396cb4b71e8f95788d0","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":152106,"merkle_root":"ac5182c6f3dd09931f2a689df5f4be36df7b55e55bcf106e195671f5ed55fd8f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260526T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-26T05:37:34Z","sig_algorithm":"ed25519","signature":"a401243fbd2c077d29a623c6ef616c78fbd5c8ce1930afa7af7165b2386e5a8cf15d5094983a1c962e71b27b911a3f3ce09c8cfab9393be2ce5ce8ee6513da06","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_c66f3f94b5fefe25cef998401d9b6eb018c497b0e139676d059a7c1e21cadab9"}}