{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YMQ4IL62WIPUY55GL2L275OVNX","short_pith_number":"pith:YMQ4IL62","canonical_record":{"source":{"id":"2607.26427","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T03:14:09Z","cross_cats_sorted":[],"title_canon_sha256":"6d8c6dfe2411192da0abddfcf5ccbd67c997af4c231c002e29ae7d6754d15e31","abstract_canon_sha256":"c059f8a0ffae38715933cb4be7d2b0dc66a845dbc7419c7e533585163083aef1"},"schema_version":"1.0"},"canonical_sha256":"c321c42fdab21f4c77a65e97aff5d56ddfcf9c077c7816a88630153b9e5c18f8","source":{"kind":"arxiv","id":"2607.26427","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26427","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26427v1","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26427","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"YMQ4IL62WIPU","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"YMQ4IL62WIPUY55G","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"YMQ4IL62","created_at":"2026-07-30T01:18:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YMQ4IL62WIPUY55GL2L275OVNX","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26427","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T03:14:09Z","cross_cats_sorted":[],"title_canon_sha256":"6d8c6dfe2411192da0abddfcf5ccbd67c997af4c231c002e29ae7d6754d15e31","abstract_canon_sha256":"c059f8a0ffae38715933cb4be7d2b0dc66a845dbc7419c7e533585163083aef1"},"schema_version":"1.0"},"canonical_sha256":"c321c42fdab21f4c77a65e97aff5d56ddfcf9c077c7816a88630153b9e5c18f8","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c321c42fdab21f4c77a65e97aff5d56ddfcf9c077c7816a88630153b9e5c18f8","last_reissued_at":"2026-07-30T01:18:23.859478Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:23.859478Z"},"source_kind":"arxiv","source_id":"2607.26427","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":"2026-07-30T01:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/BNd0Uks2aI/ADdKy8n2CJ/uDOOZJOTvWTPO3moMHwwBN50V71qbI349zfWYHtAVBYzXJWebatUDkPa3DhHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:27:52.508756Z"},"content_sha256":"eda687c6605a15a034cb4a16d228d9b1750efa0306a5a47f2113b016016a28b8","schema_version":"1.0","event_id":"sha256:eda687c6605a15a034cb4a16d228d9b1750efa0306a5a47f2113b016016a28b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YMQ4IL62WIPUY55GL2L275OVNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PSG: Pair-Space Generation for Efficient Generative Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chao Feng, Chenghao Zhang, Li Ma, Xiancheng Gao, Xiang Li, Yuanhao Pu","submitted_at":"2026-07-29T03:14:09Z","abstract_excerpt":"Modern recommender systems adopt Generator-Evaluator (G-E) for list-wise reranking: a generator produces sequences from candidates and an evaluator scores them at sequence-level to filter out the optimal one for exposure. Auto-Regressive(AR), working as the backbone for generative recommendation, suffers two limitations. First, its complexity grows linearly with list length, forcing the system to generate fewer lists under rigorous latency constraints and thus limiting exploration. Second, teacher-forcing creates a train-test mismatch; cumulative errors worsen with length and degrade quality.\n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26427","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/2607.26427/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":"2026-07-30T01:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZMjoVcR6DCOvFwXhDlrQkdqZGyuk6Nkna+mfXlPKH5ZF7G5XofBr/Lx90Ij8GT8PMxASXlBUa2p+4ZkVkLZQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:27:52.509308Z"},"content_sha256":"682cb7226054642344fc1a7a95fc016b8240f211dbf7ee3c8d07409fc213bb10","schema_version":"1.0","event_id":"sha256:682cb7226054642344fc1a7a95fc016b8240f211dbf7ee3c8d07409fc213bb10"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:YMQ4IL62WIPUY55GL2L275OVNX","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/P16-1159) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu. 2016. Minimum Risk Training for Neural Machine Translation. InProceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1:","arxiv_id":"2607.26427","detector":"doi_compliance","evidence":{"ref_index":41,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/p16-","reconstructed_doi":"10.18653/v1/P16-1159"},"severity":"advisory","ref_index":41,"audited_at":"2026-08-01T16:19:29.319262Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/P16-1159","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"15be8fd550d9363d83f14ff1b65d9a90dad7a379bd77d5b719f6d38b06ba6232","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":16166,"payload_sha256":"8c07f0ed5b85e985c7cf0d61f7c484d82e59af40af921314707aea97849c29b9","signature_b64":"g/1AXA4j5YIJmEnvB0wMQKMuz4hC4pOK6Knxkj+8fPSzhrcjOBkTuwkD6cWyxOlR3bovPHyDQGsvbknuAsBGCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T16:23:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/lGK13YMABZM3/9gu0MCb8EhTP2/JpdzvH5qeRhoFUTSu/u1RC1KN1aq2OXQPhBTraXS7aXc37sto28/SkDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:27:52.511778Z"},"content_sha256":"3a03c0b3d5152aa8afb2a3f3798b84c678a7547e0b62b0cb070c30336120358b","schema_version":"1.0","event_id":"sha256:3a03c0b3d5152aa8afb2a3f3798b84c678a7547e0b62b0cb070c30336120358b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:YMQ4IL62WIPUY55GL2L275OVNX","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/V1/2024.NAACL-INDUSTRY.2) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Jie Ou, Yueming Chen, and Wenhong Tian. 2024. Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding. InProceedings of the 2024 Conference of the North American Chapter of the Association for Computational Lingu","arxiv_id":"2607.26427","detector":"doi_compliance","evidence":{"ref_index":32,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2024.naac","reconstructed_doi":"10.18653/V1/2024.NAACL-INDUSTRY.2"},"severity":"advisory","ref_index":32,"audited_at":"2026-08-01T16:19:29.319262Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/V1/2024.NAACL-INDUSTRY.2","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"0b68e7052c61fe21a4c046e10c2d6f9725d9d3538574cdc308e94a3bf58d0362","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":16165,"payload_sha256":"8da22c40fa8f6825796f3c7a3c01003a8c687933761df2967462b8535a97a960","signature_b64":"s60Jc8nXlzqKMJzswQ+4aM0uoBGXWIAkrXMTH1gJjMkymN9+n1gS/wh3Q4aJ3ymZMS4y82TCyst7K/h5LHyaDw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T16:23:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FG50LrrWQnRTk3MeUtCvGqFEL06ho+6yMFdkhvefl4AJVhdeoNHCInB3E6fEJxV9z4vohl1f2tthhnM1krGRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:27:52.512152Z"},"content_sha256":"c15630ace609979310aea0524b86ba25904ac6c43082acf6b4c5c829849df7bb","schema_version":"1.0","event_id":"sha256:c15630ace609979310aea0524b86ba25904ac6c43082acf6b4c5c829849df7bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YMQ4IL62WIPUY55GL2L275OVNX/bundle.json","state_url":"https://pith.science/pith/YMQ4IL62WIPUY55GL2L275OVNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YMQ4IL62WIPUY55GL2L275OVNX/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":"2026-08-06T11:27:52Z","links":{"resolver":"https://pith.science/pith/YMQ4IL62WIPUY55GL2L275OVNX","bundle":"https://pith.science/pith/YMQ4IL62WIPUY55GL2L275OVNX/bundle.json","state":"https://pith.science/pith/YMQ4IL62WIPUY55GL2L275OVNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YMQ4IL62WIPUY55GL2L275OVNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YMQ4IL62WIPUY55GL2L275OVNX","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c059f8a0ffae38715933cb4be7d2b0dc66a845dbc7419c7e533585163083aef1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T03:14:09Z","title_canon_sha256":"6d8c6dfe2411192da0abddfcf5ccbd67c997af4c231c002e29ae7d6754d15e31"},"schema_version":"1.0","source":{"id":"2607.26427","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26427","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26427v1","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26427","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"YMQ4IL62WIPU","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"YMQ4IL62WIPUY55G","created_at":"2026-07-30T01:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"YMQ4IL62","created_at":"2026-07-30T01:18:23Z"}],"graph_snapshots":[{"event_id":"sha256:682cb7226054642344fc1a7a95fc016b8240f211dbf7ee3c8d07409fc213bb10","target":"graph","created_at":"2026-07-30T01:18:23Z","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/2607.26427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern recommender systems adopt Generator-Evaluator (G-E) for list-wise reranking: a generator produces sequences from candidates and an evaluator scores them at sequence-level to filter out the optimal one for exposure. Auto-Regressive(AR), working as the backbone for generative recommendation, suffers two limitations. First, its complexity grows linearly with list length, forcing the system to generate fewer lists under rigorous latency constraints and thus limiting exploration. Second, teacher-forcing creates a train-test mismatch; cumulative errors worsen with length and degrade quality.\n","authors_text":"Chao Feng, Chenghao Zhang, Li Ma, Xiancheng Gao, Xiang Li, Yuanhao Pu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T03:14:09Z","title":"PSG: Pair-Space Generation for Efficient Generative Reranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26427","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:eda687c6605a15a034cb4a16d228d9b1750efa0306a5a47f2113b016016a28b8","target":"record","created_at":"2026-07-30T01:18:23Z","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":"c059f8a0ffae38715933cb4be7d2b0dc66a845dbc7419c7e533585163083aef1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T03:14:09Z","title_canon_sha256":"6d8c6dfe2411192da0abddfcf5ccbd67c997af4c231c002e29ae7d6754d15e31"},"schema_version":"1.0","source":{"id":"2607.26427","kind":"arxiv","version":1}},"canonical_sha256":"c321c42fdab21f4c77a65e97aff5d56ddfcf9c077c7816a88630153b9e5c18f8","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c321c42fdab21f4c77a65e97aff5d56ddfcf9c077c7816a88630153b9e5c18f8","first_computed_at":"2026-07-30T01:18:23.859478Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:18:23.859478Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26427","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:3a03c0b3d5152aa8afb2a3f3798b84c678a7547e0b62b0cb070c30336120358b","sha256:c15630ace609979310aea0524b86ba25904ac6c43082acf6b4c5c829849df7bb"]}],"invalid_events":[],"applied_event_ids":["sha256:eda687c6605a15a034cb4a16d228d9b1750efa0306a5a47f2113b016016a28b8","sha256:682cb7226054642344fc1a7a95fc016b8240f211dbf7ee3c8d07409fc213bb10"],"state_sha256":"de46bc5e6f04a09d909bc73cb4d0250a0f2080d3cba75048344cdcfc18afd195"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jYudJQJCmwU7YtlH90aMD+a5kWCm3Z+HZJPWbixg7lRJ/lqRkqaLu0K/8NuZifHUBNhajPlSUqhprL3XW2LHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:27:52.514573Z","bundle_sha256":"83d9b5b9926edaa7111a76e7ec4f4f7af920097a2d4f6a2b16309e66af270817"}}