{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XLOQYE3VL7B5TPEPADSHLOATBE","short_pith_number":"pith:XLOQYE3V","canonical_record":{"source":{"id":"2608.10447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T04:01:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0acf9f54aa2636475bb8c9b5c3944a79fbe5251039de339449e7856d556e2b69","abstract_canon_sha256":"2356c05164df067d1f46fedf71a69b6c607a18bc92bda14c29c4cd0c84d6b602"},"schema_version":"1.0"},"canonical_sha256":"badd0c13755fc3d9bc8f00e475b813091091764b78842b04194e177a7ed0ed9e","source":{"kind":"arxiv","id":"2608.10447","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10447","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10447v1","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10447","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"XLOQYE3VL7B5","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"XLOQYE3VL7B5TPEP","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"XLOQYE3V","created_at":"2026-08-12T01:22:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XLOQYE3VL7B5TPEPADSHLOATBE","target":"record","payload":{"canonical_record":{"source":{"id":"2608.10447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T04:01:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0acf9f54aa2636475bb8c9b5c3944a79fbe5251039de339449e7856d556e2b69","abstract_canon_sha256":"2356c05164df067d1f46fedf71a69b6c607a18bc92bda14c29c4cd0c84d6b602"},"schema_version":"1.0"},"canonical_sha256":"badd0c13755fc3d9bc8f00e475b813091091764b78842b04194e177a7ed0ed9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:22:29.176378Z","signature_b64":"h801bex+spd1ur84FhwEw1/ted5p9bibVcF6S0/EakdHxpuTfn++cRf7tUpAvjs+p3BA2gCV/fm6vLJBk14WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"badd0c13755fc3d9bc8f00e475b813091091764b78842b04194e177a7ed0ed9e","last_reissued_at":"2026-08-12T01:22:29.174815Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:22:29.174815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.10447","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":"2026-08-12T01:22:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2mHaX/moUSYoMPQ+wRQ0hugjTk5e5ZhydKNwQT01lDHXCi8W3+XqndhcqyrzFPNtF7wIl/6S25/QNjhXqBBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T04:11:31.124720Z"},"content_sha256":"97505f8f3181674c17c5ad28b884782a1a27114e5d683ddc541d2fde01a7ec64","schema_version":"1.0","event_id":"sha256:97505f8f3181674c17c5ad28b884782a1a27114e5d683ddc541d2fde01a7ec64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XLOQYE3VL7B5TPEPADSHLOATBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Hongzhi Yin, Junliang Yu, Linh Dieu Le, Ming Jin, Shazia Sadiq, Tong Chen","submitted_at":"2026-08-11T04:01:35Z","abstract_excerpt":"Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly. However, their reasoning traces are often unnecessarily verbose, increasing inference costs without commensurate accuracy gains. Existing training-based approaches to reasoning compression often incur substantial adaptation costs, while inference-time methods are brittle and difficult to scale. These limitations motivate model merging as a promising training-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10447","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/2608.10447/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":"2026-08-12T01:22:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YevZIjduEb1Wd6eZv2natg6DW5elaA+UUcr782g0fead03LxA1+hSf2lmbiWyxWP2JsJBSmkiSdk7URlCrBYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T04:11:31.125232Z"},"content_sha256":"86310c83621c1aa1f7e81f32278162588379b838a13d40bf524054fc1fc32783","schema_version":"1.0","event_id":"sha256:86310c83621c1aa1f7e81f32278162588379b838a13d40bf524054fc1fc32783"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:XLOQYE3VL7B5TPEPADSHLOATBE","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/978-3-031-88708-6_27) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Zixuan Yi and Iadh Ounis. 2025. A Multi-modal Recipe for Improved Multi- domain Recommendation. InAdvances in Information Retrieval (ECIR 2025) (Lucca, Italy). Springer-Verlag, Berlin, Heidelberg, 421–436. doi:10.1007/978- 3-031-88708-6_27","arxiv_id":"2608.10447","detector":"doi_compliance","evidence":{"ref_index":51,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1007/978-","reconstructed_doi":"10.1007/978-3-031-88708-6_27"},"severity":"advisory","ref_index":51,"audited_at":"2026-08-15T14:39:47.004457Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/978-3-031-88708-6_27","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"d3ccb288ce17e970160c403fc01673d0e89c0ac7aa259ef1836ef2a6faf753b6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19866,"payload_sha256":"fe2df3d693539c724698eabf50ca810b4701ba9b05f33ccfb66bcc017227263b","signature_b64":"dmjN2UL65tPbSmXXjNAshBNfG+gwRDyf0mQhTrQTKE0QQ+sDZlShdrlUpjxZY6YbgjkPuPkhGjtNWiLeMPhDCQ==","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":"2026-08-15T14:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6b7Gak+H6szGn377JoL/xnhS0OQhfStgaNHoyLR6T6Lh54Ju9yj/yZzPPDRqVewr5pn/7Xo3gPfub0vurGXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T04:11:31.129924Z"},"content_sha256":"2f37897b8dfc244c2f079b06775a9b545091ac5b8e39efb2714a0ba61faa49c4","schema_version":"1.0","event_id":"sha256:2f37897b8dfc244c2f079b06775a9b545091ac5b8e39efb2714a0ba61faa49c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLOQYE3VL7B5TPEPADSHLOATBE/bundle.json","state_url":"https://pith.science/pith/XLOQYE3VL7B5TPEPADSHLOATBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLOQYE3VL7B5TPEPADSHLOATBE/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":"2026-08-16T04:11:31Z","links":{"resolver":"https://pith.science/pith/XLOQYE3VL7B5TPEPADSHLOATBE","bundle":"https://pith.science/pith/XLOQYE3VL7B5TPEPADSHLOATBE/bundle.json","state":"https://pith.science/pith/XLOQYE3VL7B5TPEPADSHLOATBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLOQYE3VL7B5TPEPADSHLOATBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XLOQYE3VL7B5TPEPADSHLOATBE","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2356c05164df067d1f46fedf71a69b6c607a18bc92bda14c29c4cd0c84d6b602","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T04:01:35Z","title_canon_sha256":"0acf9f54aa2636475bb8c9b5c3944a79fbe5251039de339449e7856d556e2b69"},"schema_version":"1.0","source":{"id":"2608.10447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10447","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10447v1","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10447","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"XLOQYE3VL7B5","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"XLOQYE3VL7B5TPEP","created_at":"2026-08-12T01:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"XLOQYE3V","created_at":"2026-08-12T01:22:29Z"}],"graph_snapshots":[{"event_id":"sha256:86310c83621c1aa1f7e81f32278162588379b838a13d40bf524054fc1fc32783","target":"graph","created_at":"2026-08-12T01:22:29Z","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/2608.10447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly. However, their reasoning traces are often unnecessarily verbose, increasing inference costs without commensurate accuracy gains. Existing training-based approaches to reasoning compression often incur substantial adaptation costs, while inference-time methods are brittle and difficult to scale. These limitations motivate model merging as a promising training-","authors_text":"Hongzhi Yin, Junliang Yu, Linh Dieu Le, Ming Jin, Shazia Sadiq, Tong Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T04:01:35Z","title":"Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10447","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":"sha256:97505f8f3181674c17c5ad28b884782a1a27114e5d683ddc541d2fde01a7ec64","target":"record","created_at":"2026-08-12T01:22:29Z","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":"2356c05164df067d1f46fedf71a69b6c607a18bc92bda14c29c4cd0c84d6b602","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T04:01:35Z","title_canon_sha256":"0acf9f54aa2636475bb8c9b5c3944a79fbe5251039de339449e7856d556e2b69"},"schema_version":"1.0","source":{"id":"2608.10447","kind":"arxiv","version":1}},"canonical_sha256":"badd0c13755fc3d9bc8f00e475b813091091764b78842b04194e177a7ed0ed9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"badd0c13755fc3d9bc8f00e475b813091091764b78842b04194e177a7ed0ed9e","first_computed_at":"2026-08-12T01:22:29.174815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:22:29.174815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h801bex+spd1ur84FhwEw1/ted5p9bibVcF6S0/EakdHxpuTfn++cRf7tUpAvjs+p3BA2gCV/fm6vLJBk14WCA==","signature_status":"signed_v1","signed_at":"2026-08-12T01:22:29.176378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97505f8f3181674c17c5ad28b884782a1a27114e5d683ddc541d2fde01a7ec64","sha256:86310c83621c1aa1f7e81f32278162588379b838a13d40bf524054fc1fc32783","sha256:2f37897b8dfc244c2f079b06775a9b545091ac5b8e39efb2714a0ba61faa49c4"],"state_sha256":"ecbab00ca78d0790f84818849d6354c313eb7fc1e731ba65492c820626873194"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"91hejLLZnpK4sYuj7fhqzshtu/Vk3+t2aqK8RxMkUKzLIi1gvYFxOAv6oK/m374KKqFDctOg04i+CEbxQ4gpBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T04:11:31.132096Z","bundle_sha256":"e3a36ea0d97de27655c7e72d7e13d90b3fccbf81244d1f712a261df53487432a"}}