{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5AWDU6EM2CFO47CKZKYSUB4QRB","short_pith_number":"pith:5AWDU6EM","canonical_record":{"source":{"id":"2602.07298","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-07T01:15:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5af7a7c202ba47d336c8e0745983b95e7b2cbf8dcf0cc15d6f8cdf491441c8f0","abstract_canon_sha256":"3821f9b04509a6f009778913c7089a7514b780772127f946f98704bf39eab4b6"},"schema_version":"1.0"},"canonical_sha256":"e82c3a788cd08aee7c4acab12a07908861c98cfa80accbf2d337960978a7c010","source":{"kind":"arxiv","id":"2602.07298","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07298","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07298v3","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07298","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"5AWDU6EM2CFO","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"5AWDU6EM2CFO47CK","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"5AWDU6EM","created_at":"2026-06-02T02:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5AWDU6EM2CFO47CKZKYSUB4QRB","target":"record","payload":{"canonical_record":{"source":{"id":"2602.07298","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-07T01:15:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5af7a7c202ba47d336c8e0745983b95e7b2cbf8dcf0cc15d6f8cdf491441c8f0","abstract_canon_sha256":"3821f9b04509a6f009778913c7089a7514b780772127f946f98704bf39eab4b6"},"schema_version":"1.0"},"canonical_sha256":"e82c3a788cd08aee7c4acab12a07908861c98cfa80accbf2d337960978a7c010","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:14.247819Z","signature_b64":"2vLQdNcaoUSPWoKw/iIGjHFcSFelWFgTjhICk8ua9pCrjfNfux/2i9fmoE/4Fe2Sx1PghEFfzbkji8UVoO65CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e82c3a788cd08aee7c4acab12a07908861c98cfa80accbf2d337960978a7c010","last_reissued_at":"2026-06-02T02:04:14.247293Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:14.247293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.07298","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5s6tapobsaUjcJn5NXBkzjudzEXChh/k02hQY37UR6O9WT012XVT5ZIyBerVUmAf0kiLyjC4lj9Q3WQWQHvKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:57:55.074388Z"},"content_sha256":"ce0b2825630e4cd178111e20ae2457ebadb5178bd2fe7553a1f43781453fceb2","schema_version":"1.0","event_id":"sha256:ce0b2825630e4cd178111e20ae2457ebadb5178bd2fe7553a1f43781453fceb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5AWDU6EM2CFO47CKZKYSUB4QRB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Benyu Zhang, Hong Yan, Hong-You Chen, Jiahao Wu, Jia Li, Jianpeng Cheng, Neeraj Bhatia, Qiang Zhang, Qifei Wang, Qunshu Zhang, Shen Li, Wei Sun, Xiangjun Fan","submitted_at":"2026-02-07T01:15:15Z","abstract_excerpt":"Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing resource allocation. We hypothesize that this may be attributed to the inherent noise, bias, and incompleteness of raw user interaction data in prior continual pre-training (CPT) efforts. This paper introduces a novel, layered framework for generating high-quality synthetic data that circumvents such issues by creating a curated, pedagogical curriculum for the LLM. We provide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07298","kind":"arxiv","version":3},"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/2602.07298/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":"2026-06-02T02:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4c8DfWS/AcV56bKjRQRTmbwcMhinRLwsbFwEONbtONxYr5j+PtaBtqeiiDYte4q+VSVKtP/JACMmpBc0JNwWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:57:55.074766Z"},"content_sha256":"9b700952134ce39f1689f51b64fa249f8d03b634eff8bf69c39c6f8952b1c521","schema_version":"1.0","event_id":"sha256:9b700952134ce39f1689f51b64fa249f8d03b634eff8bf69c39c6f8952b1c521"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5AWDU6EM2CFO47CKZKYSUB4QRB/bundle.json","state_url":"https://pith.science/pith/5AWDU6EM2CFO47CKZKYSUB4QRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5AWDU6EM2CFO47CKZKYSUB4QRB/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":"2026-06-03T20:57:55Z","links":{"resolver":"https://pith.science/pith/5AWDU6EM2CFO47CKZKYSUB4QRB","bundle":"https://pith.science/pith/5AWDU6EM2CFO47CKZKYSUB4QRB/bundle.json","state":"https://pith.science/pith/5AWDU6EM2CFO47CKZKYSUB4QRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5AWDU6EM2CFO47CKZKYSUB4QRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5AWDU6EM2CFO47CKZKYSUB4QRB","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":"3821f9b04509a6f009778913c7089a7514b780772127f946f98704bf39eab4b6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-07T01:15:15Z","title_canon_sha256":"5af7a7c202ba47d336c8e0745983b95e7b2cbf8dcf0cc15d6f8cdf491441c8f0"},"schema_version":"1.0","source":{"id":"2602.07298","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07298","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07298v3","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07298","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"5AWDU6EM2CFO","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"5AWDU6EM2CFO47CK","created_at":"2026-06-02T02:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"5AWDU6EM","created_at":"2026-06-02T02:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:9b700952134ce39f1689f51b64fa249f8d03b634eff8bf69c39c6f8952b1c521","target":"graph","created_at":"2026-06-02T02:04:14Z","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/2602.07298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing resource allocation. We hypothesize that this may be attributed to the inherent noise, bias, and incompleteness of raw user interaction data in prior continual pre-training (CPT) efforts. This paper introduces a novel, layered framework for generating high-quality synthetic data that circumvents such issues by creating a curated, pedagogical curriculum for the LLM. We provide","authors_text":"Benyu Zhang, Hong Yan, Hong-You Chen, Jiahao Wu, Jia Li, Jianpeng Cheng, Neeraj Bhatia, Qiang Zhang, Qifei Wang, Qunshu Zhang, Shen Li, Wei Sun, Xiangjun Fan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-07T01:15:15Z","title":"Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07298","kind":"arxiv","version":3},"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:ce0b2825630e4cd178111e20ae2457ebadb5178bd2fe7553a1f43781453fceb2","target":"record","created_at":"2026-06-02T02:04:14Z","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":"3821f9b04509a6f009778913c7089a7514b780772127f946f98704bf39eab4b6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-07T01:15:15Z","title_canon_sha256":"5af7a7c202ba47d336c8e0745983b95e7b2cbf8dcf0cc15d6f8cdf491441c8f0"},"schema_version":"1.0","source":{"id":"2602.07298","kind":"arxiv","version":3}},"canonical_sha256":"e82c3a788cd08aee7c4acab12a07908861c98cfa80accbf2d337960978a7c010","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e82c3a788cd08aee7c4acab12a07908861c98cfa80accbf2d337960978a7c010","first_computed_at":"2026-06-02T02:04:14.247293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:14.247293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2vLQdNcaoUSPWoKw/iIGjHFcSFelWFgTjhICk8ua9pCrjfNfux/2i9fmoE/4Fe2Sx1PghEFfzbkji8UVoO65CA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:14.247819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.07298","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce0b2825630e4cd178111e20ae2457ebadb5178bd2fe7553a1f43781453fceb2","sha256:9b700952134ce39f1689f51b64fa249f8d03b634eff8bf69c39c6f8952b1c521"],"state_sha256":"b6c017c8cb72e9b6a23b8db51e56ceb09b9f3e6972ff78a52335fa0f9a8a7ddb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AK00hV6SHzBGOb6zY9nTQB4WcvG0FhqCmZ+KSMZUTareX64J4GwduEPYfl1MGarINcOpqjdQ/BfoswYAHFOjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:57:55.076737Z","bundle_sha256":"6fd9ff9022567dc6d317c5508fec435c827f074f494c9d1abd1bed414a775a60"}}