{"paper":{"id":"2609.00057.pdf","title":"ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation","authors":["Yitong Han","Wei Gao","Yi Zhao","Prasanta Bhattacharya","Fengzhu Zeng","Mohammad Amanlou"],"arxiv_id":"","url":"","source_kind":"pdf","ir_version":"1.0"},"generated_at":"2026-09-14T04:10:45.107076+00:00","counts":{"error":0,"warning":0,"info":0},"findings":[],"top_findings":[],"ir_summary":{"claims":21,"contributions":4,"method_components":10,"experiments":3,"baselines":13,"datasets":10,"metrics":6,"tables":8,"figures":3,"citations":69,"equations":0,"quantitative_results":474,"has_repository":false},"ir_health":{"observations":[{"code":"ablation-labels-match-nothing","severity":"warning","message":"None of the experiment ablation labels match any method component.","detail":"Labels found: 'Only Stage 1'. Either the components were extracted with different wording, or these labels are baselines rather than ablations — in which case RL004 has no evidence that anything was ablated."},{"code":"numbers-are-identifier-fragments","severity":"warning","message":"17 of 474 extracted numbers (4%) are digits inside identifiers, not measurements.","detail":"e.g. '1' in 'Task\\nModel/dataset\\nConfiguration\\nAccurac', '1' in 'Task\\nModel/dataset\\nConfiguration\\nAccurac', '1' in 'Task\\nModel/dataset\\nConfiguration\\nAccurac'. Rules that compare numbers across sections can report a contradiction between an identifier and a real value."},{"code":"compile-warning","severity":"note","message":"references: the reference list carries no entry numbers; citation keys are enumeration order [1]..[N], not labels printed in the paper, so a key may not match the [N] used in the body","detail":""},{"code":"compile-warning","severity":"note","message":"semantic extraction: dropped 1 items whose quote was not found in the paper","detail":""}],"errors":0,"warnings":2,"trustworthy":true},"diagnostics":{"source":"/home/oceann/workspace/research-linter/eval/papers/2609.00057.pdf","rules_run":["RL001","RL002","RL003","RL004","RL005"],"rules_skipped":[],"rule_errors":{},"rule_findings":{"RL001":0,"RL002":0,"RL003":0,"RL004":0,"RL005":0},"rule_seconds":{"RL001":0.01,"RL002":0.81,"RL003":1.27,"RL004":0.66,"RL005":0.18},"dropped_no_evidence":0,"demoted_low_confidence":0,"ir_health":{"observations":[{"code":"ablation-labels-match-nothing","severity":"warning","message":"None of the experiment ablation labels match any method component.","detail":"Labels found: 'Only Stage 1'. Either the components were extracted with different wording, or these labels are baselines rather than ablations — in which case RL004 has no evidence that anything was ablated."},{"code":"numbers-are-identifier-fragments","severity":"warning","message":"17 of 474 extracted numbers (4%) are digits inside identifiers, not measurements.","detail":"e.g. '1' in 'Task\\nModel/dataset\\nConfiguration\\nAccurac', '1' in 'Task\\nModel/dataset\\nConfiguration\\nAccurac', '1' in 'Task\\nModel/dataset\\nConfiguration\\nAccurac'. Rules that compare numbers across sections can report a contradiction between an identifier and a real value."},{"code":"compile-warning","severity":"note","message":"references: the reference list carries no entry numbers; citation keys are enumeration order [1]..[N], not labels printed in the paper, so a key may not match the [N] used in the body","detail":""},{"code":"compile-warning","severity":"note","message":"semantic extraction: dropped 1 items whose quote was not found in the paper","detail":""}],"errors":0,"warnings":2,"trustworthy":true},"notes":["RL001 funnel arithmetic: sentences_with_from=2 endpoint_pairs=0 claims_compared=0 emitted=0 [dropped: not-a-measurement=0]","RL001 funnel delta-column: structured_tables=6 with_exactly_one_delta_column=0 rows_checked=0 emitted=0","RL001 funnel cross-location: quant=474 prose=139 prose_with_metric=44 prose_with_dataset=0 prose_with_metric_and_dataset=0 distinct_buckets=0 emitted=0 [dropped: not-a-measurement=1 not-in-quote=20]","RL001 funnel identifier-drift: settings_checked=2 sections_stating_one_value=1 emitted=0","RL002 citation entailment: attempted 1 of 1 ranked cited claims (2 in-text markers from 69 bibliography entries); 0 cited works could not be identified, 1 had no retrievable text, 0 model quotes failed verbatim verification, 0 were topically unrelated to the retrieved text.","RL002 candidate ranking (why the top 1 were chosen): [1] [unknown, title/sentence overlap near zero, no DOI/arXiv id]","RL002: 1 markers skipped because the claim is jointly attributed to several works","RL003: 3 queries -> 124 unique works (arXiv search 50, category listings 0, scholarly graph 74 [crossref 74], 0 graph works matched to an arXiv id); source errors during retrieval: arXiv 0, graph 0","RL003: parsed the reference list of 10/12 comparable papers (2 unreadable) — that is the PeerUsage denominator","RL003: enriched 1 of 3 candidates with their own abstract (2 unavailable, 0 over budget); 0 dropped as published after this paper","RL003: scholarly graph for this run = crossref","RL003 funnel (485 candidates): cited_only_from_related_work -135, is_a_dataset -1, peer_usage_below_quorum -107, survey_or_artifact -42, title_names_no_method -197 || kept: citation_context_unknown +46 || survived-cheap-gates 3 -> with-abstract 1 -> comparable 3 -> above-threshold-0.65 0","RL003 candidate: 'PointCLIP v2' score 0.229 (T 0.00 D 0.00 M 0.67 P 0.30 R 0.71; 3/10 peers cite it; title-only, no abstract available) -> not reported","RL003 candidate: 'Ulip' score 0.229 (T 0.00 D 0.00 M 0.67 P 0.30 R 0.71; 3/10 peers cite it; title-only, no abstract available) -> not reported","RL003 candidate: 'Decoupled weight decay regularization' score 0.213 (T 0.00 D 0.00 M 0.67 P 0.40 R 0.00; 4/10 peers cite it) -> not reported","RL003: 3 comparable candidates all scored below 0.65 — nothing to report for this paper","RL004 funnel: components=10 contribution_backed=3 candidates=2 ablations_found=3 matched_by_ablation=2 unmatched=0 experiments=3","RL004 unresolved label(s): 'Only Stage 1' — names no single component, so it was not used as evidence","RL004 component M1 'ValueGraph': covered (filtered earlier)","RL004 component M2 'hierarchical contrastive learning framework': excluded:is-the-whole-method","RL004 component M3 'User-level contrastive loss Luser': covered (candidate)","RL004 component M4 'Clustering loss Lcls': covered (candidate)","RL004 component M5 'masked graph autoencoding paradigm of GraphMAE2': excluded:not-a-claimed-contribution","RL004 component M6 'ModernBERT': excluded:not-a-claimed-contribution","RL004 component M7 'MoralBERT': excluded:not-a-claimed-contribution","RL004 component M8 'symmetric percentile-based strategy': excluded:not-a-claimed-contribution","RL004 component M9 'Gaussian radial basis function kernel': excluded:not-a-claimed-contribution","RL004 component M10 'K-means clustering': excluded:not-a-claimed-contribution","RL004 funnel: ranked=0 emitted=0 suppressed_by_cap=0 dropped_unverified_quote=0","RL005: https://github.com/HanYiton/ValueGraph — read 30 files, 5 canonical params, 5 paper claims, 0 mismatches"],"missing_core_rules":[],"seconds":33.43,"llm":{"calls":0,"cache_hits":2,"errors":0,"prompt_chars":0},"sources":{"arxiv":{"requests":0,"errors":0,"cache_hits":30,"available":1},"openalex":{"requests":1,"errors":0,"cache_hits":0,"available":0,"unavailable_reason":"OpenAlex free daily budget exhausted (resets midnight UTC)"},"crossref":{"requests":0,"errors":0,"cache_hits":6,"available":1},"s2":{"requests":0,"errors":0,"cache_hits":0,"available":1},"short_circuited":["crossref","openalex","s2"]},"cache":{"hits":38,"misses":1}},"compile_warnings":["references: the reference list carries no entry numbers; citation keys are enumeration order [1]..[N], not labels printed in the paper, so a key may not match the [N] used in the body","semantic extraction: dropped 1 items whose quote was not found in the paper"]}