{"as_of":"2026-08-09T03:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:08b46de33408f662951b35beb0e43825a088e2af99db2b0f3c77d4b9caf05ada","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T05:30:26.134519Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T05:49:38.650237Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.12228","last_updated":"2025-02-16T09:41:32Z","snapshot_observed_at":"2026-08-07T23:46:27.609660Z","submitted_at":"2024-10-16T04:44:15Z","title":"Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12228","snapshot_observed_at":"2026-08-08T05:30:26.134519Z","title":"Triple modality fusion: Aligning visual, textual, and graph data with large language models for multi-behavior recom- mendations","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.08346","last_updated":"2025-02-17T02:47:18Z","snapshot_observed_at":"2026-08-08T05:25:30.248415Z","submitted_at":"2025-02-12T12:13:51Z","title":"Graph Foundation Models for Recommendation: A Comprehensive Survey","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T05:30:26.134519Z"},"links":{"cited_paper":"/paper/2410.12228","citing_paper":"/paper/2502.08346"},"observation_digest":"sha256:100b6c1d0ea360501d00c2a4a6db95a2491c46833311e70aebecdc909f05c213","observation_id":"103c9088-1dfa-47a1-a73f-fa808ad0ed39","resolution":{"observed_at":"2026-08-08T05:30:26.134519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12228","last_updated":"2025-02-16T09:41:32Z","snapshot_observed_at":"2026-08-07T23:46:27.609660Z","submitted_at":"2024-10-16T04:44:15Z","title":"Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12228","snapshot_observed_at":"2026-08-06T15:02:08.404945Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17080","last_updated":"2025-07-22T23:45:43Z","snapshot_observed_at":"2026-08-06T14:54:51.848171Z","submitted_at":"2025-07-22T23:45:43Z","title":"VL-CLIP: Enhancing Multimodal Recommendations via Visual Grounding and LLM-Augmented CLIP Embeddings","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T15:02:08.404945Z"},"links":{"cited_paper":"/paper/2410.12228","citing_paper":"/paper/2507.17080"},"observation_digest":"sha256:3375b9449a384177207d5da99e8f3aab07d35481b6207576d29cb762ffec53b1","observation_id":"8e825e7e-e9be-487c-92f5-f6d93eb75f15","resolution":{"observed_at":"2026-08-06T15:02:08.404945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12228","last_updated":"2025-02-16T09:41:32Z","snapshot_observed_at":"2026-08-07T23:46:27.609660Z","submitted_at":"2024-10-16T04:44:15Z","title":"Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations","version":2},"cited_work":{"arxiv_id":"2410.12228","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.12228","snapshot_observed_at":"2026-07-04T05:49:38.650237Z","title":"Class-imbalanced graph learning without class rebalancing","venue":null,"work_id":"6fd02d6c-e9eb-46a7-a02e-0c3dbe7bfa71","year":2014},"citing_paper":{"arxiv_id":"2606.20554","last_updated":"2026-06-18T17:58:32Z","snapshot_observed_at":"2026-08-05T10:43:45.053697Z","submitted_at":"2026-06-18T17:58:32Z","title":"Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-26T15:16:26.994672Z"},"links":{"cited_paper":"/paper/2410.12228","citing_paper":"/paper/2606.20554"},"observation_digest":"sha256:e1a28305ca606cf2aa847ee3b57224301d692ac756d09a20aec1eb858bbd68aa","observation_id":"3605cf0a-028a-4303-bdf1-77f84984fbd1","resolution":{"observed_at":"2026-07-04T05:49:38.652233Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.12228/citation-record","integrity":"/paper/2410.12228/integrity","json":"/paper/2410.12228/citation-record.json","paper":"/paper/2410.12228"},"outbound":[],"paper":{"arxiv_id":"2410.12228","last_updated":"2025-02-16T09:41:32Z","latest_version":2,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-07T23:46:27.609660Z","submitted_at":"2024-10-16T04:44:15Z","title":"Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2410.12228."}