{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HQQNQWHDORSYWL2EIP6YT2DDEP","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":"ad031f05253cef25c0c466f408aaa119fe9427670114945c2f3891d45eff1e60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T08:39:07Z","title_canon_sha256":"e1993349a11b56c30936faf3a57346f78935a4413035fe176e3c257696e209fb"},"schema_version":"1.0","source":{"id":"2508.04206","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04206","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04206v1","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04206","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_12","alias_value":"HQQNQWHDORSY","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_16","alias_value":"HQQNQWHDORSYWL2E","created_at":"2026-07-05T11:49:22Z"},{"alias_kind":"pith_short_8","alias_value":"HQQNQWHD","created_at":"2026-07-05T11:49:22Z"}],"graph_snapshots":[{"event_id":"sha256:b0e5a39f7338b12ff1a86900492d5801a6a5d8c628f20562cc1fce937fdc07a4","target":"graph","created_at":"2026-07-05T11:49:22Z","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/2508.04206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recommending long-form video content demands joint modeling of visual, audio, and textual modalities, yet most benchmarks address only raw features or narrow fusion. We present ViLLA-MMBench, a reproducible, extensible benchmark for LLM-augmented multimodal movie recommendation. Built on MovieLens and MMTF-14K, it aligns dense item embeddings from three modalities: audio (block-level, i-vector), visual (CNN, AVF), and text. Missing or sparse metadata is automatically enriched using state-of-the-art LLMs (e.g., OpenAI Ada), generating high-quality synopses for thousands of movies. All text (raw","authors_text":"Ali Tourani, Fatemeh Nazary, Tommaso Di Noia, Yashar Deldjoo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T08:39:07Z","title":"ViLLA-MMBench: A Unified Benchmark Suite for LLM-Augmented Multimodal Movie Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04206","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":"sha256:5f1297a7ccc056968a44b6bad5103bcea806f78fb13bb52cce2e94aaceff2efc","target":"record","created_at":"2026-07-05T11:49:22Z","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":"ad031f05253cef25c0c466f408aaa119fe9427670114945c2f3891d45eff1e60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T08:39:07Z","title_canon_sha256":"e1993349a11b56c30936faf3a57346f78935a4413035fe176e3c257696e209fb"},"schema_version":"1.0","source":{"id":"2508.04206","kind":"arxiv","version":1}},"canonical_sha256":"3c20d858e374658b2f4443fd89e86323da7aac2409c2f818b3b8db470be8dda7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c20d858e374658b2f4443fd89e86323da7aac2409c2f818b3b8db470be8dda7","first_computed_at":"2026-07-05T11:49:22.776917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:22.776917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nxmRZ0u34g6JN7/gq0iRTZSB5Va59SoTQD1nwHfUKBomdYVfOoLGS9BwWKGgpATWHxvaKjFxpp08ro6WYmfBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:22.777408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04206","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f1297a7ccc056968a44b6bad5103bcea806f78fb13bb52cce2e94aaceff2efc","sha256:b0e5a39f7338b12ff1a86900492d5801a6a5d8c628f20562cc1fce937fdc07a4"],"state_sha256":"42503bc204ec00da597c3d024e8d933c633bd3a1f5c744f198cad10b96dec5e5"}