{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5R6UIZRG7ADDGP3D3SSRYSSU4J","short_pith_number":"pith:5R6UIZRG","schema_version":"1.0","canonical_sha256":"ec7d446626f806333f63dca51c4a54e255b32ee06a6c5f0c3dffc1d144549018","source":{"kind":"arxiv","id":"2309.15379","version":1},"attestation_state":"computed","paper":{"title":"A Content-Driven Micro-Video Recommendation Dataset at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fajie Yuan, Junchen Fu, Xiangnan He, Xiangyan Liu, Yongfeng Zhang, Yongxin Ni, Youhua Li, Yu Cheng","submitted_at":"2023-09-27T03:15:52Z","abstract_excerpt":"Micro-videos have recently gained immense popularity, sparking critical research in micro-video recommendation with significant implications for the entertainment, advertising, and e-commerce industries. However, the lack of large-scale public micro-video datasets poses a major challenge for developing effective recommender systems. To address this challenge, we introduce a very large micro-video recommendation dataset, named \"MicroLens\", consisting of one billion user-item interaction behaviors, 34 million users, and one million micro-videos. This dataset also contains various raw modality in"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.15379","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-09-27T03:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"9b49fc30308398d7d41894f16648b2d63565f8b11be1050cc41b09179b2e3c76","abstract_canon_sha256":"f56e2d4a88efba34cf233635a6459bfb53b6663fb75c876255ea2f6bd9c3e7b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:45.134694Z","signature_b64":"jULvMZykqKwWinnhAk5M4ElmOQ+yWOA8+q8QhVqUgDLNslXuY7m3O8GG+eeuG2LvJ+aKPgATYdxeZL+4ErlQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec7d446626f806333f63dca51c4a54e255b32ee06a6c5f0c3dffc1d144549018","last_reissued_at":"2026-07-05T06:54:45.134201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:45.134201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Content-Driven Micro-Video Recommendation Dataset at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fajie Yuan, Junchen Fu, Xiangnan He, Xiangyan Liu, Yongfeng Zhang, Yongxin Ni, Youhua Li, Yu Cheng","submitted_at":"2023-09-27T03:15:52Z","abstract_excerpt":"Micro-videos have recently gained immense popularity, sparking critical research in micro-video recommendation with significant implications for the entertainment, advertising, and e-commerce industries. However, the lack of large-scale public micro-video datasets poses a major challenge for developing effective recommender systems. To address this challenge, we introduce a very large micro-video recommendation dataset, named \"MicroLens\", consisting of one billion user-item interaction behaviors, 34 million users, and one million micro-videos. This dataset also contains various raw modality in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15379","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/2309.15379/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.15379","created_at":"2026-07-05T06:54:45.134260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15379v1","created_at":"2026-07-05T06:54:45.134260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15379","created_at":"2026-07-05T06:54:45.134260+00:00"},{"alias_kind":"pith_short_12","alias_value":"5R6UIZRG7ADD","created_at":"2026-07-05T06:54:45.134260+00:00"},{"alias_kind":"pith_short_16","alias_value":"5R6UIZRG7ADDGP3D","created_at":"2026-07-05T06:54:45.134260+00:00"},{"alias_kind":"pith_short_8","alias_value":"5R6UIZRG","created_at":"2026-07-05T06:54:45.134260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09595","citing_title":"Popcorn: A Configurable Benchmark for Visual Evidence in Multimodal Movie Recommendation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2403.03952","citing_title":"Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18653","citing_title":"Will It Go Viral? Grounding Micro-Video Popularity Prediction on the Open Web","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18740","citing_title":"Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26252","citing_title":"OmniTrend: Content-Context Modeling for Scalable Social Popularity Prediction","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12990","citing_title":"Sparse Contrastive Learning for Content-Based Cold Item Recommendation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J","json":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J.json","graph_json":"https://pith.science/api/pith-number/5R6UIZRG7ADDGP3D3SSRYSSU4J/graph.json","events_json":"https://pith.science/api/pith-number/5R6UIZRG7ADDGP3D3SSRYSSU4J/events.json","paper":"https://pith.science/paper/5R6UIZRG"},"agent_actions":{"view_html":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J","download_json":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J.json","view_paper":"https://pith.science/paper/5R6UIZRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15379&json=true","fetch_graph":"https://pith.science/api/pith-number/5R6UIZRG7ADDGP3D3SSRYSSU4J/graph.json","fetch_events":"https://pith.science/api/pith-number/5R6UIZRG7ADDGP3D3SSRYSSU4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J/action/storage_attestation","attest_author":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J/action/author_attestation","sign_citation":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J/action/citation_signature","submit_replication":"https://pith.science/pith/5R6UIZRG7ADDGP3D3SSRYSSU4J/action/replication_record"}},"created_at":"2026-07-05T06:54:45.134260+00:00","updated_at":"2026-07-05T06:54:45.134260+00:00"}