{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y5UFQVW4HUOK6WA2MMMX4H35E5","short_pith_number":"pith:Y5UFQVW4","schema_version":"1.0","canonical_sha256":"c7685856dc3d1caf581a63197e1f7d274232b47aa4a63026421ace0126c20482","source":{"kind":"arxiv","id":"2504.08742","version":1},"attestation_state":"computed","paper":{"title":"Simulating Filter Bubble on Short-video Recommender System with Large Language Model Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chen Gao, Haoyu Wang, Nicholas Sukiennik, Yong Li, Zailin Zeng","submitted_at":"2025-03-23T10:35:58Z","abstract_excerpt":"An increasing reliance on recommender systems has led to concerns about the creation of filter bubbles on social media, especially on short video platforms like TikTok. However, their formation is still not entirely understood due to the complex dynamics between recommendation algorithms and user feedback. In this paper, we aim to shed light on these dynamics using a large language model-based simulation framework. Our work employs real-world short-video data containing rich video content information and detailed user-agents to realistically simulate the recommendation-feedback cycle. Through "},"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":"2504.08742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-23T10:35:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d187ec47d9fe554e8568b74995418098de377e00c6afe724491668892a3057a","abstract_canon_sha256":"0adeeeff0ef971730947ec521ff8a2664cb25ad9ef98793ad043c700217af1a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:58.349328Z","signature_b64":"haH/HfpBrwu1e6qB30i4w4cUNb4sX7rNZBijQbqSdCXiEI+PRz1iK4xLSGha2DZIMqPnmTXRuZIeKs1CB695Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7685856dc3d1caf581a63197e1f7d274232b47aa4a63026421ace0126c20482","last_reissued_at":"2026-07-05T10:47:58.348840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:58.348840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simulating Filter Bubble on Short-video Recommender System with Large Language Model Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chen Gao, Haoyu Wang, Nicholas Sukiennik, Yong Li, Zailin Zeng","submitted_at":"2025-03-23T10:35:58Z","abstract_excerpt":"An increasing reliance on recommender systems has led to concerns about the creation of filter bubbles on social media, especially on short video platforms like TikTok. However, their formation is still not entirely understood due to the complex dynamics between recommendation algorithms and user feedback. In this paper, we aim to shed light on these dynamics using a large language model-based simulation framework. Our work employs real-world short-video data containing rich video content information and detailed user-agents to realistically simulate the recommendation-feedback cycle. Through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08742","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/2504.08742/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":"2504.08742","created_at":"2026-07-05T10:47:58.348897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08742v1","created_at":"2026-07-05T10:47:58.348897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08742","created_at":"2026-07-05T10:47:58.348897+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5UFQVW4HUOK","created_at":"2026-07-05T10:47:58.348897+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5UFQVW4HUOK6WA2","created_at":"2026-07-05T10:47:58.348897+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5UFQVW4","created_at":"2026-07-05T10:47:58.348897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17707","citing_title":"Do Generative Recommenders Deepen the Information Cocoon? A Closed-Loop Simulation with LLM-powered User Simulators","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5","json":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5.json","graph_json":"https://pith.science/api/pith-number/Y5UFQVW4HUOK6WA2MMMX4H35E5/graph.json","events_json":"https://pith.science/api/pith-number/Y5UFQVW4HUOK6WA2MMMX4H35E5/events.json","paper":"https://pith.science/paper/Y5UFQVW4"},"agent_actions":{"view_html":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5","download_json":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5.json","view_paper":"https://pith.science/paper/Y5UFQVW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08742&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5UFQVW4HUOK6WA2MMMX4H35E5/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5UFQVW4HUOK6WA2MMMX4H35E5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5/action/storage_attestation","attest_author":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5/action/author_attestation","sign_citation":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5/action/citation_signature","submit_replication":"https://pith.science/pith/Y5UFQVW4HUOK6WA2MMMX4H35E5/action/replication_record"}},"created_at":"2026-07-05T10:47:58.348897+00:00","updated_at":"2026-07-05T10:47:58.348897+00:00"}