{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PDIUKVG76RDRLQP6W7U66IWVR","short_pith_number":"pith:3PDIUKVG","schema_version":"1.0","canonical_sha256":"dbc68a2aa6ffa238ae0ff5bf4f7916ac743a548362acc72a11e8d215bf156fb1","source":{"kind":"arxiv","id":"2405.05596","version":1},"attestation_state":"computed","paper":{"title":"Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.IR","cs.LG","stat.ME"],"primary_cat":"cs.CY","authors_text":"Aleksander Madry, Andrew Ilyas, Hannah Li, Jennifer Allen, Sarah H. Cen","submitted_at":"2024-05-09T07:36:08Z","abstract_excerpt":"Most modern recommendation algorithms are data-driven: they generate personalized recommendations by observing users' past behaviors. A common assumption in recommendation is that how a user interacts with a piece of content (e.g., whether they choose to \"like\" it) is a reflection of the content, but not of the algorithm that generated it. Although this assumption is convenient, it fails to capture user strategization: that users may attempt to shape their future recommendations by adapting their behavior to the recommendation algorithm. In this work, we test for user strategization by conduct"},"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":"2405.05596","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-09T07:36:08Z","cross_cats_sorted":["cs.HC","cs.IR","cs.LG","stat.ME"],"title_canon_sha256":"dcecac748b2e380673fffdf084ca3c2a3cf100514da1a98b0f3226ccd5dd6477","abstract_canon_sha256":"d43c8a11e322a0a8dc9e739549c3a09a47b696405bc0c09109404039172e73bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:26.006531Z","signature_b64":"GC/5FJMF0Sb4rx/Mj+qRdf6sdvRP2vEuCwpAP4BAOXg9YdQbNs0SfjMGHpAMZbcUqrSvSR6bdibokLiVbHMHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbc68a2aa6ffa238ae0ff5bf4f7916ac743a548362acc72a11e8d215bf156fb1","last_reissued_at":"2026-07-05T08:17:26.006080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:26.006080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.IR","cs.LG","stat.ME"],"primary_cat":"cs.CY","authors_text":"Aleksander Madry, Andrew Ilyas, Hannah Li, Jennifer Allen, Sarah H. Cen","submitted_at":"2024-05-09T07:36:08Z","abstract_excerpt":"Most modern recommendation algorithms are data-driven: they generate personalized recommendations by observing users' past behaviors. A common assumption in recommendation is that how a user interacts with a piece of content (e.g., whether they choose to \"like\" it) is a reflection of the content, but not of the algorithm that generated it. Although this assumption is convenient, it fails to capture user strategization: that users may attempt to shape their future recommendations by adapting their behavior to the recommendation algorithm. In this work, we test for user strategization by conduct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05596","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/2405.05596/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":"2405.05596","created_at":"2026-07-05T08:17:26.006141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05596v1","created_at":"2026-07-05T08:17:26.006141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05596","created_at":"2026-07-05T08:17:26.006141+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PDIUKVG76RD","created_at":"2026-07-05T08:17:26.006141+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PDIUKVG76RDRLQP","created_at":"2026-07-05T08:17:26.006141+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PDIUKVG","created_at":"2026-07-05T08:17:26.006141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30801","citing_title":"Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR","json":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR.json","graph_json":"https://pith.science/api/pith-number/3PDIUKVG76RDRLQP6W7U66IWVR/graph.json","events_json":"https://pith.science/api/pith-number/3PDIUKVG76RDRLQP6W7U66IWVR/events.json","paper":"https://pith.science/paper/3PDIUKVG"},"agent_actions":{"view_html":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR","download_json":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR.json","view_paper":"https://pith.science/paper/3PDIUKVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05596&json=true","fetch_graph":"https://pith.science/api/pith-number/3PDIUKVG76RDRLQP6W7U66IWVR/graph.json","fetch_events":"https://pith.science/api/pith-number/3PDIUKVG76RDRLQP6W7U66IWVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR/action/storage_attestation","attest_author":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR/action/author_attestation","sign_citation":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR/action/citation_signature","submit_replication":"https://pith.science/pith/3PDIUKVG76RDRLQP6W7U66IWVR/action/replication_record"}},"created_at":"2026-07-05T08:17:26.006141+00:00","updated_at":"2026-07-05T08:17:26.006141+00:00"}