{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HTMZWNJNBOIELVZRG6RD7EMMTA","short_pith_number":"pith:HTMZWNJN","schema_version":"1.0","canonical_sha256":"3cd99b352d0b9045d73137a23f918c9817e6a4379a5f214c4b57e716904d9e69","source":{"kind":"arxiv","id":"2505.22238","version":2},"attestation_state":"computed","paper":{"title":"Yambda-5B -- A Large-Scale Multi-modal Dataset for Ranking And Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"A. Permiakov, A. Pismenny, A. Ploshkin, D. Burlakov, E. Krofto, E. Taychinov, N. Savushkin, V. Baikalov, V. Tytskiy","submitted_at":"2025-05-28T11:12:57Z","abstract_excerpt":"We present Yambda-5B, a large-scale open dataset sourced from the Yandex Music streaming platform. Yambda-5B contains 4.79 billion user-item interactions from 1 million users across 9.39 million tracks. The dataset includes two primary types of interactions: implicit feedback (listening events) and explicit feedback (likes, dislikes, unlikes and undislikes). In addition, we provide audio embeddings for most tracks, generated by a convolutional neural network trained on audio spectrograms. A key distinguishing feature of Yambda-5B is the inclusion of the is_organic flag, which separates organic"},"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":"2505.22238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T11:12:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11d71cc74da75506386345ddd605597a2172c530f7b81b803c8f4ee8e68be18d","abstract_canon_sha256":"3bf6763d19c294aca34a75bf9faf1f729109d21f8fb527bcf14a59c72b8c304e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:27.477458Z","signature_b64":"HZkhGnV5qeSuJZBGUz/33Qg2XH3tQDVU1x3TX7XDvd3x3O/rjmynLYConKXov4a2LBObpUqhTjkstilXRPYhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cd99b352d0b9045d73137a23f918c9817e6a4379a5f214c4b57e716904d9e69","last_reissued_at":"2026-07-05T11:13:27.476874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:27.476874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Yambda-5B -- A Large-Scale Multi-modal Dataset for Ranking And Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"A. Permiakov, A. Pismenny, A. Ploshkin, D. Burlakov, E. Krofto, E. Taychinov, N. Savushkin, V. Baikalov, V. Tytskiy","submitted_at":"2025-05-28T11:12:57Z","abstract_excerpt":"We present Yambda-5B, a large-scale open dataset sourced from the Yandex Music streaming platform. Yambda-5B contains 4.79 billion user-item interactions from 1 million users across 9.39 million tracks. The dataset includes two primary types of interactions: implicit feedback (listening events) and explicit feedback (likes, dislikes, unlikes and undislikes). In addition, we provide audio embeddings for most tracks, generated by a convolutional neural network trained on audio spectrograms. A key distinguishing feature of Yambda-5B is the inclusion of the is_organic flag, which separates organic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22238","kind":"arxiv","version":2},"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/2505.22238/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":"2505.22238","created_at":"2026-07-05T11:13:27.476956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22238v2","created_at":"2026-07-05T11:13:27.476956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22238","created_at":"2026-07-05T11:13:27.476956+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTMZWNJNBOIE","created_at":"2026-07-05T11:13:27.476956+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTMZWNJNBOIELVZR","created_at":"2026-07-05T11:13:27.476956+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTMZWNJN","created_at":"2026-07-05T11:13:27.476956+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA","json":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA.json","graph_json":"https://pith.science/api/pith-number/HTMZWNJNBOIELVZRG6RD7EMMTA/graph.json","events_json":"https://pith.science/api/pith-number/HTMZWNJNBOIELVZRG6RD7EMMTA/events.json","paper":"https://pith.science/paper/HTMZWNJN"},"agent_actions":{"view_html":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA","download_json":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA.json","view_paper":"https://pith.science/paper/HTMZWNJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22238&json=true","fetch_graph":"https://pith.science/api/pith-number/HTMZWNJNBOIELVZRG6RD7EMMTA/graph.json","fetch_events":"https://pith.science/api/pith-number/HTMZWNJNBOIELVZRG6RD7EMMTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA/action/storage_attestation","attest_author":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA/action/author_attestation","sign_citation":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA/action/citation_signature","submit_replication":"https://pith.science/pith/HTMZWNJNBOIELVZRG6RD7EMMTA/action/replication_record"}},"created_at":"2026-07-05T11:13:27.476956+00:00","updated_at":"2026-07-05T11:13:27.476956+00:00"}