{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QPWWFHGJHYZOIXFBOWJNHVL75H","short_pith_number":"pith:QPWWFHGJ","schema_version":"1.0","canonical_sha256":"83ed629cc93e32e45ca17592d3d57fe9ccdc821eed39515298b90b134c7d8c98","source":{"kind":"arxiv","id":"2506.10225","version":2},"attestation_state":"computed","paper":{"title":"Genre Controlled Music Generation via Activation Steering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aniruddh Krishna, Anish Veerakumar, Dipanshu Panda, Harshith M R, Jayden Koshy Joe, Keerthiharan A, Pranay Mathur, Swathi Narashiman","submitted_at":"2025-06-11T23:02:39Z","abstract_excerpt":"Computational Music Generation is evolving towards non-conventional styles, demanding methods that enable precise and controllable blending of diverse music elements. In this work, we present a method for fine grained control using inference-time interventions on an autoregressive generative transformer, MusicGen. Through our approach, we achieve genre control by steering the residual stream using weights of a linear probe on it. By framing activation steering as a human-controllable interaction, our work highlights how interpretable model behaviors can empower in co-creative music generation."},"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":"2506.10225","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-11T23:02:39Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"9dcc891fb54143c3dc9f05ea94d2c7632634d40e0d046f6e60bb8c720aefe7db","abstract_canon_sha256":"cdb604ec590ac1b4a130ba6dc75e1b1712362ceefc325d6c5c265a87a95499fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:35.276148Z","signature_b64":"x2KBvXvSsZsYnZ/2E7O36VXw08nIdY4AvPav1S3V4F34g15sd1OI/ak8c5SzUYILpTqAUa6syV3ntE5MIvGJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ed629cc93e32e45ca17592d3d57fe9ccdc821eed39515298b90b134c7d8c98","last_reissued_at":"2026-05-27T01:05:35.275482Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:35.275482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Genre Controlled Music Generation via Activation Steering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aniruddh Krishna, Anish Veerakumar, Dipanshu Panda, Harshith M R, Jayden Koshy Joe, Keerthiharan A, Pranay Mathur, Swathi Narashiman","submitted_at":"2025-06-11T23:02:39Z","abstract_excerpt":"Computational Music Generation is evolving towards non-conventional styles, demanding methods that enable precise and controllable blending of diverse music elements. In this work, we present a method for fine grained control using inference-time interventions on an autoregressive generative transformer, MusicGen. Through our approach, we achieve genre control by steering the residual stream using weights of a linear probe on it. By framing activation steering as a human-controllable interaction, our work highlights how interpretable model behaviors can empower in co-creative music generation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10225","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/2506.10225/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":"2506.10225","created_at":"2026-05-27T01:05:35.275550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10225v2","created_at":"2026-05-27T01:05:35.275550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10225","created_at":"2026-05-27T01:05:35.275550+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPWWFHGJHYZO","created_at":"2026-05-27T01:05:35.275550+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPWWFHGJHYZOIXFB","created_at":"2026-05-27T01:05:35.275550+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPWWFHGJ","created_at":"2026-05-27T01:05:35.275550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.31295","citing_title":"Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H","json":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H.json","graph_json":"https://pith.science/api/pith-number/QPWWFHGJHYZOIXFBOWJNHVL75H/graph.json","events_json":"https://pith.science/api/pith-number/QPWWFHGJHYZOIXFBOWJNHVL75H/events.json","paper":"https://pith.science/paper/QPWWFHGJ"},"agent_actions":{"view_html":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H","download_json":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H.json","view_paper":"https://pith.science/paper/QPWWFHGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10225&json=true","fetch_graph":"https://pith.science/api/pith-number/QPWWFHGJHYZOIXFBOWJNHVL75H/graph.json","fetch_events":"https://pith.science/api/pith-number/QPWWFHGJHYZOIXFBOWJNHVL75H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H/action/storage_attestation","attest_author":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H/action/author_attestation","sign_citation":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H/action/citation_signature","submit_replication":"https://pith.science/pith/QPWWFHGJHYZOIXFBOWJNHVL75H/action/replication_record"}},"created_at":"2026-05-27T01:05:35.275550+00:00","updated_at":"2026-05-27T01:05:35.275550+00:00"}