{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JDBYVQ4ZEB23DFGO2YSWCTYD62","short_pith_number":"pith:JDBYVQ4Z","schema_version":"1.0","canonical_sha256":"48c38ac3992075b194ced625614f03f6a80b80a02bf30d54a9240b790bcf0549","source":{"kind":"arxiv","id":"2402.03710","version":2},"attestation_state":"computed","paper":{"title":"Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2024-02-06T05:05:38Z","abstract_excerpt":"In daily life, we encounter a variety of sounds, both desirable and undesirable, with limited control over their presence and volume. Our work introduces \"Listen, Chat, and Remix\" (LCR), a novel multimodal sound remixer that controls each sound source in a mixture based on user-provided text instructions. LCR distinguishes itself with a user-friendly text interface and its unique ability to remix multiple sound sources simultaneously within a mixture, without needing to separate them. Users input open-vocabulary text prompts, which are interpreted by a large language model to create a semantic"},"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":"2402.03710","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-06T05:05:38Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"1e1730499f84417825ca33a3871be0930e0ea95564033895c7eb3a57d301b846","abstract_canon_sha256":"cb7974672cac1ea8b09140f5cf89c1e640b70d846f6b471fd96e3d8670d8dd80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:18.673811Z","signature_b64":"u9wvNeZ+4i3vZQ5/hk8cCECKGykZBnLTfj3jRVWq4y9vCwBSIxZU4KxjHXktW/0d49l9notkZqrvcO5Xer+YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48c38ac3992075b194ced625614f03f6a80b80a02bf30d54a9240b790bcf0549","last_reissued_at":"2026-07-05T11:19:18.673284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:18.673284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2024-02-06T05:05:38Z","abstract_excerpt":"In daily life, we encounter a variety of sounds, both desirable and undesirable, with limited control over their presence and volume. Our work introduces \"Listen, Chat, and Remix\" (LCR), a novel multimodal sound remixer that controls each sound source in a mixture based on user-provided text instructions. LCR distinguishes itself with a user-friendly text interface and its unique ability to remix multiple sound sources simultaneously within a mixture, without needing to separate them. Users input open-vocabulary text prompts, which are interpreted by a large language model to create a semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03710","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/2402.03710/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":"2402.03710","created_at":"2026-07-05T11:19:18.673366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03710v2","created_at":"2026-07-05T11:19:18.673366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03710","created_at":"2026-07-05T11:19:18.673366+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDBYVQ4ZEB23","created_at":"2026-07-05T11:19:18.673366+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDBYVQ4ZEB23DFGO","created_at":"2026-07-05T11:19:18.673366+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDBYVQ4Z","created_at":"2026-07-05T11:19:18.673366+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/JDBYVQ4ZEB23DFGO2YSWCTYD62","json":"https://pith.science/pith/JDBYVQ4ZEB23DFGO2YSWCTYD62.json","graph_json":"https://pith.science/api/pith-number/JDBYVQ4ZEB23DFGO2YSWCTYD62/graph.json","events_json":"https://pith.science/api/pith-number/JDBYVQ4ZEB23DFGO2YSWCTYD62/events.json","paper":"https://pith.science/paper/JDBYVQ4Z"},"agent_actions":{"view_html":"https://pith.science/pith/JDBYVQ4ZEB23DFGO2YSWCTYD62","download_json":"https://pith.science/pith/JDBYVQ4ZEB23DFGO2YSWCTYD62.json","view_paper":"https://pith.science/paper/JDBYVQ4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03710&json=true","fetch_graph":"https://pith.science/api/pith-number/JDBYVQ4ZEB23DFGO2YSWCTYD62/graph.json","fetch_events":"https://pith.science/api/pith-number/JDBYVQ4ZEB23DFGO2YSWCTYD62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDBYVQ4ZEB23DFGO2YSWCTYD62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDBYVQ4ZEB23DFGO2YSWCTYD62/action/storage_attestation","attest_author":"https://pith.science/pith/JDBYVQ4ZEB23DFGO2YSWCTYD62/action/author_attestation","sign_citation":"https://pith.science/pith/JDBYVQ4ZEB23DFGO2YSWCTYD62/action/citation_signature","submit_replication":"https://pith.science/pith/JDBYVQ4ZEB23DFGO2YSWCTYD62/action/replication_record"}},"created_at":"2026-07-05T11:19:18.673366+00:00","updated_at":"2026-07-05T11:19:18.673366+00:00"}