{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:J5H3EKMRWX3Q7MRV5GCJ6KNMKJ","short_pith_number":"pith:J5H3EKMR","canonical_record":{"source":{"id":"2410.10676","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-14T16:18:29Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"7ec4558b99b1dafd83a0766c2d9ed9f59377cd99ecaa3bd75301718f93e04f1e","abstract_canon_sha256":"2201cfb5a34e7068452da951aae716dcbfdd9f3367882b6c60a6b20527d8f011"},"schema_version":"1.0"},"canonical_sha256":"4f4fb22991b5f70fb235e9849f29ac526e00f66c8300c8aed7ab33028fa5dd1b","source":{"kind":"arxiv","id":"2410.10676","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10676","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10676v2","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10676","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_12","alias_value":"J5H3EKMRWX3Q","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_16","alias_value":"J5H3EKMRWX3Q7MRV","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_8","alias_value":"J5H3EKMR","created_at":"2026-07-05T10:19:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:J5H3EKMRWX3Q7MRV5GCJ6KNMKJ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10676","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-14T16:18:29Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"7ec4558b99b1dafd83a0766c2d9ed9f59377cd99ecaa3bd75301718f93e04f1e","abstract_canon_sha256":"2201cfb5a34e7068452da951aae716dcbfdd9f3367882b6c60a6b20527d8f011"},"schema_version":"1.0"},"canonical_sha256":"4f4fb22991b5f70fb235e9849f29ac526e00f66c8300c8aed7ab33028fa5dd1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:29.572064Z","signature_b64":"GYLZtj9eu24DIl9/4VtuPOnk26T4fBCHgUzpL3nGJrOKokVCZitrCwNkRo/IlyULHCefVC4ekcjF3yC7nZKhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f4fb22991b5f70fb235e9849f29ac526e00f66c8300c8aed7ab33028fa5dd1b","last_reissued_at":"2026-07-05T10:19:29.571595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:29.571595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10676","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:19:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l84YN5n44pntNNOGqaP7fwjpOmjVm/SSANXLUp3Upu40zs3TLjAVmopnWkrb8HWCMJrmoQi1egmoeg2w8e3RAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:07:51.497084Z"},"content_sha256":"5a1955462595a8eedfd5fe72f60ed3e33af945e68e9fc529bda5addf68c75e1a","schema_version":"1.0","event_id":"sha256:5a1955462595a8eedfd5fe72f60ed3e33af945e68e9fc529bda5addf68c75e1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:J5H3EKMRWX3Q7MRV5GCJ6KNMKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Honggang Zhang, Huadai Liu, Peiwen Sun, Sitong Cheng, Wei Xue, Xiangtai Li, Yike Guo, Zhen Ye","submitted_at":"2024-10-14T16:18:29Z","abstract_excerpt":"Recently, diffusion models have achieved great success in mono-channel audio generation. However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions. Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models. To the best of our knowledge, this work represents the first attempt to address these issues. We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions even including moving and multiple "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10676","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/2410.10676/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:19:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YoHrAabA6lE9vuT4NLMtLfC+cmmpAL27gtjwEt5lOiFxCp1fYM+gYD30OWJv4lAJvp+VchtnRsjzuPGHbaAJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:07:51.497791Z"},"content_sha256":"f2bbd304e29ca7459849862a5cb4c0a2e34bdd8b66713f94e412294eda04a9ea","schema_version":"1.0","event_id":"sha256:f2bbd304e29ca7459849862a5cb4c0a2e34bdd8b66713f94e412294eda04a9ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5H3EKMRWX3Q7MRV5GCJ6KNMKJ/bundle.json","state_url":"https://pith.science/pith/J5H3EKMRWX3Q7MRV5GCJ6KNMKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5H3EKMRWX3Q7MRV5GCJ6KNMKJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T15:07:51Z","links":{"resolver":"https://pith.science/pith/J5H3EKMRWX3Q7MRV5GCJ6KNMKJ","bundle":"https://pith.science/pith/J5H3EKMRWX3Q7MRV5GCJ6KNMKJ/bundle.json","state":"https://pith.science/pith/J5H3EKMRWX3Q7MRV5GCJ6KNMKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5H3EKMRWX3Q7MRV5GCJ6KNMKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J5H3EKMRWX3Q7MRV5GCJ6KNMKJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2201cfb5a34e7068452da951aae716dcbfdd9f3367882b6c60a6b20527d8f011","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-14T16:18:29Z","title_canon_sha256":"7ec4558b99b1dafd83a0766c2d9ed9f59377cd99ecaa3bd75301718f93e04f1e"},"schema_version":"1.0","source":{"id":"2410.10676","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10676","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10676v2","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10676","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_12","alias_value":"J5H3EKMRWX3Q","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_16","alias_value":"J5H3EKMRWX3Q7MRV","created_at":"2026-07-05T10:19:29Z"},{"alias_kind":"pith_short_8","alias_value":"J5H3EKMR","created_at":"2026-07-05T10:19:29Z"}],"graph_snapshots":[{"event_id":"sha256:f2bbd304e29ca7459849862a5cb4c0a2e34bdd8b66713f94e412294eda04a9ea","target":"graph","created_at":"2026-07-05T10:19:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.10676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, diffusion models have achieved great success in mono-channel audio generation. However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions. Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models. To the best of our knowledge, this work represents the first attempt to address these issues. We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions even including moving and multiple ","authors_text":"Honggang Zhang, Huadai Liu, Peiwen Sun, Sitong Cheng, Wei Xue, Xiangtai Li, Yike Guo, Zhen Ye","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-14T16:18:29Z","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10676","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5a1955462595a8eedfd5fe72f60ed3e33af945e68e9fc529bda5addf68c75e1a","target":"record","created_at":"2026-07-05T10:19:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2201cfb5a34e7068452da951aae716dcbfdd9f3367882b6c60a6b20527d8f011","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-14T16:18:29Z","title_canon_sha256":"7ec4558b99b1dafd83a0766c2d9ed9f59377cd99ecaa3bd75301718f93e04f1e"},"schema_version":"1.0","source":{"id":"2410.10676","kind":"arxiv","version":2}},"canonical_sha256":"4f4fb22991b5f70fb235e9849f29ac526e00f66c8300c8aed7ab33028fa5dd1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f4fb22991b5f70fb235e9849f29ac526e00f66c8300c8aed7ab33028fa5dd1b","first_computed_at":"2026-07-05T10:19:29.571595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:29.571595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GYLZtj9eu24DIl9/4VtuPOnk26T4fBCHgUzpL3nGJrOKokVCZitrCwNkRo/IlyULHCefVC4ekcjF3yC7nZKhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:29.572064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10676","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a1955462595a8eedfd5fe72f60ed3e33af945e68e9fc529bda5addf68c75e1a","sha256:f2bbd304e29ca7459849862a5cb4c0a2e34bdd8b66713f94e412294eda04a9ea"],"state_sha256":"eb1a61fa6852efa2be9510c37fe16ab4926504f00ccb35ebf012fcd1acbdb634"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3q/f6v2EhqEoYhL/gYsNqAMaYcuYal5cJjoPRdravnYWcYb4FGsNhShLs5n2soqyvY4fqljeKVdGNwik0XFaDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:07:51.502865Z","bundle_sha256":"ba5275ce8ab40fc2823de73fda2554a3e34f0a88fa4040d012619a0b9799d8bc"}}