{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DRMX3DBWXHS2RNNGMZKFXKDYMS","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":"ba3205de721717a03c19c891991320e059fc546029986a5f5e4c90050db282ba","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T22:15:10Z","title_canon_sha256":"b0727901f0addbc4b74471aa59e2204539c103f76b6b4e138d74d0863954f61d"},"schema_version":"1.0","source":{"id":"2506.00273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00273","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00273v1","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00273","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"DRMX3DBWXHS2","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"DRMX3DBWXHS2RNNG","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"DRMX3DBW","created_at":"2026-07-05T11:13:31Z"}],"graph_snapshots":[{"event_id":"sha256:1e2849ca1ec465f490965cb814813cfbc5ed7910f5420a5876adbca03934d642","target":"graph","created_at":"2026-07-05T11:13:31Z","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/2506.00273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces SoundSculpt, a neural network designed to extract target sound fields from ambisonic recordings. SoundSculpt employs an ambisonic-in-ambisonic-out architecture and is conditioned on both spatial information (e.g., target direction obtained by pointing at an immersive video) and semantic embeddings (e.g., derived from image segmentation and captioning). Trained and evaluated on synthetic and real ambisonic mixtures, SoundSculpt demonstrates superior performance compared to various signal processing baselines. Our results further reveal that while spatial conditioning alone","authors_text":"D Shin, Hakan Erdogan, Sinan Hersek, Tuochao Chen","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T22:15:10Z","title":"SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00273","kind":"arxiv","version":1},"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":"sha256:1430b47714ae0d255621dade3c127e876d9c2abfc4466c4d54728c189ab9b973","target":"record","created_at":"2026-07-05T11:13:31Z","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":"ba3205de721717a03c19c891991320e059fc546029986a5f5e4c90050db282ba","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T22:15:10Z","title_canon_sha256":"b0727901f0addbc4b74471aa59e2204539c103f76b6b4e138d74d0863954f61d"},"schema_version":"1.0","source":{"id":"2506.00273","kind":"arxiv","version":1}},"canonical_sha256":"1c597d8c36b9e5a8b5a666545ba87864a04a48c4bb42c60604079614f27c4e4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c597d8c36b9e5a8b5a666545ba87864a04a48c4bb42c60604079614f27c4e4d","first_computed_at":"2026-07-05T11:13:31.853080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:31.853080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vVQqdIUd2M3QyO/1s82rY/k4ft+h/URwkPp088gSS5LDEiGdcJjbaeuAnsYSjn/hA+8gsUNA4D2JC+1E6FbsAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:31.853487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1430b47714ae0d255621dade3c127e876d9c2abfc4466c4d54728c189ab9b973","sha256:1e2849ca1ec465f490965cb814813cfbc5ed7910f5420a5876adbca03934d642"],"state_sha256":"80597673b75c6f27fe6d61f4c47ff2059d4e969baeb4e3d77773bfdbe5faa6a5"}