{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OWDILHDJNBCHYQSVVCO4KKZKVL","short_pith_number":"pith:OWDILHDJ","canonical_record":{"source":{"id":"2406.06612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T22:55:01Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"b8c6e6c86d39dabc92b7b0a6ba010ebd74f923072a0cfdfaab1362422c902500","abstract_canon_sha256":"270f64623d09093d819a94d99f0dbf7fa42bd19e7601c783aa3b22508baaf776"},"schema_version":"1.0"},"canonical_sha256":"7586859c6968447c4255a89dc52b2aaaeba103d854974c5e77ef785283d3a1a1","source":{"kind":"arxiv","id":"2406.06612","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06612","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06612v2","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06612","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"pith_short_12","alias_value":"OWDILHDJNBCH","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"OWDILHDJNBCHYQSV","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"OWDILHDJ","created_at":"2026-07-05T11:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OWDILHDJNBCHYQSVVCO4KKZKVL","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T22:55:01Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"b8c6e6c86d39dabc92b7b0a6ba010ebd74f923072a0cfdfaab1362422c902500","abstract_canon_sha256":"270f64623d09093d819a94d99f0dbf7fa42bd19e7601c783aa3b22508baaf776"},"schema_version":"1.0"},"canonical_sha256":"7586859c6968447c4255a89dc52b2aaaeba103d854974c5e77ef785283d3a1a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:01.599179Z","signature_b64":"X3Pz4iq4dq65zOOu+NNeDhFD1ssAHGzcw+mXjC6mBqHZwJGIc8xIyR1SLggltwLA//YcgUxHNkmcTJdChmY7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7586859c6968447c4255a89dc52b2aaaeba103d854974c5e77ef785283d3a1a1","last_reissued_at":"2026-07-05T11:33:01.598684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:01.598684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06612","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":"2026-07-05T11:33:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RYPfIUt1lKcbWhWIFodl1OhxWZkxdB4jHGgDEX2Cbjb1T6HHKHh4htQTuJCnMTbD8MM4EzxqEPrA/eAAXpO8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:30:39.668155Z"},"content_sha256":"5e5b856c1379ad60cb71a34f7289ed4e95b1b9885dc99436da929f567fe44d09","schema_version":"1.0","event_id":"sha256:5e5b856c1379ad60cb71a34f7289ed4e95b1b9885dc99436da929f567fe44d09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OWDILHDJNBCHYQSVVCO4KKZKVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Houman Khosravani, Rishit Dagli, Robert Wu, Shivesh Prakash","submitted_at":"2024-06-06T22:55:01Z","abstract_excerpt":"Generating combined visual and auditory sensory experiences is critical for the consumption of immersive content. Recent advances in neural generative models have enabled the creation of high-resolution content across multiple modalities such as images, text, speech, and videos. Despite these successes, there remains a significant gap in the generation of high-quality spatial audio that complements generated visual content. Furthermore, current audio generation models excel in either generating natural audio or speech or music but fall short in integrating spatial audio cues necessary for imme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06612","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/2406.06612/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":"2026-07-05T11:33:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SwlCC1pT2O8tz5UGoKvGD5aMiUoInfmKsCiGff8xYI8eQsYvqvArZvBli0hY45PLdDDpvgikFWsPZ9JB7X/EAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:30:39.672511Z"},"content_sha256":"d8b6cd86bd2e09375f0189e3c55f844409734b32508229fb58f853de0df04298","schema_version":"1.0","event_id":"sha256:d8b6cd86bd2e09375f0189e3c55f844409734b32508229fb58f853de0df04298"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWDILHDJNBCHYQSVVCO4KKZKVL/bundle.json","state_url":"https://pith.science/pith/OWDILHDJNBCHYQSVVCO4KKZKVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWDILHDJNBCHYQSVVCO4KKZKVL/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":"2026-08-04T00:30:39Z","links":{"resolver":"https://pith.science/pith/OWDILHDJNBCHYQSVVCO4KKZKVL","bundle":"https://pith.science/pith/OWDILHDJNBCHYQSVVCO4KKZKVL/bundle.json","state":"https://pith.science/pith/OWDILHDJNBCHYQSVVCO4KKZKVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWDILHDJNBCHYQSVVCO4KKZKVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OWDILHDJNBCHYQSVVCO4KKZKVL","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":"270f64623d09093d819a94d99f0dbf7fa42bd19e7601c783aa3b22508baaf776","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T22:55:01Z","title_canon_sha256":"b8c6e6c86d39dabc92b7b0a6ba010ebd74f923072a0cfdfaab1362422c902500"},"schema_version":"1.0","source":{"id":"2406.06612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06612","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06612v2","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06612","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"pith_short_12","alias_value":"OWDILHDJNBCH","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"OWDILHDJNBCHYQSV","created_at":"2026-07-05T11:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"OWDILHDJ","created_at":"2026-07-05T11:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:d8b6cd86bd2e09375f0189e3c55f844409734b32508229fb58f853de0df04298","target":"graph","created_at":"2026-07-05T11:33:01Z","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/2406.06612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating combined visual and auditory sensory experiences is critical for the consumption of immersive content. Recent advances in neural generative models have enabled the creation of high-resolution content across multiple modalities such as images, text, speech, and videos. Despite these successes, there remains a significant gap in the generation of high-quality spatial audio that complements generated visual content. Furthermore, current audio generation models excel in either generating natural audio or speech or music but fall short in integrating spatial audio cues necessary for imme","authors_text":"Houman Khosravani, Rishit Dagli, Robert Wu, Shivesh Prakash","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T22:55:01Z","title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06612","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":"sha256:5e5b856c1379ad60cb71a34f7289ed4e95b1b9885dc99436da929f567fe44d09","target":"record","created_at":"2026-07-05T11:33:01Z","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":"270f64623d09093d819a94d99f0dbf7fa42bd19e7601c783aa3b22508baaf776","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T22:55:01Z","title_canon_sha256":"b8c6e6c86d39dabc92b7b0a6ba010ebd74f923072a0cfdfaab1362422c902500"},"schema_version":"1.0","source":{"id":"2406.06612","kind":"arxiv","version":2}},"canonical_sha256":"7586859c6968447c4255a89dc52b2aaaeba103d854974c5e77ef785283d3a1a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7586859c6968447c4255a89dc52b2aaaeba103d854974c5e77ef785283d3a1a1","first_computed_at":"2026-07-05T11:33:01.598684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:01.598684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X3Pz4iq4dq65zOOu+NNeDhFD1ssAHGzcw+mXjC6mBqHZwJGIc8xIyR1SLggltwLA//YcgUxHNkmcTJdChmY7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:01.599179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e5b856c1379ad60cb71a34f7289ed4e95b1b9885dc99436da929f567fe44d09","sha256:d8b6cd86bd2e09375f0189e3c55f844409734b32508229fb58f853de0df04298"],"state_sha256":"167dc185874ebc4c30c1e1a0b1ea009c14e5b1fbac35342a011d7f90004611ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JR1PP4LBD7dwgHQT04Y2GjfNZVufVBnnImzeGX6bueUNiORsYjBQqrV79VCgNBm9ciH6c20tzDdIg5brKbzZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:30:39.693083Z","bundle_sha256":"b3283a091ee959a86a8fda8dc28f6366bd6394519897e0904ef37dcd4b4c1a01"}}