{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6NOWCFC2IC6CEXKBSIQ4256ALM","short_pith_number":"pith:6NOWCFC2","canonical_record":{"source":{"id":"2509.06598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-08T12:07:32Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV","eess.SP"],"title_canon_sha256":"45a38a90c7d553c0f8d71afe528072da176b7ef3afc1173fcedcfed97e95157d","abstract_canon_sha256":"a141a91e59a5f8f925430dd6a9c02e3e2df2591e82dfa329c08227ed543f99b4"},"schema_version":"1.0"},"canonical_sha256":"f35d61145a40bc225d419221cd77c05b33457df3ebbeb61654fcb031beb38c3b","source":{"kind":"arxiv","id":"2509.06598","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06598","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06598v1","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06598","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"6NOWCFC2IC6C","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"6NOWCFC2IC6CEXKB","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"6NOWCFC2","created_at":"2026-07-05T12:06:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6NOWCFC2IC6CEXKBSIQ4256ALM","target":"record","payload":{"canonical_record":{"source":{"id":"2509.06598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-08T12:07:32Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV","eess.SP"],"title_canon_sha256":"45a38a90c7d553c0f8d71afe528072da176b7ef3afc1173fcedcfed97e95157d","abstract_canon_sha256":"a141a91e59a5f8f925430dd6a9c02e3e2df2591e82dfa329c08227ed543f99b4"},"schema_version":"1.0"},"canonical_sha256":"f35d61145a40bc225d419221cd77c05b33457df3ebbeb61654fcb031beb38c3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:39.012564Z","signature_b64":"qCk5rMCcVx2mqHLn0/vvoH7kYyBe49knxMeB3MJ4lgcyiCypEcjXTOiJJXVNOHdRIIQmYCG7Cz+r8QyI6mJrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f35d61145a40bc225d419221cd77c05b33457df3ebbeb61654fcb031beb38c3b","last_reissued_at":"2026-07-05T12:06:39.012099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:39.012099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.06598","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/AmWGCvKhERQ1jUHu1cpz7I24KvoIcwn/9eUKBxJIGIk2XBNlVLMm4m8qouuRFZwcRkT+4Q3ZL8wCKfmUiNrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:54:52.765243Z"},"content_sha256":"ab353fa2509289ee690fb55abbdebbb21c615f351ce355eadcf0ea22b08412e6","schema_version":"1.0","event_id":"sha256:ab353fa2509289ee690fb55abbdebbb21c615f351ce355eadcf0ea22b08412e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6NOWCFC2IC6CEXKBSIQ4256ALM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV","eess.SP"],"primary_cat":"eess.AS","authors_text":"Davide Berghi, Philip J. B. Jackson","submitted_at":"2025-09-08T12:07:32Z","abstract_excerpt":"In this study, we address the multimodal task of stereo sound event localization and detection with source distance estimation (3D SELD) in regular video content. 3D SELD is a complex task that combines temporal event classification with spatial localization, requiring reasoning across spatial, temporal, and semantic dimensions. The last is arguably the most challenging to model. Traditional SELD approaches typically rely on multichannel input, limiting their capacity to benefit from large-scale pre-training due to data constraints. To overcome this, we enhance a standard SELD architecture wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06598","kind":"arxiv","version":1},"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/2509.06598/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":"2026-07-05T12:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGrc4WugY63nFmrQDCr/dkkDyKN8I7C+lmGC7aBlAPV4zRwGVOzSX5+GY5k4Pn07nqoz1UjCI4ipKdy8sruXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:54:52.766139Z"},"content_sha256":"645d215b050d59a7d9ee85dc7beae7420e495e221ec1fb7a7315bd9cf30f829c","schema_version":"1.0","event_id":"sha256:645d215b050d59a7d9ee85dc7beae7420e495e221ec1fb7a7315bd9cf30f829c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6NOWCFC2IC6CEXKBSIQ4256ALM/bundle.json","state_url":"https://pith.science/pith/6NOWCFC2IC6CEXKBSIQ4256ALM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6NOWCFC2IC6CEXKBSIQ4256ALM/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":"2026-08-18T11:54:52Z","links":{"resolver":"https://pith.science/pith/6NOWCFC2IC6CEXKBSIQ4256ALM","bundle":"https://pith.science/pith/6NOWCFC2IC6CEXKBSIQ4256ALM/bundle.json","state":"https://pith.science/pith/6NOWCFC2IC6CEXKBSIQ4256ALM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6NOWCFC2IC6CEXKBSIQ4256ALM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6NOWCFC2IC6CEXKBSIQ4256ALM","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":"a141a91e59a5f8f925430dd6a9c02e3e2df2591e82dfa329c08227ed543f99b4","cross_cats_sorted":["cs.AI","cs.LG","eess.IV","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-08T12:07:32Z","title_canon_sha256":"45a38a90c7d553c0f8d71afe528072da176b7ef3afc1173fcedcfed97e95157d"},"schema_version":"1.0","source":{"id":"2509.06598","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06598","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06598v1","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06598","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"6NOWCFC2IC6C","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"6NOWCFC2IC6CEXKB","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"6NOWCFC2","created_at":"2026-07-05T12:06:39Z"}],"graph_snapshots":[{"event_id":"sha256:645d215b050d59a7d9ee85dc7beae7420e495e221ec1fb7a7315bd9cf30f829c","target":"graph","created_at":"2026-07-05T12:06:39Z","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/2509.06598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we address the multimodal task of stereo sound event localization and detection with source distance estimation (3D SELD) in regular video content. 3D SELD is a complex task that combines temporal event classification with spatial localization, requiring reasoning across spatial, temporal, and semantic dimensions. The last is arguably the most challenging to model. Traditional SELD approaches typically rely on multichannel input, limiting their capacity to benefit from large-scale pre-training due to data constraints. To overcome this, we enhance a standard SELD architecture wit","authors_text":"Davide Berghi, Philip J. B. Jackson","cross_cats":["cs.AI","cs.LG","eess.IV","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-08T12:07:32Z","title":"Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06598","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:ab353fa2509289ee690fb55abbdebbb21c615f351ce355eadcf0ea22b08412e6","target":"record","created_at":"2026-07-05T12:06:39Z","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":"a141a91e59a5f8f925430dd6a9c02e3e2df2591e82dfa329c08227ed543f99b4","cross_cats_sorted":["cs.AI","cs.LG","eess.IV","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-08T12:07:32Z","title_canon_sha256":"45a38a90c7d553c0f8d71afe528072da176b7ef3afc1173fcedcfed97e95157d"},"schema_version":"1.0","source":{"id":"2509.06598","kind":"arxiv","version":1}},"canonical_sha256":"f35d61145a40bc225d419221cd77c05b33457df3ebbeb61654fcb031beb38c3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f35d61145a40bc225d419221cd77c05b33457df3ebbeb61654fcb031beb38c3b","first_computed_at":"2026-07-05T12:06:39.012099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:39.012099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qCk5rMCcVx2mqHLn0/vvoH7kYyBe49knxMeB3MJ4lgcyiCypEcjXTOiJJXVNOHdRIIQmYCG7Cz+r8QyI6mJrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:39.012564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06598","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab353fa2509289ee690fb55abbdebbb21c615f351ce355eadcf0ea22b08412e6","sha256:645d215b050d59a7d9ee85dc7beae7420e495e221ec1fb7a7315bd9cf30f829c"],"state_sha256":"5cc84a02c2ff7e4947d4ce0e0c1b85e2c9e4d11b87e66b5cb76b80d0639d7592"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0J6RyVpbm8LIT0EV47zyNOZmUTAUmyWnLd5Pkp+05nbUZpmKm+Mb54DTIGbFZv6XvbM5cwztF/zdmTgQzrAKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:54:52.772370Z","bundle_sha256":"09900b21c7a288fc4ba97249be1412f88abcaaf44c49d44108ae704106413efb"}}