{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2IYFNMJESPLQR7WA56CSG22WBG","short_pith_number":"pith:2IYFNMJE","canonical_record":{"source":{"id":"2506.18557","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T12:08:07Z","cross_cats_sorted":[],"title_canon_sha256":"ea7c5b780027a14f519521ce1ec87ea374ffd132347ee29273c16b0a4a3013d9","abstract_canon_sha256":"373de04fb23f707f2b9bc5035001756670e1b0d212121e80004a97bd6b6715b4"},"schema_version":"1.0"},"canonical_sha256":"d23056b12493d708fec0ef85236b5609a58aa65d5c82dd11ced16524aed4b949","source":{"kind":"arxiv","id":"2506.18557","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18557","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18557v2","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18557","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"2IYFNMJESPLQ","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"2IYFNMJESPLQR7WA","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"2IYFNMJE","created_at":"2026-07-05T11:26:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2IYFNMJESPLQR7WA56CSG22WBG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18557","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T12:08:07Z","cross_cats_sorted":[],"title_canon_sha256":"ea7c5b780027a14f519521ce1ec87ea374ffd132347ee29273c16b0a4a3013d9","abstract_canon_sha256":"373de04fb23f707f2b9bc5035001756670e1b0d212121e80004a97bd6b6715b4"},"schema_version":"1.0"},"canonical_sha256":"d23056b12493d708fec0ef85236b5609a58aa65d5c82dd11ced16524aed4b949","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:06.379738Z","signature_b64":"NKmqAynh8bgEDZulNf32iktAWtz7eZwJoHVPaWzNCNOdpLKKyhz248FisTDD2YXvwFxhX4yf8eQ+Qwi289YPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d23056b12493d708fec0ef85236b5609a58aa65d5c82dd11ced16524aed4b949","last_reissued_at":"2026-07-05T11:26:06.379271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:06.379271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18557","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":"2026-07-05T11:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VXuQlcADBHMrPzDZrUZYZtBBb5Oy8eeeoY22BPitDCJZWy/efXajje4husAQhhl8D//k6SQqCgoiH+37JC+oBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:54:56.430774Z"},"content_sha256":"2495b03a46f2f4d49fa81c2c1c501f5cd36bbd61272442da541f214f166be1b9","schema_version":"1.0","event_id":"sha256:2495b03a46f2f4d49fa81c2c1c501f5cd36bbd61272442da541f214f166be1b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2IYFNMJESPLQR7WA56CSG22WBG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Object-aware Sound Source Localization via Audio-Visual Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongjin Kim, Jung Uk Kim, Sangmin Lee, Sung Jin Um","submitted_at":"2025-06-23T12:08:07Z","abstract_excerpt":"Audio-visual sound source localization task aims to spatially localize sound-making objects within visual scenes by integrating visual and audio cues. However, existing methods struggle with accurately localizing sound-making objects in complex scenes, particularly when visually similar silent objects coexist. This limitation arises primarily from their reliance on simple audio-visual correspondence, which does not capture fine-grained semantic differences between sound-making and silent objects. To address these challenges, we propose a novel sound source localization framework leveraging Mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18557","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/2506.18557/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":"2026-07-05T11:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"axEzG2yvzpJM907lljwWBtoPE5O7e+LeksMNU2AY636RSTDgJ3Mw9RWspyBt7EZGURuXQyZGZm714mLb88izBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:54:56.431319Z"},"content_sha256":"7ec960e65d5ece081b111250d86ef9bfa873558e60a185da87acc7cc5202555c","schema_version":"1.0","event_id":"sha256:7ec960e65d5ece081b111250d86ef9bfa873558e60a185da87acc7cc5202555c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2IYFNMJESPLQR7WA56CSG22WBG/bundle.json","state_url":"https://pith.science/pith/2IYFNMJESPLQR7WA56CSG22WBG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2IYFNMJESPLQR7WA56CSG22WBG/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":"2026-08-10T15:54:56Z","links":{"resolver":"https://pith.science/pith/2IYFNMJESPLQR7WA56CSG22WBG","bundle":"https://pith.science/pith/2IYFNMJESPLQR7WA56CSG22WBG/bundle.json","state":"https://pith.science/pith/2IYFNMJESPLQR7WA56CSG22WBG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2IYFNMJESPLQR7WA56CSG22WBG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2IYFNMJESPLQR7WA56CSG22WBG","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":"373de04fb23f707f2b9bc5035001756670e1b0d212121e80004a97bd6b6715b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T12:08:07Z","title_canon_sha256":"ea7c5b780027a14f519521ce1ec87ea374ffd132347ee29273c16b0a4a3013d9"},"schema_version":"1.0","source":{"id":"2506.18557","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18557","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18557v2","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18557","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"2IYFNMJESPLQ","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"2IYFNMJESPLQR7WA","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"2IYFNMJE","created_at":"2026-07-05T11:26:06Z"}],"graph_snapshots":[{"event_id":"sha256:7ec960e65d5ece081b111250d86ef9bfa873558e60a185da87acc7cc5202555c","target":"graph","created_at":"2026-07-05T11:26:06Z","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/2506.18557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual sound source localization task aims to spatially localize sound-making objects within visual scenes by integrating visual and audio cues. However, existing methods struggle with accurately localizing sound-making objects in complex scenes, particularly when visually similar silent objects coexist. This limitation arises primarily from their reliance on simple audio-visual correspondence, which does not capture fine-grained semantic differences between sound-making and silent objects. To address these challenges, we propose a novel sound source localization framework leveraging Mul","authors_text":"Dongjin Kim, Jung Uk Kim, Sangmin Lee, Sung Jin Um","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T12:08:07Z","title":"Object-aware Sound Source Localization via Audio-Visual Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18557","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":"sha256:2495b03a46f2f4d49fa81c2c1c501f5cd36bbd61272442da541f214f166be1b9","target":"record","created_at":"2026-07-05T11:26:06Z","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":"373de04fb23f707f2b9bc5035001756670e1b0d212121e80004a97bd6b6715b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T12:08:07Z","title_canon_sha256":"ea7c5b780027a14f519521ce1ec87ea374ffd132347ee29273c16b0a4a3013d9"},"schema_version":"1.0","source":{"id":"2506.18557","kind":"arxiv","version":2}},"canonical_sha256":"d23056b12493d708fec0ef85236b5609a58aa65d5c82dd11ced16524aed4b949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d23056b12493d708fec0ef85236b5609a58aa65d5c82dd11ced16524aed4b949","first_computed_at":"2026-07-05T11:26:06.379271Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:06.379271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NKmqAynh8bgEDZulNf32iktAWtz7eZwJoHVPaWzNCNOdpLKKyhz248FisTDD2YXvwFxhX4yf8eQ+Qwi289YPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:06.379738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18557","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2495b03a46f2f4d49fa81c2c1c501f5cd36bbd61272442da541f214f166be1b9","sha256:7ec960e65d5ece081b111250d86ef9bfa873558e60a185da87acc7cc5202555c"],"state_sha256":"8bd3f327c7478a00056dc3116e7838085ca17f3d7fdb3dfd77ca7d02011aa719"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w0jLUCCYvTW9ZzdUpITKss8Vh62QL5zwgNysMDZgmHw4qmLtP4M/oEz+7yD2HGQaonWOUSK8PXQo5NoHizB4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T15:54:56.437094Z","bundle_sha256":"ad505e2af372f6570625b4172a10e32fffeba652a2f9b22d99c9c007969f084f"}}