{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:I7NNA7FH5FLGNVP5VAG6KPK2LD","short_pith_number":"pith:I7NNA7FH","canonical_record":{"source":{"id":"2211.03019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-06T03:48:45Z","cross_cats_sorted":[],"title_canon_sha256":"e9e3c8e965e795ede1cf589c927dc1a4361704d29ce3c18868274b2074fc49f6","abstract_canon_sha256":"9139301364d64b0e5a8911d08cbd547ef29e761725c4430c90e07717b56602ea"},"schema_version":"1.0"},"canonical_sha256":"47dad07ca7e95666d5fda80de53d5a58db2232a159780cb122a8f9db8d28973f","source":{"kind":"arxiv","id":"2211.03019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03019","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03019v1","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03019","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"I7NNA7FH5FLG","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"I7NNA7FH5FLGNVP5","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"I7NNA7FH","created_at":"2026-07-05T05:13:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:I7NNA7FH5FLGNVP5VAG6KPK2LD","target":"record","payload":{"canonical_record":{"source":{"id":"2211.03019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-06T03:48:45Z","cross_cats_sorted":[],"title_canon_sha256":"e9e3c8e965e795ede1cf589c927dc1a4361704d29ce3c18868274b2074fc49f6","abstract_canon_sha256":"9139301364d64b0e5a8911d08cbd547ef29e761725c4430c90e07717b56602ea"},"schema_version":"1.0"},"canonical_sha256":"47dad07ca7e95666d5fda80de53d5a58db2232a159780cb122a8f9db8d28973f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:43.553809Z","signature_b64":"fd15XbEZeJVEmVAqIpAf0iR5XoPm7gumN2mkPE7ZU4dA/sq4+PusWcPgfaI3Rbwto12/ftQCllWz/pgJ5iwpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47dad07ca7e95666d5fda80de53d5a58db2232a159780cb122a8f9db8d28973f","last_reissued_at":"2026-07-05T05:13:43.553305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:43.553305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.03019","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":"2026-07-05T05:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wrVIbSjizus2fLiykAWwi63UMBRzd7HxQFhIRi5ZjmRI+QDUtsYkdCdImTVKNMt27t9m7wxV/vAHIDBGl8B+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T01:54:39.391908Z"},"content_sha256":"6a2dd1224c692add87f67e172668ccfa99521d8c980c2e661cf6187484406384","schema_version":"1.0","event_id":"sha256:6a2dd1224c692add87f67e172668ccfa99521d8c980c2e661cf6187484406384"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:I7NNA7FH5FLGNVP5VAG6KPK2LD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhavin Jawade, Deen Dayal Mohan, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju","submitted_at":"2022-11-06T03:48:45Z","abstract_excerpt":"Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the source of the sound. In a video, oftentimes, the objects exhibiting movement are the ones generating the sound. In this work, we capture this characteristic by modeling the optical flow in a video as a prior to better aid in localizing the sound source. We further demonstrate that the addition of flow-based attention substantially improves visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03019","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/2211.03019/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":"2026-07-05T05:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yYLoya37gnkr9WbVY6rbkpbUYtBAhpuCEE8XqliBr6+kDQlOdBF+i6ZAl7kEw0SjiKeOSQdwitGq6UZ5pOzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T01:54:39.392421Z"},"content_sha256":"464b5ca28a2e32acd2712173435f5cdf45f29db3d7839870468f1e563214927c","schema_version":"1.0","event_id":"sha256:464b5ca28a2e32acd2712173435f5cdf45f29db3d7839870468f1e563214927c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/bundle.json","state_url":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/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":"2026-08-23T01:54:39Z","links":{"resolver":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD","bundle":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/bundle.json","state":"https://pith.science/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I7NNA7FH5FLGNVP5VAG6KPK2LD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:I7NNA7FH5FLGNVP5VAG6KPK2LD","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":"9139301364d64b0e5a8911d08cbd547ef29e761725c4430c90e07717b56602ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-06T03:48:45Z","title_canon_sha256":"e9e3c8e965e795ede1cf589c927dc1a4361704d29ce3c18868274b2074fc49f6"},"schema_version":"1.0","source":{"id":"2211.03019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03019","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03019v1","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03019","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"I7NNA7FH5FLG","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"I7NNA7FH5FLGNVP5","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"I7NNA7FH","created_at":"2026-07-05T05:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:464b5ca28a2e32acd2712173435f5cdf45f29db3d7839870468f1e563214927c","target":"graph","created_at":"2026-07-05T05:13:43Z","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/2211.03019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the source of the sound. In a video, oftentimes, the objects exhibiting movement are the ones generating the sound. In this work, we capture this characteristic by modeling the optical flow in a video as a prior to better aid in localizing the sound source. We further demonstrate that the addition of flow-based attention substantially improves visual ","authors_text":"Bhavin Jawade, Deen Dayal Mohan, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-06T03:48:45Z","title":"Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03019","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":"sha256:6a2dd1224c692add87f67e172668ccfa99521d8c980c2e661cf6187484406384","target":"record","created_at":"2026-07-05T05:13:43Z","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":"9139301364d64b0e5a8911d08cbd547ef29e761725c4430c90e07717b56602ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-06T03:48:45Z","title_canon_sha256":"e9e3c8e965e795ede1cf589c927dc1a4361704d29ce3c18868274b2074fc49f6"},"schema_version":"1.0","source":{"id":"2211.03019","kind":"arxiv","version":1}},"canonical_sha256":"47dad07ca7e95666d5fda80de53d5a58db2232a159780cb122a8f9db8d28973f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47dad07ca7e95666d5fda80de53d5a58db2232a159780cb122a8f9db8d28973f","first_computed_at":"2026-07-05T05:13:43.553305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:43.553305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fd15XbEZeJVEmVAqIpAf0iR5XoPm7gumN2mkPE7ZU4dA/sq4+PusWcPgfaI3Rbwto12/ftQCllWz/pgJ5iwpCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:43.553809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.03019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a2dd1224c692add87f67e172668ccfa99521d8c980c2e661cf6187484406384","sha256:464b5ca28a2e32acd2712173435f5cdf45f29db3d7839870468f1e563214927c"],"state_sha256":"abc7799ff509ab97a04b6821f95831b89f2cc60f7880d1b2d0f7a9c7fe7d686d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oeGpfBSuRn4yoLUkFI3os2Ndh8LJuyD4pSYY1ysS+uxEYxNc2cIBSC9JkyWRrnqlHScrm3vXWWluSacYsu0fCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T01:54:39.397861Z","bundle_sha256":"7468d8f80f6a3a8b2c51d6d76dd4feea1652f77f4181aee9e79dbe8bdf55e229"}}