{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VNIPCZUUJ4BNTJ5PYTYKCS3PCV","short_pith_number":"pith:VNIPCZUU","canonical_record":{"source":{"id":"2211.15058","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T04:30:50Z","cross_cats_sorted":[],"title_canon_sha256":"169f080188fc102b1fa1c554bf665de718e91f10f796fdca2546936f6e2cff88","abstract_canon_sha256":"fee8fb50b196eca80b9684828957172f8b4ed4dec0d36b666599046b5aa3607e"},"schema_version":"1.0"},"canonical_sha256":"ab50f166944f02d9a7afc4f0a14b6f156ec2082bb10bb51bd0616a1dab65a422","source":{"kind":"arxiv","id":"2211.15058","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15058","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15058v1","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15058","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"VNIPCZUUJ4BN","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"VNIPCZUUJ4BNTJ5P","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"VNIPCZUU","created_at":"2026-07-05T05:19:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VNIPCZUUJ4BNTJ5PYTYKCS3PCV","target":"record","payload":{"canonical_record":{"source":{"id":"2211.15058","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T04:30:50Z","cross_cats_sorted":[],"title_canon_sha256":"169f080188fc102b1fa1c554bf665de718e91f10f796fdca2546936f6e2cff88","abstract_canon_sha256":"fee8fb50b196eca80b9684828957172f8b4ed4dec0d36b666599046b5aa3607e"},"schema_version":"1.0"},"canonical_sha256":"ab50f166944f02d9a7afc4f0a14b6f156ec2082bb10bb51bd0616a1dab65a422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:59.271765Z","signature_b64":"iz8dqu/HYflMZXMhujUmK8YNJ4Kpgp9G0/QgG0stZi6bnQv6sXnSTxMYsQEBY30pa84vZ4bThPY3Siflg62MAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab50f166944f02d9a7afc4f0a14b6f156ec2082bb10bb51bd0616a1dab65a422","last_reissued_at":"2026-07-05T05:19:59.271399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:59.271399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.15058","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":"2026-07-05T05:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Jof8avW8OKpoF+Gu3EfpK7+C2L4pbKWXlgx7/joyp2eKIRtZzvX253/AOQcSmduz4fkFEXq+axdW0THBQh3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:19:15.079479Z"},"content_sha256":"f1eaf2dd43f8c7fd5c4cc242675cc1b83d887ece45e635ffa9ae5253a945a47d","schema_version":"1.0","event_id":"sha256:f1eaf2dd43f8c7fd5c4cc242675cc1b83d887ece45e635ffa9ae5253a945a47d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VNIPCZUUJ4BNTJ5PYTYKCS3PCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mix and Localize: Localizing Sound Sources in Mixtures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Xixi Hu, Ziyang Chen","submitted_at":"2022-11-28T04:30:50Z","abstract_excerpt":"We present a method for simultaneously localizing multiple sound sources within a visual scene. This task requires a model to both group a sound mixture into individual sources, and to associate them with a visual signal. Our method jointly solves both tasks at once, using a formulation inspired by the contrastive random walk of Jabri et al. We create a graph in which images and separated sounds correspond to nodes, and train a random walker to transition between nodes from different modalities with high return probability. The transition probabilities for this walk are determined by an audio-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15058","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/2211.15058/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":"2026-07-05T05:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3KftR0P/EoKZlqldLqstNs8LR3DuegvqT4H816BBSBOaD74ucHkzleOdh5v6Rj3MzfVYKhAOh8eCalx438DCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:19:15.079987Z"},"content_sha256":"9fe4fc52f79dee91675a1bfc6a2a41e941d44f1fbdfa8fac6c74380eab86168a","schema_version":"1.0","event_id":"sha256:9fe4fc52f79dee91675a1bfc6a2a41e941d44f1fbdfa8fac6c74380eab86168a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VNIPCZUUJ4BNTJ5PYTYKCS3PCV/bundle.json","state_url":"https://pith.science/pith/VNIPCZUUJ4BNTJ5PYTYKCS3PCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VNIPCZUUJ4BNTJ5PYTYKCS3PCV/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":"2026-08-13T04:19:15Z","links":{"resolver":"https://pith.science/pith/VNIPCZUUJ4BNTJ5PYTYKCS3PCV","bundle":"https://pith.science/pith/VNIPCZUUJ4BNTJ5PYTYKCS3PCV/bundle.json","state":"https://pith.science/pith/VNIPCZUUJ4BNTJ5PYTYKCS3PCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VNIPCZUUJ4BNTJ5PYTYKCS3PCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VNIPCZUUJ4BNTJ5PYTYKCS3PCV","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":"fee8fb50b196eca80b9684828957172f8b4ed4dec0d36b666599046b5aa3607e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T04:30:50Z","title_canon_sha256":"169f080188fc102b1fa1c554bf665de718e91f10f796fdca2546936f6e2cff88"},"schema_version":"1.0","source":{"id":"2211.15058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15058","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15058v1","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15058","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"VNIPCZUUJ4BN","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"VNIPCZUUJ4BNTJ5P","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"VNIPCZUU","created_at":"2026-07-05T05:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:9fe4fc52f79dee91675a1bfc6a2a41e941d44f1fbdfa8fac6c74380eab86168a","target":"graph","created_at":"2026-07-05T05:19:59Z","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/2211.15058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a method for simultaneously localizing multiple sound sources within a visual scene. This task requires a model to both group a sound mixture into individual sources, and to associate them with a visual signal. Our method jointly solves both tasks at once, using a formulation inspired by the contrastive random walk of Jabri et al. We create a graph in which images and separated sounds correspond to nodes, and train a random walker to transition between nodes from different modalities with high return probability. The transition probabilities for this walk are determined by an audio-","authors_text":"Andrew Owens, Xixi Hu, Ziyang Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T04:30:50Z","title":"Mix and Localize: Localizing Sound Sources in Mixtures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15058","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:f1eaf2dd43f8c7fd5c4cc242675cc1b83d887ece45e635ffa9ae5253a945a47d","target":"record","created_at":"2026-07-05T05:19:59Z","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":"fee8fb50b196eca80b9684828957172f8b4ed4dec0d36b666599046b5aa3607e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T04:30:50Z","title_canon_sha256":"169f080188fc102b1fa1c554bf665de718e91f10f796fdca2546936f6e2cff88"},"schema_version":"1.0","source":{"id":"2211.15058","kind":"arxiv","version":1}},"canonical_sha256":"ab50f166944f02d9a7afc4f0a14b6f156ec2082bb10bb51bd0616a1dab65a422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab50f166944f02d9a7afc4f0a14b6f156ec2082bb10bb51bd0616a1dab65a422","first_computed_at":"2026-07-05T05:19:59.271399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:59.271399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iz8dqu/HYflMZXMhujUmK8YNJ4Kpgp9G0/QgG0stZi6bnQv6sXnSTxMYsQEBY30pa84vZ4bThPY3Siflg62MAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:59.271765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.15058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1eaf2dd43f8c7fd5c4cc242675cc1b83d887ece45e635ffa9ae5253a945a47d","sha256:9fe4fc52f79dee91675a1bfc6a2a41e941d44f1fbdfa8fac6c74380eab86168a"],"state_sha256":"fd56904ac146f1a2f0b36e901b5c13989dc6f52ae20f4ec53bb4f4e3de200292"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bqRL/LescZalG7453VEhlCtL1xMSHTZsTivplQnHu+pfQHk9l6lZ3hzKrKtDGLEzdFDT4lx5AmIm/ydoyP3hAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:19:15.085658Z","bundle_sha256":"fcc2e14b3853666c9381e3da6dc5fd83c7a1e90d1e29c0fddb55d4d06a310696"}}