{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:37RO6D3FM3Q4Z4G33CKZX3AV64","short_pith_number":"pith:37RO6D3F","canonical_record":{"source":{"id":"1712.06651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T19:52:53Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"7738b164e1b7b08d7b08ec142905c3360943e4cf218d138af3737c3c21afa56d","abstract_canon_sha256":"6fd5333b00e529a742025b2905b268355656d58bc2930ec333f85881f96307f5"},"schema_version":"1.0"},"canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","source":{"kind":"arxiv","id":"1712.06651","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06651","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06651v2","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06651","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"37RO6D3FM3Q4","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"37RO6D3FM3Q4Z4G3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"37RO6D3F","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:37RO6D3FM3Q4Z4G33CKZX3AV64","target":"record","payload":{"canonical_record":{"source":{"id":"1712.06651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T19:52:53Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"7738b164e1b7b08d7b08ec142905c3360943e4cf218d138af3737c3c21afa56d","abstract_canon_sha256":"6fd5333b00e529a742025b2905b268355656d58bc2930ec333f85881f96307f5"},"schema_version":"1.0"},"canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:47.469494Z","signature_b64":"CWyMWBH6HUly2i+db9jxmpxceBOy5XqWbVKFY7XBsEYUulaX6i3DXgyq/Hle0MoNGfbs1wOxmy3xKohjw8FOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","last_reissued_at":"2026-05-18T00:09:47.468743Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:47.468743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.06651","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":"2026-05-18T00:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xca7hlW6di5Xe4NkjiuSXqRWWrRE6eHWRzULTykjKSy0Ir9ryKT9tTZf8xr7FDagxGGD9+RBCBmV+qqQq/yrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:17:26.107970Z"},"content_sha256":"bcc17d0be25983a96aba103d44f07453cd01b0157685bc3d606cc2f74bb50b78","schema_version":"1.0","event_id":"sha256:bcc17d0be25983a96aba103d44f07453cd01b0157685bc3d606cc2f74bb50b78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:37RO6D3FM3Q4Z4G33CKZX3AV64","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Objects that Sound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Relja Arandjelovi\\'c","submitted_at":"2017-12-18T19:52:53Z","abstract_excerpt":"In this paper our objectives are, first, networks that can embed audio and visual inputs into a common space that is suitable for cross-modal retrieval; and second, a network that can localize the object that sounds in an image, given the audio signal. We achieve both these objectives by training from unlabelled video using only audio-visual correspondence (AVC) as the objective function. This is a form of cross-modal self-supervision from video.\n  To this end, we design new network architectures that can be trained for cross-modal retrieval and localizing the sound source in an image, by usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06651","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":""},"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":"2026-05-18T00:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7YwFCztYCjQEXSNid5YrMfE/xMkkPQj70XNfleygD7BPlg6l3nOvAt0d6IvIK4iTFoX2WIo1g77jHptY9X5XBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:17:26.108650Z"},"content_sha256":"f181e624613a61de5eba2112e107f8edf9982e681947694c8e441c99c670cb0d","schema_version":"1.0","event_id":"sha256:f181e624613a61de5eba2112e107f8edf9982e681947694c8e441c99c670cb0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/bundle.json","state_url":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/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":"2026-05-25T18:17:26Z","links":{"resolver":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64","bundle":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/bundle.json","state":"https://pith.science/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37RO6D3FM3Q4Z4G33CKZX3AV64/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:37RO6D3FM3Q4Z4G33CKZX3AV64","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":"6fd5333b00e529a742025b2905b268355656d58bc2930ec333f85881f96307f5","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T19:52:53Z","title_canon_sha256":"7738b164e1b7b08d7b08ec142905c3360943e4cf218d138af3737c3c21afa56d"},"schema_version":"1.0","source":{"id":"1712.06651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06651","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06651v2","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06651","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"37RO6D3FM3Q4","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"37RO6D3FM3Q4Z4G3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"37RO6D3F","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:f181e624613a61de5eba2112e107f8edf9982e681947694c8e441c99c670cb0d","target":"graph","created_at":"2026-05-18T00:09:47Z","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"},"paper":{"abstract_excerpt":"In this paper our objectives are, first, networks that can embed audio and visual inputs into a common space that is suitable for cross-modal retrieval; and second, a network that can localize the object that sounds in an image, given the audio signal. We achieve both these objectives by training from unlabelled video using only audio-visual correspondence (AVC) as the objective function. This is a form of cross-modal self-supervision from video.\n  To this end, we design new network architectures that can be trained for cross-modal retrieval and localizing the sound source in an image, by usin","authors_text":"Andrew Zisserman, Relja Arandjelovi\\'c","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T19:52:53Z","title":"Objects that Sound"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06651","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:bcc17d0be25983a96aba103d44f07453cd01b0157685bc3d606cc2f74bb50b78","target":"record","created_at":"2026-05-18T00:09:47Z","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":"6fd5333b00e529a742025b2905b268355656d58bc2930ec333f85881f96307f5","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T19:52:53Z","title_canon_sha256":"7738b164e1b7b08d7b08ec142905c3360943e4cf218d138af3737c3c21afa56d"},"schema_version":"1.0","source":{"id":"1712.06651","kind":"arxiv","version":2}},"canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfe2ef0f6566e1ccf0dbd8959bec15f721ef83854fbe0a7a9c21d7b92a1cacb2","first_computed_at":"2026-05-18T00:09:47.468743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:47.468743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CWyMWBH6HUly2i+db9jxmpxceBOy5XqWbVKFY7XBsEYUulaX6i3DXgyq/Hle0MoNGfbs1wOxmy3xKohjw8FOAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:47.469494Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.06651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcc17d0be25983a96aba103d44f07453cd01b0157685bc3d606cc2f74bb50b78","sha256:f181e624613a61de5eba2112e107f8edf9982e681947694c8e441c99c670cb0d"],"state_sha256":"8ae028fbc41d93cd7edd6d8627b3d6afd46b90dbcb83038976cc00fa39652d23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aAukC//pTPEmLBDRyaUNkdVOkJHMNM7dCEn4YIWzciQLmkyhHUxQArOP/G1mbB46l5eU0sgLrjQ0FVg6zK9MDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:17:26.112912Z","bundle_sha256":"ad7bad160adecd24c655902d737adce6db38193f8dd05bb1933b5426ca4e28bb"}}