{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WW7UJ32FIFR4UE3OTCGXS3KYWY","short_pith_number":"pith:WW7UJ32F","canonical_record":{"source":{"id":"1705.08168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-23T10:37:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0be33856381606f9ecbbfcbc71c78762fd289df8794d6418b267e0a609f7400e","abstract_canon_sha256":"5c25c238871d95b63ece62b92df76c12d928130188d954d65903973e0d7595f8"},"schema_version":"1.0"},"canonical_sha256":"b5bf44ef454163ca136e988d796d58b6228e6f0710417418b614b9d4a9ada4d3","source":{"kind":"arxiv","id":"1705.08168","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08168","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08168v2","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08168","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"WW7UJ32FIFR4","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WW7UJ32FIFR4UE3O","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WW7UJ32F","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WW7UJ32FIFR4UE3OTCGXS3KYWY","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-23T10:37:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0be33856381606f9ecbbfcbc71c78762fd289df8794d6418b267e0a609f7400e","abstract_canon_sha256":"5c25c238871d95b63ece62b92df76c12d928130188d954d65903973e0d7595f8"},"schema_version":"1.0"},"canonical_sha256":"b5bf44ef454163ca136e988d796d58b6228e6f0710417418b614b9d4a9ada4d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:06.479104Z","signature_b64":"02U8qKPpTGgOXFKhkGu1TG+GDZt5DRnck2UNv0RVnx7ADYfqLAcjn4F0MMPqSdPPK3RmjIrwvOIvptXjVgWIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5bf44ef454163ca136e988d796d58b6228e6f0710417418b614b9d4a9ada4d3","last_reissued_at":"2026-05-18T00:39:06.478479Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:06.478479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08168","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":"2026-05-18T00:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FxTwTUjnjtwOR6OgJCyEBa+D963PPDxcpvpPH6ZvU3TneCuPly7J+YWmvq3BoGRw0s1MHpFqub3waVq+WsopCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:22:34.768175Z"},"content_sha256":"b44e4c9a3c4d3d9a7b276be0320bf0de9ac9dc85f148fabb23a9d457ddba20cf","schema_version":"1.0","event_id":"sha256:b44e4c9a3c4d3d9a7b276be0320bf0de9ac9dc85f148fabb23a9d457ddba20cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WW7UJ32FIFR4UE3OTCGXS3KYWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Look, Listen and Learn","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Relja Arandjelovi\\'c","submitted_at":"2017-05-23T10:37:54Z","abstract_excerpt":"We consider the question: what can be learnt by looking at and listening to a large number of unlabelled videos? There is a valuable, but so far untapped, source of information contained in the video itself -- the correspondence between the visual and the audio streams, and we introduce a novel \"Audio-Visual Correspondence\" learning task that makes use of this. Training visual and audio networks from scratch, without any additional supervision other than the raw unconstrained videos themselves, is shown to successfully solve this task, and, more interestingly, result in good visual and audio r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08168","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":"2026-05-18T00:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RhnFF/SrrpCjvuHbytPtP79sWEmU2I8PcemR8PVpfwx4i8r7cRyQ4iXqu76qRhE6XoXUOimN6qcj1oFDI7AkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:22:34.768897Z"},"content_sha256":"1416fca9dbc5d6642e9a3614b78772d956cd3eefffaf748b398f74097329cb8f","schema_version":"1.0","event_id":"sha256:1416fca9dbc5d6642e9a3614b78772d956cd3eefffaf748b398f74097329cb8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WW7UJ32FIFR4UE3OTCGXS3KYWY/bundle.json","state_url":"https://pith.science/pith/WW7UJ32FIFR4UE3OTCGXS3KYWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WW7UJ32FIFR4UE3OTCGXS3KYWY/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":"2026-05-31T19:22:34Z","links":{"resolver":"https://pith.science/pith/WW7UJ32FIFR4UE3OTCGXS3KYWY","bundle":"https://pith.science/pith/WW7UJ32FIFR4UE3OTCGXS3KYWY/bundle.json","state":"https://pith.science/pith/WW7UJ32FIFR4UE3OTCGXS3KYWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WW7UJ32FIFR4UE3OTCGXS3KYWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WW7UJ32FIFR4UE3OTCGXS3KYWY","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":"5c25c238871d95b63ece62b92df76c12d928130188d954d65903973e0d7595f8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-23T10:37:54Z","title_canon_sha256":"0be33856381606f9ecbbfcbc71c78762fd289df8794d6418b267e0a609f7400e"},"schema_version":"1.0","source":{"id":"1705.08168","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08168","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08168v2","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08168","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"WW7UJ32FIFR4","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WW7UJ32FIFR4UE3O","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WW7UJ32F","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:1416fca9dbc5d6642e9a3614b78772d956cd3eefffaf748b398f74097329cb8f","target":"graph","created_at":"2026-05-18T00:39:06Z","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"},"paper":{"abstract_excerpt":"We consider the question: what can be learnt by looking at and listening to a large number of unlabelled videos? There is a valuable, but so far untapped, source of information contained in the video itself -- the correspondence between the visual and the audio streams, and we introduce a novel \"Audio-Visual Correspondence\" learning task that makes use of this. Training visual and audio networks from scratch, without any additional supervision other than the raw unconstrained videos themselves, is shown to successfully solve this task, and, more interestingly, result in good visual and audio r","authors_text":"Andrew Zisserman, Relja Arandjelovi\\'c","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-23T10:37:54Z","title":"Look, Listen and Learn"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08168","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:b44e4c9a3c4d3d9a7b276be0320bf0de9ac9dc85f148fabb23a9d457ddba20cf","target":"record","created_at":"2026-05-18T00:39:06Z","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":"5c25c238871d95b63ece62b92df76c12d928130188d954d65903973e0d7595f8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-23T10:37:54Z","title_canon_sha256":"0be33856381606f9ecbbfcbc71c78762fd289df8794d6418b267e0a609f7400e"},"schema_version":"1.0","source":{"id":"1705.08168","kind":"arxiv","version":2}},"canonical_sha256":"b5bf44ef454163ca136e988d796d58b6228e6f0710417418b614b9d4a9ada4d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5bf44ef454163ca136e988d796d58b6228e6f0710417418b614b9d4a9ada4d3","first_computed_at":"2026-05-18T00:39:06.478479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:06.478479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"02U8qKPpTGgOXFKhkGu1TG+GDZt5DRnck2UNv0RVnx7ADYfqLAcjn4F0MMPqSdPPK3RmjIrwvOIvptXjVgWIAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:06.479104Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08168","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b44e4c9a3c4d3d9a7b276be0320bf0de9ac9dc85f148fabb23a9d457ddba20cf","sha256:1416fca9dbc5d6642e9a3614b78772d956cd3eefffaf748b398f74097329cb8f"],"state_sha256":"2d22ae6f2c26d8cdbb3c9ca02296b2247266b6f7dd0134f082975b1aa1ad1e91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D8C9obBRyqBJCQAde/OC+GDesDENXBE6CmcDUgEBBViiGKZ5OMl2rK6r/o4bO7tEIiKiIxBKApU4gDBJz7QZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:22:34.772437Z","bundle_sha256":"b3b97a90c831ab7ed8da9a5f3edfbcdfaba2bc6c1d1d834004f2c258554f9ffd"}}