{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:H2F6DXOGVPUUCZQXK5TYTZR3XW","short_pith_number":"pith:H2F6DXOG","canonical_record":{"source":{"id":"1804.07345","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-19T19:33:11Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"dadf82095724037c6386f764f0da983f3bcdae85efbac71b38f2c2a56e648b64","abstract_canon_sha256":"4b59cd5256bfb48799b6f437c893526105eedc965deea62667e03383553f95d4"},"schema_version":"1.0"},"canonical_sha256":"3e8be1ddc6abe9416617576789e63bbd91b09a152def8d8fab538f468295380a","source":{"kind":"arxiv","id":"1804.07345","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07345","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07345v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07345","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"H2F6DXOGVPUU","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"H2F6DXOGVPUUCZQX","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"H2F6DXOG","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:H2F6DXOGVPUUCZQXK5TYTZR3XW","target":"record","payload":{"canonical_record":{"source":{"id":"1804.07345","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-19T19:33:11Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"dadf82095724037c6386f764f0da983f3bcdae85efbac71b38f2c2a56e648b64","abstract_canon_sha256":"4b59cd5256bfb48799b6f437c893526105eedc965deea62667e03383553f95d4"},"schema_version":"1.0"},"canonical_sha256":"3e8be1ddc6abe9416617576789e63bbd91b09a152def8d8fab538f468295380a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:17.469329Z","signature_b64":"tWzqB1ppg8GRrd2MCzJztAQ/ImUsU3DTUcYFRmKISFg0p/VuxY/xv+9X0CtF01nAh+/hlHVumWP+pqOC1UsbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8be1ddc6abe9416617576789e63bbd91b09a152def8d8fab538f468295380a","last_reissued_at":"2026-05-18T00:11:17.468740Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:17.468740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.07345","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":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csUQ/b8FK2nw8wHobrZRjG7juUup9Z5QdcZA0QFPZtpa8vJbv1YnUJ1IEAceDnlgx225JttI45MLIEhJLdteCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T22:33:29.588371Z"},"content_sha256":"05bad3c1a2584b4850a6e35c1886467b2b8808736432c397e92d91d1df8a5d7d","schema_version":"1.0","event_id":"sha256:05bad3c1a2584b4850a6e35c1886467b2b8808736432c397e92d91d1df8a5d7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:H2F6DXOGVPUUCZQXK5TYTZR3XW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Alexey Ozerov, Ga\\\"el Richard, Ngoc Q. K. Duong, Patrick P\\'erez, Sanjeel Parekh, Slim Essid","submitted_at":"2018-04-19T19:33:11Z","abstract_excerpt":"Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events. To this end, we propose a novel multimodal framework that instantiates multiple instance learning. We show that the learnt representations are useful for classifying events and localizing their characteristic audio-visual elements. The system is trained using only video-level event labels without any timing information. An important feature of our method is its capacity to learn from unsynchronized audio-visual events. We achieve state-of-the-art r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07345","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":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ObfRDg3bHQZh/znT5dMaJQR04YK1A11nCv+FZwaNB+mLQAtPGJkSE5waB2DmkXF6l2kiII+0UIz3QlMVccdCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T22:33:29.589062Z"},"content_sha256":"fc1f0ed9cba6eccfe4b3a1fb767eb84ce806919eff30f190a1b34aa531d9dbaa","schema_version":"1.0","event_id":"sha256:fc1f0ed9cba6eccfe4b3a1fb767eb84ce806919eff30f190a1b34aa531d9dbaa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2F6DXOGVPUUCZQXK5TYTZR3XW/bundle.json","state_url":"https://pith.science/pith/H2F6DXOGVPUUCZQXK5TYTZR3XW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2F6DXOGVPUUCZQXK5TYTZR3XW/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":"2026-05-26T22:33:29Z","links":{"resolver":"https://pith.science/pith/H2F6DXOGVPUUCZQXK5TYTZR3XW","bundle":"https://pith.science/pith/H2F6DXOGVPUUCZQXK5TYTZR3XW/bundle.json","state":"https://pith.science/pith/H2F6DXOGVPUUCZQXK5TYTZR3XW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2F6DXOGVPUUCZQXK5TYTZR3XW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:H2F6DXOGVPUUCZQXK5TYTZR3XW","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":"4b59cd5256bfb48799b6f437c893526105eedc965deea62667e03383553f95d4","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-19T19:33:11Z","title_canon_sha256":"dadf82095724037c6386f764f0da983f3bcdae85efbac71b38f2c2a56e648b64"},"schema_version":"1.0","source":{"id":"1804.07345","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07345","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07345v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07345","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"H2F6DXOGVPUU","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"H2F6DXOGVPUUCZQX","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"H2F6DXOG","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:fc1f0ed9cba6eccfe4b3a1fb767eb84ce806919eff30f190a1b34aa531d9dbaa","target":"graph","created_at":"2026-05-18T00:11:17Z","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":"Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events. To this end, we propose a novel multimodal framework that instantiates multiple instance learning. We show that the learnt representations are useful for classifying events and localizing their characteristic audio-visual elements. The system is trained using only video-level event labels without any timing information. An important feature of our method is its capacity to learn from unsynchronized audio-visual events. We achieve state-of-the-art r","authors_text":"Alexey Ozerov, Ga\\\"el Richard, Ngoc Q. K. Duong, Patrick P\\'erez, Sanjeel Parekh, Slim Essid","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-19T19:33:11Z","title":"Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07345","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":"sha256:05bad3c1a2584b4850a6e35c1886467b2b8808736432c397e92d91d1df8a5d7d","target":"record","created_at":"2026-05-18T00:11:17Z","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":"4b59cd5256bfb48799b6f437c893526105eedc965deea62667e03383553f95d4","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-19T19:33:11Z","title_canon_sha256":"dadf82095724037c6386f764f0da983f3bcdae85efbac71b38f2c2a56e648b64"},"schema_version":"1.0","source":{"id":"1804.07345","kind":"arxiv","version":2}},"canonical_sha256":"3e8be1ddc6abe9416617576789e63bbd91b09a152def8d8fab538f468295380a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e8be1ddc6abe9416617576789e63bbd91b09a152def8d8fab538f468295380a","first_computed_at":"2026-05-18T00:11:17.468740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:17.468740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tWzqB1ppg8GRrd2MCzJztAQ/ImUsU3DTUcYFRmKISFg0p/VuxY/xv+9X0CtF01nAh+/hlHVumWP+pqOC1UsbDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:17.469329Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.07345","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05bad3c1a2584b4850a6e35c1886467b2b8808736432c397e92d91d1df8a5d7d","sha256:fc1f0ed9cba6eccfe4b3a1fb767eb84ce806919eff30f190a1b34aa531d9dbaa"],"state_sha256":"4f32647699420f5fe6de1200f82ce5cd44be618d19ac27da417c255504a36a07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"85rX3Im1QlJauuAvV+ulXOpIRr9lRQIzQKW3kd/hnfEBvzJ1SO3E3l9C+FuO4Ovy1N7qxotQbB+c8nL4dXxfDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T22:33:29.592789Z","bundle_sha256":"4dd347631331dc35fe64edd19939592a5886661a6b05a7e3776750a3a5a4f3b1"}}