{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2RMP3SECO7YZVH7DALNF4EN5YI","short_pith_number":"pith:2RMP3SEC","canonical_record":{"source":{"id":"2011.01819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-03T16:20:04Z","cross_cats_sorted":[],"title_canon_sha256":"272343f0ecd310f73d73369afeb7ab0896b9bc526e66b8a54813c4c81a694d1e","abstract_canon_sha256":"acba7424f0c0cb0b20e80427de7fc98afbc06f90035c4c64210339368845dcf8"},"schema_version":"1.0"},"canonical_sha256":"d458fdc88277f19a9fe302da5e11bdc22859129051664e4a5866172e9de9ba57","source":{"kind":"arxiv","id":"2011.01819","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01819","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01819v1","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01819","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"2RMP3SECO7YZ","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_16","alias_value":"2RMP3SECO7YZVH7D","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_8","alias_value":"2RMP3SEC","created_at":"2026-07-05T01:48:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2RMP3SECO7YZVH7DALNF4EN5YI","target":"record","payload":{"canonical_record":{"source":{"id":"2011.01819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-03T16:20:04Z","cross_cats_sorted":[],"title_canon_sha256":"272343f0ecd310f73d73369afeb7ab0896b9bc526e66b8a54813c4c81a694d1e","abstract_canon_sha256":"acba7424f0c0cb0b20e80427de7fc98afbc06f90035c4c64210339368845dcf8"},"schema_version":"1.0"},"canonical_sha256":"d458fdc88277f19a9fe302da5e11bdc22859129051664e4a5866172e9de9ba57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:36.286280Z","signature_b64":"+xqHCpc+Mri/cwd1ac/A46Z5e5Xe66YitSmN+K84Qk2qA3RXJog+dqeRYpPJAfbiZhP/kpCtIlljFA5xBLzkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d458fdc88277f19a9fe302da5e11bdc22859129051664e4a5866172e9de9ba57","last_reissued_at":"2026-07-05T01:48:36.285801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:36.285801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.01819","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":"2026-07-05T01:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8clRgajsZir4hjFdpaIq+tauX9qn4JyYDZUjDhJ8zpQubiSkpcTY84rQ7KynAD0xd6/MMO3wmat4DYkkYMViCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:00:37.237653Z"},"content_sha256":"a32ed2651eb5ac3359724cae023013e157fc73a7bcf6366717e7a9e6a06348e5","schema_version":"1.0","event_id":"sha256:a32ed2651eb5ac3359724cae023013e157fc73a7bcf6366717e7a9e6a06348e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2RMP3SECO7YZVH7DALNF4EN5YI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Representations from Audio-Visual Spatial Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nuno Vasconcelos, Pedro Morgado, Yi Li","submitted_at":"2020-11-03T16:20:04Z","abstract_excerpt":"We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual correspondence (AVC) predict whether audio and video clips originate from the same or different video instances. Audio-visual temporal synchronization (AVTS) further discriminates negative pairs originated from the same video instance but at different moments in time. While these approaches learn high-quality representations for downstream tasks such as action r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01819","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/2011.01819/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":"2026-07-05T01:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUSjwNC3yiQBonw7G2JtYzTPwnpZMOYDLVA7nKQysfDxqUr8YJEMNbL1V1TU+pH8Y+XY2tN5ZACF2UXnnTI3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:00:37.238144Z"},"content_sha256":"853ed79a19ed823252b49ea5cc7242e8e2109e5608fd227f145c04eaa4a8df6d","schema_version":"1.0","event_id":"sha256:853ed79a19ed823252b49ea5cc7242e8e2109e5608fd227f145c04eaa4a8df6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/bundle.json","state_url":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2RMP3SECO7YZVH7DALNF4EN5YI/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":"2026-08-04T10:00:37Z","links":{"resolver":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI","bundle":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/bundle.json","state":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2RMP3SECO7YZVH7DALNF4EN5YI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2RMP3SECO7YZVH7DALNF4EN5YI","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":"acba7424f0c0cb0b20e80427de7fc98afbc06f90035c4c64210339368845dcf8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-03T16:20:04Z","title_canon_sha256":"272343f0ecd310f73d73369afeb7ab0896b9bc526e66b8a54813c4c81a694d1e"},"schema_version":"1.0","source":{"id":"2011.01819","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01819","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01819v1","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01819","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"2RMP3SECO7YZ","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_16","alias_value":"2RMP3SECO7YZVH7D","created_at":"2026-07-05T01:48:36Z"},{"alias_kind":"pith_short_8","alias_value":"2RMP3SEC","created_at":"2026-07-05T01:48:36Z"}],"graph_snapshots":[{"event_id":"sha256:853ed79a19ed823252b49ea5cc7242e8e2109e5608fd227f145c04eaa4a8df6d","target":"graph","created_at":"2026-07-05T01:48:36Z","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/2011.01819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual correspondence (AVC) predict whether audio and video clips originate from the same or different video instances. Audio-visual temporal synchronization (AVTS) further discriminates negative pairs originated from the same video instance but at different moments in time. While these approaches learn high-quality representations for downstream tasks such as action r","authors_text":"Nuno Vasconcelos, Pedro Morgado, Yi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-03T16:20:04Z","title":"Learning Representations from Audio-Visual Spatial Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01819","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:a32ed2651eb5ac3359724cae023013e157fc73a7bcf6366717e7a9e6a06348e5","target":"record","created_at":"2026-07-05T01:48:36Z","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":"acba7424f0c0cb0b20e80427de7fc98afbc06f90035c4c64210339368845dcf8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-03T16:20:04Z","title_canon_sha256":"272343f0ecd310f73d73369afeb7ab0896b9bc526e66b8a54813c4c81a694d1e"},"schema_version":"1.0","source":{"id":"2011.01819","kind":"arxiv","version":1}},"canonical_sha256":"d458fdc88277f19a9fe302da5e11bdc22859129051664e4a5866172e9de9ba57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d458fdc88277f19a9fe302da5e11bdc22859129051664e4a5866172e9de9ba57","first_computed_at":"2026-07-05T01:48:36.285801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:36.285801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+xqHCpc+Mri/cwd1ac/A46Z5e5Xe66YitSmN+K84Qk2qA3RXJog+dqeRYpPJAfbiZhP/kpCtIlljFA5xBLzkCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:36.286280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.01819","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a32ed2651eb5ac3359724cae023013e157fc73a7bcf6366717e7a9e6a06348e5","sha256:853ed79a19ed823252b49ea5cc7242e8e2109e5608fd227f145c04eaa4a8df6d"],"state_sha256":"7c29abd8c7b5421649876eb595a884aea0ec656e91ba3b6a414c9702fdd86100"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"851PVjrLL9wPiP4/bwytRn9lmij/PLt7eEsQBPBnDjHyzDjZttE+RLjAZFKwDQsQnIlgiDjaiq9xTrwA50gCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:00:37.241877Z","bundle_sha256":"0cf15973102b32765960fb4d17784149b11e74950290120dd9dd5c75e0244382"}}