{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZLXXXV77E6GM23POZU2WZZTRKU","short_pith_number":"pith:ZLXXXV77","canonical_record":{"source":{"id":"2103.15916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T19:52:29Z","cross_cats_sorted":[],"title_canon_sha256":"02fe108362f807d6c029f61dfde078ceb6532fca1812aafc49010381ba77fbcb","abstract_canon_sha256":"8c7446acfc334b454c306c673faf6b78f0030d6c4ee90e46ced5ab46ebee25fb"},"schema_version":"1.0"},"canonical_sha256":"caef7bd7ff278ccd6deecd356ce6715527e22f4a4d577965c998bdbfbf0deffe","source":{"kind":"arxiv","id":"2103.15916","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15916","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15916v1","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15916","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZLXXXV77E6GM","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZLXXXV77E6GM23PO","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZLXXXV77","created_at":"2026-07-05T02:27:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZLXXXV77E6GM23POZU2WZZTRKU","target":"record","payload":{"canonical_record":{"source":{"id":"2103.15916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T19:52:29Z","cross_cats_sorted":[],"title_canon_sha256":"02fe108362f807d6c029f61dfde078ceb6532fca1812aafc49010381ba77fbcb","abstract_canon_sha256":"8c7446acfc334b454c306c673faf6b78f0030d6c4ee90e46ced5ab46ebee25fb"},"schema_version":"1.0"},"canonical_sha256":"caef7bd7ff278ccd6deecd356ce6715527e22f4a4d577965c998bdbfbf0deffe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:12.048465Z","signature_b64":"dWZZZpPoHAMVb16AYpVyFxCWB/fQpHIK8RRFgJucSC1NuxRiQ5I0oYZHdGvSmGoddduYmlA1U4vxUDee4nO+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caef7bd7ff278ccd6deecd356ce6715527e22f4a4d577965c998bdbfbf0deffe","last_reissued_at":"2026-07-05T02:27:12.047994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:12.047994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.15916","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":"2026-07-05T02:27:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FVjGQaV5qBev1+Bs4H3SUqrecoghIcJ4GqiOf+ywzZVwX5NlHsGfAuY6fl3rLdShdqpe5X5d/Y9TJh854gq5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:23:17.164231Z"},"content_sha256":"2865d7b224a228881692cc95b604c067dc79f0f0b5589fc6c895a04d647de413","schema_version":"1.0","event_id":"sha256:2865d7b224a228881692cc95b604c067dc79f0f0b5589fc6c895a04d647de413"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZLXXXV77E6GM23POZU2WZZTRKU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Audio-Visual Instance Discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ishan Misra, Nuno Vasconcelos, Pedro Morgado","submitted_at":"2021-03-29T19:52:29Z","abstract_excerpt":"We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is trained to match representations from the two modalities. However, the standard approach introduces two sources of training noise. First, audio-visual correspondences often produce faulty positives since the audio and video signals can be uninformative of each other. To limit the detrimental impact of faulty positives, we optimize a weighted contrastive learning l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15916","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/2103.15916/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":"2026-07-05T02:27:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dO3EgINAUuQWazj+mXLfQPJMvMdRnW18F2snSQa42SvaDGrJ0dd8Tvpkz2tTowJMBXTt7/Y1iCj/ka+jLeY4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:23:17.164729Z"},"content_sha256":"3fe548b2015a351206f310a4952f024a49552a9915fa27a56d15f198e70ccada","schema_version":"1.0","event_id":"sha256:3fe548b2015a351206f310a4952f024a49552a9915fa27a56d15f198e70ccada"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLXXXV77E6GM23POZU2WZZTRKU/bundle.json","state_url":"https://pith.science/pith/ZLXXXV77E6GM23POZU2WZZTRKU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLXXXV77E6GM23POZU2WZZTRKU/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":"2026-08-22T05:23:17Z","links":{"resolver":"https://pith.science/pith/ZLXXXV77E6GM23POZU2WZZTRKU","bundle":"https://pith.science/pith/ZLXXXV77E6GM23POZU2WZZTRKU/bundle.json","state":"https://pith.science/pith/ZLXXXV77E6GM23POZU2WZZTRKU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLXXXV77E6GM23POZU2WZZTRKU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZLXXXV77E6GM23POZU2WZZTRKU","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":"8c7446acfc334b454c306c673faf6b78f0030d6c4ee90e46ced5ab46ebee25fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T19:52:29Z","title_canon_sha256":"02fe108362f807d6c029f61dfde078ceb6532fca1812aafc49010381ba77fbcb"},"schema_version":"1.0","source":{"id":"2103.15916","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15916","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15916v1","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15916","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZLXXXV77E6GM","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZLXXXV77E6GM23PO","created_at":"2026-07-05T02:27:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZLXXXV77","created_at":"2026-07-05T02:27:12Z"}],"graph_snapshots":[{"event_id":"sha256:3fe548b2015a351206f310a4952f024a49552a9915fa27a56d15f198e70ccada","target":"graph","created_at":"2026-07-05T02:27:12Z","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/2103.15916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is trained to match representations from the two modalities. However, the standard approach introduces two sources of training noise. First, audio-visual correspondences often produce faulty positives since the audio and video signals can be uninformative of each other. To limit the detrimental impact of faulty positives, we optimize a weighted contrastive learning l","authors_text":"Ishan Misra, Nuno Vasconcelos, Pedro Morgado","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T19:52:29Z","title":"Robust Audio-Visual Instance Discrimination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15916","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":"sha256:2865d7b224a228881692cc95b604c067dc79f0f0b5589fc6c895a04d647de413","target":"record","created_at":"2026-07-05T02:27:12Z","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":"8c7446acfc334b454c306c673faf6b78f0030d6c4ee90e46ced5ab46ebee25fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T19:52:29Z","title_canon_sha256":"02fe108362f807d6c029f61dfde078ceb6532fca1812aafc49010381ba77fbcb"},"schema_version":"1.0","source":{"id":"2103.15916","kind":"arxiv","version":1}},"canonical_sha256":"caef7bd7ff278ccd6deecd356ce6715527e22f4a4d577965c998bdbfbf0deffe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caef7bd7ff278ccd6deecd356ce6715527e22f4a4d577965c998bdbfbf0deffe","first_computed_at":"2026-07-05T02:27:12.047994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:27:12.047994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dWZZZpPoHAMVb16AYpVyFxCWB/fQpHIK8RRFgJucSC1NuxRiQ5I0oYZHdGvSmGoddduYmlA1U4vxUDee4nO+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:27:12.048465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.15916","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2865d7b224a228881692cc95b604c067dc79f0f0b5589fc6c895a04d647de413","sha256:3fe548b2015a351206f310a4952f024a49552a9915fa27a56d15f198e70ccada"],"state_sha256":"60970cd33e8a4eab124ad26732ecb4e74d8a4f59d5c27d4f56ad80ef1bd5c706"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z7WKi7SmWfRYPG8io3ivQLt0iu487jyx5eLpd+sq34Z3nIogv7iHcOXnV9RXxxrNkNVYh799efUx9gASEBzYAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T05:23:17.168724Z","bundle_sha256":"806c1fb56b918261179627ff1ade253ded6c3fbd08f8602c21287ae5294f9d86"}}