{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NWPHF4HNO54ZBU3QT5DT67G2LY","short_pith_number":"pith:NWPHF4HN","canonical_record":{"source":{"id":"2304.05600","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-12T04:17:45Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"e70910155fe5a85f4ea13d6d76e2cb6cc5431db90c848c3b6ab9e9822be23f18","abstract_canon_sha256":"32415a9f42162d89169e31d53939b335965792779090bab5acc3df96405f067c"},"schema_version":"1.0"},"canonical_sha256":"6d9e72f0ed777990d3709f473f7cda5e38e9b19480ed4683946f809bc61a7d45","source":{"kind":"arxiv","id":"2304.05600","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05600","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05600v2","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05600","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"NWPHF4HNO54Z","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"pith_short_16","alias_value":"NWPHF4HNO54ZBU3Q","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"pith_short_8","alias_value":"NWPHF4HN","created_at":"2026-07-05T08:28:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NWPHF4HNO54ZBU3QT5DT67G2LY","target":"record","payload":{"canonical_record":{"source":{"id":"2304.05600","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-12T04:17:45Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"e70910155fe5a85f4ea13d6d76e2cb6cc5431db90c848c3b6ab9e9822be23f18","abstract_canon_sha256":"32415a9f42162d89169e31d53939b335965792779090bab5acc3df96405f067c"},"schema_version":"1.0"},"canonical_sha256":"6d9e72f0ed777990d3709f473f7cda5e38e9b19480ed4683946f809bc61a7d45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:56.452271Z","signature_b64":"lAzMnO+oN9omGhob0/fwAHAdi7US/EmefxiaVaNz/coYQOkue795NJcIfyFRNInuvPcQ/oJyy4rY4zIQO+i1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d9e72f0ed777990d3709f473f7cda5e38e9b19480ed4683946f809bc61a7d45","last_reissued_at":"2026-07-05T08:28:56.451812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:56.451812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.05600","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":"2026-07-05T08:28:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nqqseEhFcfaaxF7fLLfyN9pBZlgea3Rle3Rqq0lKzpwSoUDSTnx4qjkpgP5e/147bLRH/iSiqnEYYzj3HwdkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:53:14.495043Z"},"content_sha256":"c8ac46fe069afb689da387a616ee3c5e372b1b4ec16eb397a74390616f33b14a","schema_version":"1.0","event_id":"sha256:c8ac46fe069afb689da387a616ee3c5e372b1b4ec16eb397a74390616f33b14a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NWPHF4HNO54ZBU3QT5DT67G2LY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chih-Wei Wu, Iroro Orife, Mahdi Kalayeh, Nikhil Singh","submitted_at":"2023-04-12T04:17:45Z","abstract_excerpt":"Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual scene. Consider, for example, different conversations on the same crowded street. The effect of such counterfactual pairs on audiovisual representation learning has not been previously explored. To investigate this, we use dubbed versions of movies and television shows to augment cross-modal contrastive learning. Our approach learns to represent alternate audio tracks, differing only in speech, similarly to the same"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05600","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.05600/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":"2026-07-05T08:28:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJPSitd2YDFqmE5TxS1eRA4NF8NevQ6m34RKuK1xdNj2sUDUdwHU/bguyXp6J40qQT1dxnBbc4v9/fzY1HBKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:53:14.495892Z"},"content_sha256":"144896e0b77983b317977dfa9d5da6d5481176ff72d0e1dba7513f497b57db11","schema_version":"1.0","event_id":"sha256:144896e0b77983b317977dfa9d5da6d5481176ff72d0e1dba7513f497b57db11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NWPHF4HNO54ZBU3QT5DT67G2LY/bundle.json","state_url":"https://pith.science/pith/NWPHF4HNO54ZBU3QT5DT67G2LY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NWPHF4HNO54ZBU3QT5DT67G2LY/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":"2026-08-05T18:53:14Z","links":{"resolver":"https://pith.science/pith/NWPHF4HNO54ZBU3QT5DT67G2LY","bundle":"https://pith.science/pith/NWPHF4HNO54ZBU3QT5DT67G2LY/bundle.json","state":"https://pith.science/pith/NWPHF4HNO54ZBU3QT5DT67G2LY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NWPHF4HNO54ZBU3QT5DT67G2LY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NWPHF4HNO54ZBU3QT5DT67G2LY","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":"32415a9f42162d89169e31d53939b335965792779090bab5acc3df96405f067c","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-12T04:17:45Z","title_canon_sha256":"e70910155fe5a85f4ea13d6d76e2cb6cc5431db90c848c3b6ab9e9822be23f18"},"schema_version":"1.0","source":{"id":"2304.05600","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05600","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05600v2","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05600","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"NWPHF4HNO54Z","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"pith_short_16","alias_value":"NWPHF4HNO54ZBU3Q","created_at":"2026-07-05T08:28:56Z"},{"alias_kind":"pith_short_8","alias_value":"NWPHF4HN","created_at":"2026-07-05T08:28:56Z"}],"graph_snapshots":[{"event_id":"sha256:144896e0b77983b317977dfa9d5da6d5481176ff72d0e1dba7513f497b57db11","target":"graph","created_at":"2026-07-05T08:28:56Z","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/2304.05600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual scene. Consider, for example, different conversations on the same crowded street. The effect of such counterfactual pairs on audiovisual representation learning has not been previously explored. To investigate this, we use dubbed versions of movies and television shows to augment cross-modal contrastive learning. Our approach learns to represent alternate audio tracks, differing only in speech, similarly to the same","authors_text":"Chih-Wei Wu, Iroro Orife, Mahdi Kalayeh, Nikhil Singh","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-12T04:17:45Z","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05600","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:c8ac46fe069afb689da387a616ee3c5e372b1b4ec16eb397a74390616f33b14a","target":"record","created_at":"2026-07-05T08:28:56Z","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":"32415a9f42162d89169e31d53939b335965792779090bab5acc3df96405f067c","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-12T04:17:45Z","title_canon_sha256":"e70910155fe5a85f4ea13d6d76e2cb6cc5431db90c848c3b6ab9e9822be23f18"},"schema_version":"1.0","source":{"id":"2304.05600","kind":"arxiv","version":2}},"canonical_sha256":"6d9e72f0ed777990d3709f473f7cda5e38e9b19480ed4683946f809bc61a7d45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d9e72f0ed777990d3709f473f7cda5e38e9b19480ed4683946f809bc61a7d45","first_computed_at":"2026-07-05T08:28:56.451812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:56.451812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lAzMnO+oN9omGhob0/fwAHAdi7US/EmefxiaVaNz/coYQOkue795NJcIfyFRNInuvPcQ/oJyy4rY4zIQO+i1Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:56.452271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05600","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8ac46fe069afb689da387a616ee3c5e372b1b4ec16eb397a74390616f33b14a","sha256:144896e0b77983b317977dfa9d5da6d5481176ff72d0e1dba7513f497b57db11"],"state_sha256":"9fe151298083479a2b623b83993af8569c382c7de927712c5e602c77a03c4636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RX9yT8njSMTgUXDsV5YLqRh5ndON2aoOXtnHKJrxjZWRXSOJ3lbSiR+T35id5lhQT3cykKQDCkhvQ3ic0w4GBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:53:14.501135Z","bundle_sha256":"0a2d4212a982c18793b69e293070bd55954ac771435a0fd0150e209a0b39f713"}}