{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HWC2FEQDMLZHTN5GY7HPXL7X2Y","short_pith_number":"pith:HWC2FEQD","schema_version":"1.0","canonical_sha256":"3d85a2920362f279b7a6c7cefbaff7d61a31caa3bd881a8e8715b1e9e293e9fa","source":{"kind":"arxiv","id":"1807.00230","version":2},"attestation_state":"computed","paper":{"title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bruno Korbar, Du Tran, Lorenzo Torresani","submitted_at":"2018-06-30T21:50:21Z","abstract_excerpt":"There is a natural correlation between the visual and auditive elements of a video. In this work we leverage this connection to learn general and effective models for both audio and video analysis from self-supervised temporal synchronization. We demonstrate that a calibrated curriculum learning scheme, a careful choice of negative examples, and the use of a contrastive loss are critical ingredients to obtain powerful multi-sensory representations from models optimized to discern temporal synchronization of audio-video pairs. Without further finetuning, the resulting audio features achieve per"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1807.00230","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-30T21:50:21Z","cross_cats_sorted":[],"title_canon_sha256":"bd2971d2ee736d00988e09fe24656f41cad97339b3ec0fbb2c076101800ae80e","abstract_canon_sha256":"6386bfd5e91af154e24c69ef531fe0261db6a4deaef76d42c9d2ca775d99fe72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:07.244542Z","signature_b64":"FEISm+/2CgXe5k52aUxKzdtQ4h4v2U0HUYK89hB3rB5hBclw+HadvYJGv/NFTF5dTo693QlcgQwE+4Rn0z77BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d85a2920362f279b7a6c7cefbaff7d61a31caa3bd881a8e8715b1e9e293e9fa","last_reissued_at":"2026-05-18T00:01:07.243963Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:07.243963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bruno Korbar, Du Tran, Lorenzo Torresani","submitted_at":"2018-06-30T21:50:21Z","abstract_excerpt":"There is a natural correlation between the visual and auditive elements of a video. In this work we leverage this connection to learn general and effective models for both audio and video analysis from self-supervised temporal synchronization. We demonstrate that a calibrated curriculum learning scheme, a careful choice of negative examples, and the use of a contrastive loss are critical ingredients to obtain powerful multi-sensory representations from models optimized to discern temporal synchronization of audio-video pairs. Without further finetuning, the resulting audio features achieve per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00230","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.00230","created_at":"2026-05-18T00:01:07.244051+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00230v2","created_at":"2026-05-18T00:01:07.244051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00230","created_at":"2026-05-18T00:01:07.244051+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWC2FEQDMLZH","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWC2FEQDMLZHTN5G","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWC2FEQD","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20838","citing_title":"USV: Towards Understanding the User-generated Short-form Videos","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y","json":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y.json","graph_json":"https://pith.science/api/pith-number/HWC2FEQDMLZHTN5GY7HPXL7X2Y/graph.json","events_json":"https://pith.science/api/pith-number/HWC2FEQDMLZHTN5GY7HPXL7X2Y/events.json","paper":"https://pith.science/paper/HWC2FEQD"},"agent_actions":{"view_html":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y","download_json":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y.json","view_paper":"https://pith.science/paper/HWC2FEQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00230&json=true","fetch_graph":"https://pith.science/api/pith-number/HWC2FEQDMLZHTN5GY7HPXL7X2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/HWC2FEQDMLZHTN5GY7HPXL7X2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/action/storage_attestation","attest_author":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/action/author_attestation","sign_citation":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/action/citation_signature","submit_replication":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/action/replication_record"}},"created_at":"2026-05-18T00:01:07.244051+00:00","updated_at":"2026-05-18T00:01:07.244051+00:00"}