{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HWC2FEQDMLZHTN5GY7HPXL7X2Y","short_pith_number":"pith:HWC2FEQD","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"},"canonical_sha256":"3d85a2920362f279b7a6c7cefbaff7d61a31caa3bd881a8e8715b1e9e293e9fa","source":{"kind":"arxiv","id":"1807.00230","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.00230","created_at":"2026-05-18T00:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"1807.00230v2","created_at":"2026-05-18T00:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00230","created_at":"2026-05-18T00:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"HWC2FEQDMLZH","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HWC2FEQDMLZHTN5G","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HWC2FEQD","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HWC2FEQDMLZHTN5GY7HPXL7X2Y","target":"record","payload":{"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"},"canonical_sha256":"3d85a2920362f279b7a6c7cefbaff7d61a31caa3bd881a8e8715b1e9e293e9fa","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"},"source_kind":"arxiv","source_id":"1807.00230","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":"2026-05-18T00:01:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OG95tcjzNfvaBsNeQIaH0epa39z/3vMeSB8kISrq/xRMAix9661oYv38dF+gJ97yoEUKPy/MWucdRzTEBFiWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T17:24:43.409706Z"},"content_sha256":"a229759a473fbc46be4d35f1796fea6e5865d98e80daab181523bd7e8bcd1dd6","schema_version":"1.0","event_id":"sha256:a229759a473fbc46be4d35f1796fea6e5865d98e80daab181523bd7e8bcd1dd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HWC2FEQDMLZHTN5GY7HPXL7X2Y","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fybdcKgGbcMOrXr0RphXGf0L2ZOV1JswcWmpj20gL4rqeQd3BRTKA6nKH8TcWg1rsFkkHQQpAIlrooTWkXc9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T17:24:43.410246Z"},"content_sha256":"28d76ddbd1bfce612b979393f9f99113b16d755d476a673c275d4b3111c9579c","schema_version":"1.0","event_id":"sha256:28d76ddbd1bfce612b979393f9f99113b16d755d476a673c275d4b3111c9579c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/bundle.json","state_url":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/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":"2026-05-24T17:24:43Z","links":{"resolver":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y","bundle":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/bundle.json","state":"https://pith.science/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HWC2FEQDMLZHTN5GY7HPXL7X2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HWC2FEQDMLZHTN5GY7HPXL7X2Y","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":"6386bfd5e91af154e24c69ef531fe0261db6a4deaef76d42c9d2ca775d99fe72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-30T21:50:21Z","title_canon_sha256":"bd2971d2ee736d00988e09fe24656f41cad97339b3ec0fbb2c076101800ae80e"},"schema_version":"1.0","source":{"id":"1807.00230","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.00230","created_at":"2026-05-18T00:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"1807.00230v2","created_at":"2026-05-18T00:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00230","created_at":"2026-05-18T00:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"HWC2FEQDMLZH","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HWC2FEQDMLZHTN5G","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HWC2FEQD","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:28d76ddbd1bfce612b979393f9f99113b16d755d476a673c275d4b3111c9579c","target":"graph","created_at":"2026-05-18T00:01:07Z","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":"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","authors_text":"Bruno Korbar, Du Tran, Lorenzo Torresani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-30T21:50:21Z","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00230","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:a229759a473fbc46be4d35f1796fea6e5865d98e80daab181523bd7e8bcd1dd6","target":"record","created_at":"2026-05-18T00:01:07Z","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":"6386bfd5e91af154e24c69ef531fe0261db6a4deaef76d42c9d2ca775d99fe72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-30T21:50:21Z","title_canon_sha256":"bd2971d2ee736d00988e09fe24656f41cad97339b3ec0fbb2c076101800ae80e"},"schema_version":"1.0","source":{"id":"1807.00230","kind":"arxiv","version":2}},"canonical_sha256":"3d85a2920362f279b7a6c7cefbaff7d61a31caa3bd881a8e8715b1e9e293e9fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d85a2920362f279b7a6c7cefbaff7d61a31caa3bd881a8e8715b1e9e293e9fa","first_computed_at":"2026-05-18T00:01:07.243963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:07.243963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FEISm+/2CgXe5k52aUxKzdtQ4h4v2U0HUYK89hB3rB5hBclw+HadvYJGv/NFTF5dTo693QlcgQwE+4Rn0z77BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:07.244542Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.00230","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a229759a473fbc46be4d35f1796fea6e5865d98e80daab181523bd7e8bcd1dd6","sha256:28d76ddbd1bfce612b979393f9f99113b16d755d476a673c275d4b3111c9579c"],"state_sha256":"c306a6a7716039d29fb55725dca0482c60e6aa6d7b9e7fea24c8d86e52e72869"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+4xjgXKEMySrSnI1U9P8o1yaSnLyxaXQbC+conpGGYCxPlSbRjfynZXRRjrRxHoA4G2aNrVYV5aTa3eKmPQeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T17:24:43.413588Z","bundle_sha256":"fb927a5163248b9357b059226e25583e833d8b96e2bc8248a457602491d31e33"}}