{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CFSHRG45YJSMMYF3LD7FPHWNCT","short_pith_number":"pith:CFSHRG45","canonical_record":{"source":{"id":"2407.05782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-08T09:45:20Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"b90dc3fb8be8d574974255704abdd6498c9a0478e1e85736289711aebd232e9c","abstract_canon_sha256":"15ffa7193505fe80007df6c6269844d61c3ee5ee7ca195a45d3c99b3526da27b"},"schema_version":"1.0"},"canonical_sha256":"1164789b9dc264c660bb58fe579ecd14ffaf87e20b8c0320ac5789fcb197d249","source":{"kind":"arxiv","id":"2407.05782","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05782","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05782v2","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05782","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"pith_short_12","alias_value":"CFSHRG45YJSM","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"pith_short_16","alias_value":"CFSHRG45YJSMMYF3","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"pith_short_8","alias_value":"CFSHRG45","created_at":"2026-07-05T10:31:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CFSHRG45YJSMMYF3LD7FPHWNCT","target":"record","payload":{"canonical_record":{"source":{"id":"2407.05782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-08T09:45:20Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"b90dc3fb8be8d574974255704abdd6498c9a0478e1e85736289711aebd232e9c","abstract_canon_sha256":"15ffa7193505fe80007df6c6269844d61c3ee5ee7ca195a45d3c99b3526da27b"},"schema_version":"1.0"},"canonical_sha256":"1164789b9dc264c660bb58fe579ecd14ffaf87e20b8c0320ac5789fcb197d249","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:44.874417Z","signature_b64":"0hR5xzxIyEZ9NfyOMI1rWFmqGdwO09LCS6qvR9ejdGMriw4QuzNXxoy6h0g1uadLskgmHmRFywsnR6PMvSocBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1164789b9dc264c660bb58fe579ecd14ffaf87e20b8c0320ac5789fcb197d249","last_reissued_at":"2026-07-05T10:31:44.873747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:44.873747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.05782","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":"2026-07-05T10:31:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i2sTXD2QUkLZgVDFbVxkTuxmdYRxb2zFE1cwniRSxJ6SssKo2x+YAtwUpEPMawweVsAn6iMygskDMqXJBk6mDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:27:43.216907Z"},"content_sha256":"dffa56d9f49a869c6f6a7a8fa7258adca4c666678b62d5a24e91a36e9d6dd494","schema_version":"1.0","event_id":"sha256:dffa56d9f49a869c6f6a7a8fa7258adca4c666678b62d5a24e91a36e9d6dd494"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CFSHRG45YJSMMYF3LD7FPHWNCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sequential Contrastive Audio-Visual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chunghsin Yeh, Ioannis Tsiamas, Joan Serr\\`a, Santiago Pascual","submitted_at":"2024-07-08T09:45:20Z","abstract_excerpt":"Contrastive learning has emerged as a powerful technique in audio-visual representation learning, leveraging the natural co-occurrence of audio and visual modalities in webscale video datasets. However, conventional contrastive audio-visual learning (CAV) methodologies often rely on aggregated representations derived through temporal aggregation, neglecting the intrinsic sequential nature of the data. This oversight raises concerns regarding the ability of standard approaches to capture and utilize fine-grained information within sequences. In response to this limitation, we propose sequential"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05782","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/2407.05782/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":"2026-07-05T10:31:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kq4hEu8YTlm2wadFxM76/Ujs+CxUFmdpH381C1AeEwbUbevpMo3noBweV2YXbCTh5TeqDLgnBiv4akP13k5KCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:27:43.217486Z"},"content_sha256":"4d72fcf08d9fc82419c5c5482c338507af6cf14856c82657c338d0a8fed7af76","schema_version":"1.0","event_id":"sha256:4d72fcf08d9fc82419c5c5482c338507af6cf14856c82657c338d0a8fed7af76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CFSHRG45YJSMMYF3LD7FPHWNCT/bundle.json","state_url":"https://pith.science/pith/CFSHRG45YJSMMYF3LD7FPHWNCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CFSHRG45YJSMMYF3LD7FPHWNCT/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":"2026-08-08T07:27:43Z","links":{"resolver":"https://pith.science/pith/CFSHRG45YJSMMYF3LD7FPHWNCT","bundle":"https://pith.science/pith/CFSHRG45YJSMMYF3LD7FPHWNCT/bundle.json","state":"https://pith.science/pith/CFSHRG45YJSMMYF3LD7FPHWNCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CFSHRG45YJSMMYF3LD7FPHWNCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CFSHRG45YJSMMYF3LD7FPHWNCT","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":"15ffa7193505fe80007df6c6269844d61c3ee5ee7ca195a45d3c99b3526da27b","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-08T09:45:20Z","title_canon_sha256":"b90dc3fb8be8d574974255704abdd6498c9a0478e1e85736289711aebd232e9c"},"schema_version":"1.0","source":{"id":"2407.05782","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05782","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05782v2","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05782","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"pith_short_12","alias_value":"CFSHRG45YJSM","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"pith_short_16","alias_value":"CFSHRG45YJSMMYF3","created_at":"2026-07-05T10:31:44Z"},{"alias_kind":"pith_short_8","alias_value":"CFSHRG45","created_at":"2026-07-05T10:31:44Z"}],"graph_snapshots":[{"event_id":"sha256:4d72fcf08d9fc82419c5c5482c338507af6cf14856c82657c338d0a8fed7af76","target":"graph","created_at":"2026-07-05T10:31:44Z","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/2407.05782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive learning has emerged as a powerful technique in audio-visual representation learning, leveraging the natural co-occurrence of audio and visual modalities in webscale video datasets. However, conventional contrastive audio-visual learning (CAV) methodologies often rely on aggregated representations derived through temporal aggregation, neglecting the intrinsic sequential nature of the data. This oversight raises concerns regarding the ability of standard approaches to capture and utilize fine-grained information within sequences. In response to this limitation, we propose sequential","authors_text":"Chunghsin Yeh, Ioannis Tsiamas, Joan Serr\\`a, Santiago Pascual","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-08T09:45:20Z","title":"Sequential Contrastive Audio-Visual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05782","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:dffa56d9f49a869c6f6a7a8fa7258adca4c666678b62d5a24e91a36e9d6dd494","target":"record","created_at":"2026-07-05T10:31:44Z","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":"15ffa7193505fe80007df6c6269844d61c3ee5ee7ca195a45d3c99b3526da27b","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-08T09:45:20Z","title_canon_sha256":"b90dc3fb8be8d574974255704abdd6498c9a0478e1e85736289711aebd232e9c"},"schema_version":"1.0","source":{"id":"2407.05782","kind":"arxiv","version":2}},"canonical_sha256":"1164789b9dc264c660bb58fe579ecd14ffaf87e20b8c0320ac5789fcb197d249","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1164789b9dc264c660bb58fe579ecd14ffaf87e20b8c0320ac5789fcb197d249","first_computed_at":"2026-07-05T10:31:44.873747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:44.873747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0hR5xzxIyEZ9NfyOMI1rWFmqGdwO09LCS6qvR9ejdGMriw4QuzNXxoy6h0g1uadLskgmHmRFywsnR6PMvSocBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:44.874417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05782","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dffa56d9f49a869c6f6a7a8fa7258adca4c666678b62d5a24e91a36e9d6dd494","sha256:4d72fcf08d9fc82419c5c5482c338507af6cf14856c82657c338d0a8fed7af76"],"state_sha256":"b448c59b0b740719ee7a946ff09ba1c7127d3d8c819c1efee5a801c63c8586ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gPFV72yZGhcqOb+9r1bjY3tb6EyY6FEBFEPvdtAXtFh5dlKI56Rx4CXT46cH1F0Mp8h/h094ZXAd9KsREoE3Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:27:43.221832Z","bundle_sha256":"4dde407ab3df42608300121e25c596c4167d0994052ef19dccb628c9a1f4e436"}}