{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2RMP3SECO7YZVH7DALNF4EN5YI","short_pith_number":"pith:2RMP3SEC","schema_version":"1.0","canonical_sha256":"d458fdc88277f19a9fe302da5e11bdc22859129051664e4a5866172e9de9ba57","source":{"kind":"arxiv","id":"2011.01819","version":1},"attestation_state":"computed","paper":{"title":"Learning Representations from Audio-Visual Spatial Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nuno Vasconcelos, Pedro Morgado, Yi Li","submitted_at":"2020-11-03T16:20:04Z","abstract_excerpt":"We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual correspondence (AVC) predict whether audio and video clips originate from the same or different video instances. Audio-visual temporal synchronization (AVTS) further discriminates negative pairs originated from the same video instance but at different moments in time. While these approaches learn high-quality representations for downstream tasks such as action r"},"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":"2011.01819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-03T16:20:04Z","cross_cats_sorted":[],"title_canon_sha256":"272343f0ecd310f73d73369afeb7ab0896b9bc526e66b8a54813c4c81a694d1e","abstract_canon_sha256":"acba7424f0c0cb0b20e80427de7fc98afbc06f90035c4c64210339368845dcf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:36.286280Z","signature_b64":"+xqHCpc+Mri/cwd1ac/A46Z5e5Xe66YitSmN+K84Qk2qA3RXJog+dqeRYpPJAfbiZhP/kpCtIlljFA5xBLzkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d458fdc88277f19a9fe302da5e11bdc22859129051664e4a5866172e9de9ba57","last_reissued_at":"2026-07-05T01:48:36.285801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:36.285801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Representations from Audio-Visual Spatial Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nuno Vasconcelos, Pedro Morgado, Yi Li","submitted_at":"2020-11-03T16:20:04Z","abstract_excerpt":"We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual correspondence (AVC) predict whether audio and video clips originate from the same or different video instances. Audio-visual temporal synchronization (AVTS) further discriminates negative pairs originated from the same video instance but at different moments in time. While these approaches learn high-quality representations for downstream tasks such as action r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01819","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/2011.01819/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.01819","created_at":"2026-07-05T01:48:36.285858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.01819v1","created_at":"2026-07-05T01:48:36.285858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01819","created_at":"2026-07-05T01:48:36.285858+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RMP3SECO7YZ","created_at":"2026-07-05T01:48:36.285858+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RMP3SECO7YZVH7D","created_at":"2026-07-05T01:48:36.285858+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RMP3SEC","created_at":"2026-07-05T01:48:36.285858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI","json":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI.json","graph_json":"https://pith.science/api/pith-number/2RMP3SECO7YZVH7DALNF4EN5YI/graph.json","events_json":"https://pith.science/api/pith-number/2RMP3SECO7YZVH7DALNF4EN5YI/events.json","paper":"https://pith.science/paper/2RMP3SEC"},"agent_actions":{"view_html":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI","download_json":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI.json","view_paper":"https://pith.science/paper/2RMP3SEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.01819&json=true","fetch_graph":"https://pith.science/api/pith-number/2RMP3SECO7YZVH7DALNF4EN5YI/graph.json","fetch_events":"https://pith.science/api/pith-number/2RMP3SECO7YZVH7DALNF4EN5YI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/action/storage_attestation","attest_author":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/action/author_attestation","sign_citation":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/action/citation_signature","submit_replication":"https://pith.science/pith/2RMP3SECO7YZVH7DALNF4EN5YI/action/replication_record"}},"created_at":"2026-07-05T01:48:36.285858+00:00","updated_at":"2026-07-05T01:48:36.285858+00:00"}