{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KPOLUWNSPN43ODALTDZPZGILGY","short_pith_number":"pith:KPOLUWNS","schema_version":"1.0","canonical_sha256":"53dcba59b27b79b70c0b98f2fc990b360590acb108a782333578a1b3b951b5f5","source":{"kind":"arxiv","id":"2006.09199","version":2},"attestation_state":"computed","paper":{"title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Rouditchenko, Angie Boggust, Antonio Torralba, Brian Chen, Brian Kingsbury, David Harwath, Dhiraj Joshi, Hilde Kuehne, James Glass, Kartik Audhkhasi, Michael Picheny, Rameswar Panda, Rogerio Feris, Samuel Thomas","submitted_at":"2020-06-16T14:38:03Z","abstract_excerpt":"Current methods for learning visually grounded language from videos often rely on text annotation, such as human generated captions or machine generated automatic speech recognition (ASR) transcripts. In this work, we introduce the Audio-Video Language Network (AVLnet), a self-supervised network that learns a shared audio-visual embedding space directly from raw video inputs. To circumvent the need for text annotation, we learn audio-visual representations from randomly segmented video clips and their raw audio waveforms. We train AVLnet on HowTo100M, a large corpus of publicly available instr"},"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":"2006.09199","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-16T14:38:03Z","cross_cats_sorted":["cs.CL","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"e56694db694dbf751f2e90ff21987a0c7b16b3db5c290a0b3432be3af1cbc16a","abstract_canon_sha256":"d1c843fa62fb8c0bfa46f358e6fcd1111af42b02e48733dfb6bf0cf2204fde1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:51.946171Z","signature_b64":"K1pIV1uSXmemeDn9GwMl41VkTdPkDOnvMk5I2IB5NrIH1TGc0gcCIXlyxEAKtBvi7WfZpv3S0Pfdl5+35vnRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53dcba59b27b79b70c0b98f2fc990b360590acb108a782333578a1b3b951b5f5","last_reissued_at":"2026-07-05T02:53:51.945667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:51.945667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Rouditchenko, Angie Boggust, Antonio Torralba, Brian Chen, Brian Kingsbury, David Harwath, Dhiraj Joshi, Hilde Kuehne, James Glass, Kartik Audhkhasi, Michael Picheny, Rameswar Panda, Rogerio Feris, Samuel Thomas","submitted_at":"2020-06-16T14:38:03Z","abstract_excerpt":"Current methods for learning visually grounded language from videos often rely on text annotation, such as human generated captions or machine generated automatic speech recognition (ASR) transcripts. In this work, we introduce the Audio-Video Language Network (AVLnet), a self-supervised network that learns a shared audio-visual embedding space directly from raw video inputs. To circumvent the need for text annotation, we learn audio-visual representations from randomly segmented video clips and their raw audio waveforms. We train AVLnet on HowTo100M, a large corpus of publicly available instr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09199","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/2006.09199/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":"2006.09199","created_at":"2026-07-05T02:53:51.945722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09199v2","created_at":"2026-07-05T02:53:51.945722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09199","created_at":"2026-07-05T02:53:51.945722+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPOLUWNSPN43","created_at":"2026-07-05T02:53:51.945722+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPOLUWNSPN43ODAL","created_at":"2026-07-05T02:53:51.945722+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPOLUWNS","created_at":"2026-07-05T02:53:51.945722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":118,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY","json":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY.json","graph_json":"https://pith.science/api/pith-number/KPOLUWNSPN43ODALTDZPZGILGY/graph.json","events_json":"https://pith.science/api/pith-number/KPOLUWNSPN43ODALTDZPZGILGY/events.json","paper":"https://pith.science/paper/KPOLUWNS"},"agent_actions":{"view_html":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY","download_json":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY.json","view_paper":"https://pith.science/paper/KPOLUWNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09199&json=true","fetch_graph":"https://pith.science/api/pith-number/KPOLUWNSPN43ODALTDZPZGILGY/graph.json","fetch_events":"https://pith.science/api/pith-number/KPOLUWNSPN43ODALTDZPZGILGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY/action/storage_attestation","attest_author":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY/action/author_attestation","sign_citation":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY/action/citation_signature","submit_replication":"https://pith.science/pith/KPOLUWNSPN43ODALTDZPZGILGY/action/replication_record"}},"created_at":"2026-07-05T02:53:51.945722+00:00","updated_at":"2026-07-05T02:53:51.945722+00:00"}