{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:S54LTZQLFQIXSAHGDQY3DK7UMQ","short_pith_number":"pith:S54LTZQL","schema_version":"1.0","canonical_sha256":"9778b9e60b2c117900e61c31b1abf464378ea216282777768347ca3a47f128a2","source":{"kind":"arxiv","id":"2003.11100","version":1},"attestation_state":"computed","paper":{"title":"How deep is your encoder: an analysis of features descriptors for an autoencoder-based audio-visual quality metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.IV"],"primary_cat":"cs.MM","authors_text":"Andrew Hines, Helard Martinez, Mylene C. Q. Farias","submitted_at":"2020-03-24T20:15:12Z","abstract_excerpt":"The development of audio-visual quality assessment models poses a number of challenges in order to obtain accurate predictions. One of these challenges is the modelling of the complex interaction that audio and visual stimuli have and how this interaction is interpreted by human users. The No-Reference Audio-Visual Quality Metric Based on a Deep Autoencoder (NAViDAd) deals with this problem from a machine learning perspective. The metric receives two sets of audio and video features descriptors and produces a low-dimensional set of features used to predict the audio-visual quality. A basic imp"},"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":"2003.11100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2020-03-24T20:15:12Z","cross_cats_sorted":["cs.CV","cs.LG","eess.IV"],"title_canon_sha256":"60b4ef083e150a8803eec5798e95c993d88bd3e80688b2ec618f8febb7afb17e","abstract_canon_sha256":"f6f4079ee81f7c2efbc289bb9e312855fc17dc46a5d6ea87f03c9219c646145a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:30.922122Z","signature_b64":"Zeq9UqmBA2TYx+wrMXtKenoGZKl9YxCZ2fY3HqAn0ITEg97WDvfAZ4WY3JIGT8EwP8M419DGqX6ppXndxHQaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9778b9e60b2c117900e61c31b1abf464378ea216282777768347ca3a47f128a2","last_reissued_at":"2026-07-05T00:50:30.921700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:30.921700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How deep is your encoder: an analysis of features descriptors for an autoencoder-based audio-visual quality metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.IV"],"primary_cat":"cs.MM","authors_text":"Andrew Hines, Helard Martinez, Mylene C. Q. Farias","submitted_at":"2020-03-24T20:15:12Z","abstract_excerpt":"The development of audio-visual quality assessment models poses a number of challenges in order to obtain accurate predictions. One of these challenges is the modelling of the complex interaction that audio and visual stimuli have and how this interaction is interpreted by human users. The No-Reference Audio-Visual Quality Metric Based on a Deep Autoencoder (NAViDAd) deals with this problem from a machine learning perspective. The metric receives two sets of audio and video features descriptors and produces a low-dimensional set of features used to predict the audio-visual quality. A basic imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11100","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/2003.11100/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":"2003.11100","created_at":"2026-07-05T00:50:30.921772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11100v1","created_at":"2026-07-05T00:50:30.921772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11100","created_at":"2026-07-05T00:50:30.921772+00:00"},{"alias_kind":"pith_short_12","alias_value":"S54LTZQLFQIX","created_at":"2026-07-05T00:50:30.921772+00:00"},{"alias_kind":"pith_short_16","alias_value":"S54LTZQLFQIXSAHG","created_at":"2026-07-05T00:50:30.921772+00:00"},{"alias_kind":"pith_short_8","alias_value":"S54LTZQL","created_at":"2026-07-05T00:50:30.921772+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/S54LTZQLFQIXSAHGDQY3DK7UMQ","json":"https://pith.science/pith/S54LTZQLFQIXSAHGDQY3DK7UMQ.json","graph_json":"https://pith.science/api/pith-number/S54LTZQLFQIXSAHGDQY3DK7UMQ/graph.json","events_json":"https://pith.science/api/pith-number/S54LTZQLFQIXSAHGDQY3DK7UMQ/events.json","paper":"https://pith.science/paper/S54LTZQL"},"agent_actions":{"view_html":"https://pith.science/pith/S54LTZQLFQIXSAHGDQY3DK7UMQ","download_json":"https://pith.science/pith/S54LTZQLFQIXSAHGDQY3DK7UMQ.json","view_paper":"https://pith.science/paper/S54LTZQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11100&json=true","fetch_graph":"https://pith.science/api/pith-number/S54LTZQLFQIXSAHGDQY3DK7UMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/S54LTZQLFQIXSAHGDQY3DK7UMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S54LTZQLFQIXSAHGDQY3DK7UMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S54LTZQLFQIXSAHGDQY3DK7UMQ/action/storage_attestation","attest_author":"https://pith.science/pith/S54LTZQLFQIXSAHGDQY3DK7UMQ/action/author_attestation","sign_citation":"https://pith.science/pith/S54LTZQLFQIXSAHGDQY3DK7UMQ/action/citation_signature","submit_replication":"https://pith.science/pith/S54LTZQLFQIXSAHGDQY3DK7UMQ/action/replication_record"}},"created_at":"2026-07-05T00:50:30.921772+00:00","updated_at":"2026-07-05T00:50:30.921772+00:00"}