{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P7S3CVUYFATB6CO2ZK5MACC3NK","short_pith_number":"pith:P7S3CVUY","schema_version":"1.0","canonical_sha256":"7fe5b1569828261f09dacabac0085b6a81810b87e0b147f4c1e47091f1d86a69","source":{"kind":"arxiv","id":"2307.07265","version":1},"attestation_state":"computed","paper":{"title":"AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kin Wai Lau, Lan Ma, Yasar Abbas Ur Rehman, Yuyang Xie","submitted_at":"2023-07-14T10:39:05Z","abstract_excerpt":"This report presents the technical details of our submission to the 2023 Epic-Kitchen EPIC-SOUNDS Audio-Based Interaction Recognition Challenge. The task is to learn the mapping from audio samples to their corresponding action labels. To achieve this goal, we propose a simple yet effective single-stream CNN-based architecture called AudioInceptionNeXt that operates on the time-frequency log-mel-spectrogram of the audio samples. Motivated by the design of the InceptionNeXt, we propose parallel multi-scale depthwise separable convolutional kernels in the AudioInceptionNeXt block, which enable th"},"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":"2307.07265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-14T10:39:05Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"1960234263dbfebbbea751c272ff7f299e513d3cd532eaaf757b5c717e3ede27","abstract_canon_sha256":"023d9da39a0e61c451e2009013ae0d2304f668b62f19a26d2643dbea6e03d52e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:53.467810Z","signature_b64":"lhnd9JdYkehDNAXydBHm2awAqrw7YP4ZeFt6WITytUH5xp2Hevp5AridEsNct7fRFC8xrRU8C8tB6AntWWydBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe5b1569828261f09dacabac0085b6a81810b87e0b147f4c1e47091f1d86a69","last_reissued_at":"2026-07-05T06:30:53.467408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:53.467408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kin Wai Lau, Lan Ma, Yasar Abbas Ur Rehman, Yuyang Xie","submitted_at":"2023-07-14T10:39:05Z","abstract_excerpt":"This report presents the technical details of our submission to the 2023 Epic-Kitchen EPIC-SOUNDS Audio-Based Interaction Recognition Challenge. The task is to learn the mapping from audio samples to their corresponding action labels. To achieve this goal, we propose a simple yet effective single-stream CNN-based architecture called AudioInceptionNeXt that operates on the time-frequency log-mel-spectrogram of the audio samples. Motivated by the design of the InceptionNeXt, we propose parallel multi-scale depthwise separable convolutional kernels in the AudioInceptionNeXt block, which enable th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07265","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/2307.07265/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":"2307.07265","created_at":"2026-07-05T06:30:53.467478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07265v1","created_at":"2026-07-05T06:30:53.467478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07265","created_at":"2026-07-05T06:30:53.467478+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7S3CVUYFATB","created_at":"2026-07-05T06:30:53.467478+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7S3CVUYFATB6CO2","created_at":"2026-07-05T06:30:53.467478+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7S3CVUY","created_at":"2026-07-05T06:30:53.467478+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/P7S3CVUYFATB6CO2ZK5MACC3NK","json":"https://pith.science/pith/P7S3CVUYFATB6CO2ZK5MACC3NK.json","graph_json":"https://pith.science/api/pith-number/P7S3CVUYFATB6CO2ZK5MACC3NK/graph.json","events_json":"https://pith.science/api/pith-number/P7S3CVUYFATB6CO2ZK5MACC3NK/events.json","paper":"https://pith.science/paper/P7S3CVUY"},"agent_actions":{"view_html":"https://pith.science/pith/P7S3CVUYFATB6CO2ZK5MACC3NK","download_json":"https://pith.science/pith/P7S3CVUYFATB6CO2ZK5MACC3NK.json","view_paper":"https://pith.science/paper/P7S3CVUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07265&json=true","fetch_graph":"https://pith.science/api/pith-number/P7S3CVUYFATB6CO2ZK5MACC3NK/graph.json","fetch_events":"https://pith.science/api/pith-number/P7S3CVUYFATB6CO2ZK5MACC3NK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7S3CVUYFATB6CO2ZK5MACC3NK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7S3CVUYFATB6CO2ZK5MACC3NK/action/storage_attestation","attest_author":"https://pith.science/pith/P7S3CVUYFATB6CO2ZK5MACC3NK/action/author_attestation","sign_citation":"https://pith.science/pith/P7S3CVUYFATB6CO2ZK5MACC3NK/action/citation_signature","submit_replication":"https://pith.science/pith/P7S3CVUYFATB6CO2ZK5MACC3NK/action/replication_record"}},"created_at":"2026-07-05T06:30:53.467478+00:00","updated_at":"2026-07-05T06:30:53.467478+00:00"}