{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WCBNEV3S5VRTI6SUEIHD7CDCR3","short_pith_number":"pith:WCBNEV3S","schema_version":"1.0","canonical_sha256":"b082d25772ed63347a54220e3f88628ec8ecf011ebb92cf0546cb7138da7de9e","source":{"kind":"arxiv","id":"2305.08191","version":1},"attestation_state":"computed","paper":{"title":"Is end-to-end learning enough for fitness activity recognition?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Antoine Mercier, Cornelius Boehm, Florian Letsch, Guillaume Berger, Ingo Bax, Nahua Kang, Roland Memisevic, Sunny Panchal","submitted_at":"2023-05-14T16:00:03Z","abstract_excerpt":"End-to-end learning has taken hold of many computer vision tasks, in particular, related to still images, with task-specific optimization yielding very strong performance. Nevertheless, human-centric action recognition is still largely dominated by hand-crafted pipelines, and only individual components are replaced by neural networks that typically operate on individual frames. As a testbed to study the relevance of such pipelines, we present a new fully annotated video dataset of fitness activities. Any recognition capabilities in this domain are almost exclusively a function of human poses a"},"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":"2305.08191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-14T16:00:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a08f41ce67e5e6bc532847ef8838c1f448dcef828656c5c3d78eec35798f1d3","abstract_canon_sha256":"e0680bf36ee04df7370d5311f28d08cad19fafed71752bad040262af22d0b336"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:58.631038Z","signature_b64":"cqeipiLBel5CMsoyWeTXB7EWCvCdmf8pEAawd/MBVTHL4ZDdzWqAo0KOe6+Ma0o6zhRf7/lbISPcZJm+gA3qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b082d25772ed63347a54220e3f88628ec8ecf011ebb92cf0546cb7138da7de9e","last_reissued_at":"2026-07-05T06:09:58.630600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:58.630600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is end-to-end learning enough for fitness activity recognition?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Antoine Mercier, Cornelius Boehm, Florian Letsch, Guillaume Berger, Ingo Bax, Nahua Kang, Roland Memisevic, Sunny Panchal","submitted_at":"2023-05-14T16:00:03Z","abstract_excerpt":"End-to-end learning has taken hold of many computer vision tasks, in particular, related to still images, with task-specific optimization yielding very strong performance. Nevertheless, human-centric action recognition is still largely dominated by hand-crafted pipelines, and only individual components are replaced by neural networks that typically operate on individual frames. As a testbed to study the relevance of such pipelines, we present a new fully annotated video dataset of fitness activities. Any recognition capabilities in this domain are almost exclusively a function of human poses a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08191","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/2305.08191/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":"2305.08191","created_at":"2026-07-05T06:09:58.630657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08191v1","created_at":"2026-07-05T06:09:58.630657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08191","created_at":"2026-07-05T06:09:58.630657+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCBNEV3S5VRT","created_at":"2026-07-05T06:09:58.630657+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCBNEV3S5VRTI6SU","created_at":"2026-07-05T06:09:58.630657+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCBNEV3S","created_at":"2026-07-05T06:09:58.630657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.08101","citing_title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3","json":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3.json","graph_json":"https://pith.science/api/pith-number/WCBNEV3S5VRTI6SUEIHD7CDCR3/graph.json","events_json":"https://pith.science/api/pith-number/WCBNEV3S5VRTI6SUEIHD7CDCR3/events.json","paper":"https://pith.science/paper/WCBNEV3S"},"agent_actions":{"view_html":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3","download_json":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3.json","view_paper":"https://pith.science/paper/WCBNEV3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08191&json=true","fetch_graph":"https://pith.science/api/pith-number/WCBNEV3S5VRTI6SUEIHD7CDCR3/graph.json","fetch_events":"https://pith.science/api/pith-number/WCBNEV3S5VRTI6SUEIHD7CDCR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3/action/storage_attestation","attest_author":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3/action/author_attestation","sign_citation":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3/action/citation_signature","submit_replication":"https://pith.science/pith/WCBNEV3S5VRTI6SUEIHD7CDCR3/action/replication_record"}},"created_at":"2026-07-05T06:09:58.630657+00:00","updated_at":"2026-07-05T06:09:58.630657+00:00"}