{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:72GGEVK4T3VXHTC2WRFNP3L2OP","short_pith_number":"pith:72GGEVK4","schema_version":"1.0","canonical_sha256":"fe8c62555c9eeb73cc5ab44ad7ed7a73fddd0240cbb5a5e50514dcc51d129b4b","source":{"kind":"arxiv","id":"2506.11678","version":1},"attestation_state":"computed","paper":{"title":"Pose Matters: Evaluating Vision Transformers and CNNs for Human Action Recognition on Small COCO Subsets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Madiha Kazi, Mingze Tang","submitted_at":"2025-06-13T11:16:50Z","abstract_excerpt":"This study explores human action recognition using a three-class subset of the COCO image corpus, benchmarking models from simple fully connected networks to transformer architectures. The binary Vision Transformer (ViT) achieved 90% mean test accuracy, significantly exceeding multiclass classifiers such as convolutional networks (approximately 35%) and CLIP-based models (approximately 62-64%). A one-way ANOVA (F = 61.37, p < 0.001) confirmed these differences are statistically significant. Qualitative analysis with SHAP explainer and LeGrad heatmaps indicated that the ViT localizes pose-speci"},"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":"2506.11678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T11:16:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b127c757d93f53ae1db4d0c438fbb083083055eabb14e0efd717a89b089401f","abstract_canon_sha256":"00ee7616ccebceda312db8033dd2ad4a29522b61a889a6a8a3a9d73f4caa05d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:09.097805Z","signature_b64":"cS1sy9Q6OIBq9D9PuJQioIx2630l3gnkourbxIa8VcYvrfsQ5A7FzzwZ2TYNYdZeSSoveQdQfWylOfrUZH3bCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe8c62555c9eeb73cc5ab44ad7ed7a73fddd0240cbb5a5e50514dcc51d129b4b","last_reissued_at":"2026-07-05T11:21:09.097449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:09.097449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pose Matters: Evaluating Vision Transformers and CNNs for Human Action Recognition on Small COCO Subsets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Madiha Kazi, Mingze Tang","submitted_at":"2025-06-13T11:16:50Z","abstract_excerpt":"This study explores human action recognition using a three-class subset of the COCO image corpus, benchmarking models from simple fully connected networks to transformer architectures. The binary Vision Transformer (ViT) achieved 90% mean test accuracy, significantly exceeding multiclass classifiers such as convolutional networks (approximately 35%) and CLIP-based models (approximately 62-64%). A one-way ANOVA (F = 61.37, p < 0.001) confirmed these differences are statistically significant. Qualitative analysis with SHAP explainer and LeGrad heatmaps indicated that the ViT localizes pose-speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11678","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/2506.11678/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":"2506.11678","created_at":"2026-07-05T11:21:09.097514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11678v1","created_at":"2026-07-05T11:21:09.097514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11678","created_at":"2026-07-05T11:21:09.097514+00:00"},{"alias_kind":"pith_short_12","alias_value":"72GGEVK4T3VX","created_at":"2026-07-05T11:21:09.097514+00:00"},{"alias_kind":"pith_short_16","alias_value":"72GGEVK4T3VXHTC2","created_at":"2026-07-05T11:21:09.097514+00:00"},{"alias_kind":"pith_short_8","alias_value":"72GGEVK4","created_at":"2026-07-05T11:21:09.097514+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/72GGEVK4T3VXHTC2WRFNP3L2OP","json":"https://pith.science/pith/72GGEVK4T3VXHTC2WRFNP3L2OP.json","graph_json":"https://pith.science/api/pith-number/72GGEVK4T3VXHTC2WRFNP3L2OP/graph.json","events_json":"https://pith.science/api/pith-number/72GGEVK4T3VXHTC2WRFNP3L2OP/events.json","paper":"https://pith.science/paper/72GGEVK4"},"agent_actions":{"view_html":"https://pith.science/pith/72GGEVK4T3VXHTC2WRFNP3L2OP","download_json":"https://pith.science/pith/72GGEVK4T3VXHTC2WRFNP3L2OP.json","view_paper":"https://pith.science/paper/72GGEVK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11678&json=true","fetch_graph":"https://pith.science/api/pith-number/72GGEVK4T3VXHTC2WRFNP3L2OP/graph.json","fetch_events":"https://pith.science/api/pith-number/72GGEVK4T3VXHTC2WRFNP3L2OP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72GGEVK4T3VXHTC2WRFNP3L2OP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72GGEVK4T3VXHTC2WRFNP3L2OP/action/storage_attestation","attest_author":"https://pith.science/pith/72GGEVK4T3VXHTC2WRFNP3L2OP/action/author_attestation","sign_citation":"https://pith.science/pith/72GGEVK4T3VXHTC2WRFNP3L2OP/action/citation_signature","submit_replication":"https://pith.science/pith/72GGEVK4T3VXHTC2WRFNP3L2OP/action/replication_record"}},"created_at":"2026-07-05T11:21:09.097514+00:00","updated_at":"2026-07-05T11:21:09.097514+00:00"}