{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PSHTJBXIQBVCTW7UFGUXNBT2EK","short_pith_number":"pith:PSHTJBXI","schema_version":"1.0","canonical_sha256":"7c8f3486e8806a29dbf429a976867a2287817205c1750fbf676bb7c7593d6782","source":{"kind":"arxiv","id":"2506.13458","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Cristina Mahanta, Gagan Bhatia","submitted_at":"2025-06-16T13:15:02Z","abstract_excerpt":"Recognising human activity in a single photo enables indexing, safety and assistive applications, yet lacks motion cues. Using 285 MSCOCO images labelled as walking, running, sitting, and standing, scratch CNNs scored 41% accuracy. Fine-tuning multimodal CLIP raised this to 76%, demonstrating that contrastive vision-language pre-training decisively improves still-image action recognition in real-world deployments."},"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":"2506.13458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-16T13:15:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b8521320de48164226cc9d285afdd621ae5b18451361d220ac3a6044b9265bde","abstract_canon_sha256":"8ff00ab27a5e88fa699f738f586710fafba3813bb3ea55eb02d4a6be1936131b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:20.345503Z","signature_b64":"wC3vrak/hgjutvFrb17vm3j9/d8dkEKc9EfM8dx8J0rcS0zjsqJlpqmLCsAM9UFtRqJc3sSax2M+mTwQSm0gDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c8f3486e8806a29dbf429a976867a2287817205c1750fbf676bb7c7593d6782","last_reissued_at":"2026-07-05T11:22:20.344864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:20.344864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Cristina Mahanta, Gagan Bhatia","submitted_at":"2025-06-16T13:15:02Z","abstract_excerpt":"Recognising human activity in a single photo enables indexing, safety and assistive applications, yet lacks motion cues. Using 285 MSCOCO images labelled as walking, running, sitting, and standing, scratch CNNs scored 41% accuracy. Fine-tuning multimodal CLIP raised this to 76%, demonstrating that contrastive vision-language pre-training decisively improves still-image action recognition in real-world deployments."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13458","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/2506.13458/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":"2506.13458","created_at":"2026-07-05T11:22:20.344934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13458v1","created_at":"2026-07-05T11:22:20.344934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13458","created_at":"2026-07-05T11:22:20.344934+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSHTJBXIQBVC","created_at":"2026-07-05T11:22:20.344934+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSHTJBXIQBVCTW7U","created_at":"2026-07-05T11:22:20.344934+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSHTJBXI","created_at":"2026-07-05T11:22:20.344934+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/PSHTJBXIQBVCTW7UFGUXNBT2EK","json":"https://pith.science/pith/PSHTJBXIQBVCTW7UFGUXNBT2EK.json","graph_json":"https://pith.science/api/pith-number/PSHTJBXIQBVCTW7UFGUXNBT2EK/graph.json","events_json":"https://pith.science/api/pith-number/PSHTJBXIQBVCTW7UFGUXNBT2EK/events.json","paper":"https://pith.science/paper/PSHTJBXI"},"agent_actions":{"view_html":"https://pith.science/pith/PSHTJBXIQBVCTW7UFGUXNBT2EK","download_json":"https://pith.science/pith/PSHTJBXIQBVCTW7UFGUXNBT2EK.json","view_paper":"https://pith.science/paper/PSHTJBXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13458&json=true","fetch_graph":"https://pith.science/api/pith-number/PSHTJBXIQBVCTW7UFGUXNBT2EK/graph.json","fetch_events":"https://pith.science/api/pith-number/PSHTJBXIQBVCTW7UFGUXNBT2EK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSHTJBXIQBVCTW7UFGUXNBT2EK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSHTJBXIQBVCTW7UFGUXNBT2EK/action/storage_attestation","attest_author":"https://pith.science/pith/PSHTJBXIQBVCTW7UFGUXNBT2EK/action/author_attestation","sign_citation":"https://pith.science/pith/PSHTJBXIQBVCTW7UFGUXNBT2EK/action/citation_signature","submit_replication":"https://pith.science/pith/PSHTJBXIQBVCTW7UFGUXNBT2EK/action/replication_record"}},"created_at":"2026-07-05T11:22:20.344934+00:00","updated_at":"2026-07-05T11:22:20.344934+00:00"}