{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BGEUALRPDCYNMXXPABR6T4BBXA","short_pith_number":"pith:BGEUALRP","schema_version":"1.0","canonical_sha256":"0989402e2f18b0d65eef0063e9f021b82cb79d948877b7e5214b6693fe50c36b","source":{"kind":"arxiv","id":"2508.16942","version":1},"attestation_state":"computed","paper":{"title":"HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junhao Wu, Xiaomei Zhang, Xiuer Gu, Yeying Jin, Yunfeng Diao, Zhaoxin Fan, Zhenbo Song, Zhiying Li, Zhiyu Li","submitted_at":"2025-08-23T08:19:27Z","abstract_excerpt":"Evaluating human actions with clear and detailed feedback is important in areas such as sports, healthcare, and robotics, where decisions rely not only on final outcomes but also on interpretable reasoning. However, most existing methods provide only a final score without explanation or detailed analysis, limiting their practical applicability. To address this, we introduce HieroAction, a vision-language model that delivers accurate and structured assessments of human actions. HieroAction builds on two key ideas: (1) Stepwise Action Reasoning, a tailored chain of thought process designed 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":"2508.16942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-23T08:19:27Z","cross_cats_sorted":[],"title_canon_sha256":"808d9a27b60ec1c0d0d8a11991238ef3d5d091eb97e652a6a22848a04df14af1","abstract_canon_sha256":"ffdc10768f329b214f30fe630067ee343f0ce120cab382fb4e9a7ee23eed9c14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:06.871214Z","signature_b64":"U81Hs57iXQ/Atw+38shB3BoqOrtGpDq5AiIyvSwoXlizXC5qpTOJi6zWb1r9mrTxFOJVpcAKU8ggZflaX/XoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0989402e2f18b0d65eef0063e9f021b82cb79d948877b7e5214b6693fe50c36b","last_reissued_at":"2026-07-05T11:58:06.870752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:06.870752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junhao Wu, Xiaomei Zhang, Xiuer Gu, Yeying Jin, Yunfeng Diao, Zhaoxin Fan, Zhenbo Song, Zhiying Li, Zhiyu Li","submitted_at":"2025-08-23T08:19:27Z","abstract_excerpt":"Evaluating human actions with clear and detailed feedback is important in areas such as sports, healthcare, and robotics, where decisions rely not only on final outcomes but also on interpretable reasoning. However, most existing methods provide only a final score without explanation or detailed analysis, limiting their practical applicability. To address this, we introduce HieroAction, a vision-language model that delivers accurate and structured assessments of human actions. HieroAction builds on two key ideas: (1) Stepwise Action Reasoning, a tailored chain of thought process designed speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16942","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/2508.16942/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":"2508.16942","created_at":"2026-07-05T11:58:06.870805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16942v1","created_at":"2026-07-05T11:58:06.870805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16942","created_at":"2026-07-05T11:58:06.870805+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGEUALRPDCYN","created_at":"2026-07-05T11:58:06.870805+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGEUALRPDCYNMXXP","created_at":"2026-07-05T11:58:06.870805+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGEUALRP","created_at":"2026-07-05T11:58:06.870805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.27125","citing_title":"TactiPlay: Multi-Granularity Tactical Parsing and Video-Anchored Match Review for Amateur Badminton Players","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA","json":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA.json","graph_json":"https://pith.science/api/pith-number/BGEUALRPDCYNMXXPABR6T4BBXA/graph.json","events_json":"https://pith.science/api/pith-number/BGEUALRPDCYNMXXPABR6T4BBXA/events.json","paper":"https://pith.science/paper/BGEUALRP"},"agent_actions":{"view_html":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA","download_json":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA.json","view_paper":"https://pith.science/paper/BGEUALRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16942&json=true","fetch_graph":"https://pith.science/api/pith-number/BGEUALRPDCYNMXXPABR6T4BBXA/graph.json","fetch_events":"https://pith.science/api/pith-number/BGEUALRPDCYNMXXPABR6T4BBXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA/action/storage_attestation","attest_author":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA/action/author_attestation","sign_citation":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA/action/citation_signature","submit_replication":"https://pith.science/pith/BGEUALRPDCYNMXXPABR6T4BBXA/action/replication_record"}},"created_at":"2026-07-05T11:58:06.870805+00:00","updated_at":"2026-07-05T11:58:06.870805+00:00"}