{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TZEEMXL5DFUG3SOQZZFI65YFZ2","short_pith_number":"pith:TZEEMXL5","schema_version":"1.0","canonical_sha256":"9e48465d7d19686dc9d0ce4a8f7705ce9807b51e6627f3af718ec850c93baeec","source":{"kind":"arxiv","id":"2503.16973","version":3},"attestation_state":"computed","paper":{"title":"ARFlow: Human Action-Reaction Flow Matching with Physical Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baoxiong Jia, Jingya Wang, Kaiyang Ji, Siyuan Huang, Wentao Jiang, Ye Shi","submitted_at":"2025-03-21T09:41:24Z","abstract_excerpt":"Human action-reaction synthesis, a fundamental challenge in modeling causal human interactions, plays a critical role in applications ranging from virtual reality to social robotics. While diffusion-based models have demonstrated promising performance, they exhibit two key limitations for interaction synthesis: reliance on complex noise-to-reaction generators with intricate conditional mechanisms, and frequent physical violations in generated motions. To address these issues, we propose Action-Reaction Flow Matching (ARFlow), a novel framework that establishes direct action-to-reaction mapping"},"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":"2503.16973","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T09:41:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"777b4b8996b71aa9032e6f3812c19cbae6cc69f83c488c24d62312161d1690bf","abstract_canon_sha256":"4fc8b669ed867cff2329e642f652f6e63cc79207bbd5cc8d49e0ed1b57844ff5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:05.876082Z","signature_b64":"11WJJpQPzG24TI7QXCHhYo8mNQqtfN0H23wvUpwshzWhzJxShYobXSzujNbohm/LhO2rqIVyD/Djfd2VL99NDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e48465d7d19686dc9d0ce4a8f7705ce9807b51e6627f3af718ec850c93baeec","last_reissued_at":"2026-07-05T11:14:05.875559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:05.875559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARFlow: Human Action-Reaction Flow Matching with Physical Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baoxiong Jia, Jingya Wang, Kaiyang Ji, Siyuan Huang, Wentao Jiang, Ye Shi","submitted_at":"2025-03-21T09:41:24Z","abstract_excerpt":"Human action-reaction synthesis, a fundamental challenge in modeling causal human interactions, plays a critical role in applications ranging from virtual reality to social robotics. While diffusion-based models have demonstrated promising performance, they exhibit two key limitations for interaction synthesis: reliance on complex noise-to-reaction generators with intricate conditional mechanisms, and frequent physical violations in generated motions. To address these issues, we propose Action-Reaction Flow Matching (ARFlow), a novel framework that establishes direct action-to-reaction mapping"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16973","kind":"arxiv","version":3},"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/2503.16973/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":"2503.16973","created_at":"2026-07-05T11:14:05.875623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16973v3","created_at":"2026-07-05T11:14:05.875623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16973","created_at":"2026-07-05T11:14:05.875623+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZEEMXL5DFUG","created_at":"2026-07-05T11:14:05.875623+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZEEMXL5DFUG3SOQ","created_at":"2026-07-05T11:14:05.875623+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZEEMXL5","created_at":"2026-07-05T11:14:05.875623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02106","citing_title":"Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2","json":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2.json","graph_json":"https://pith.science/api/pith-number/TZEEMXL5DFUG3SOQZZFI65YFZ2/graph.json","events_json":"https://pith.science/api/pith-number/TZEEMXL5DFUG3SOQZZFI65YFZ2/events.json","paper":"https://pith.science/paper/TZEEMXL5"},"agent_actions":{"view_html":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2","download_json":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2.json","view_paper":"https://pith.science/paper/TZEEMXL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16973&json=true","fetch_graph":"https://pith.science/api/pith-number/TZEEMXL5DFUG3SOQZZFI65YFZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/TZEEMXL5DFUG3SOQZZFI65YFZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2/action/storage_attestation","attest_author":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2/action/author_attestation","sign_citation":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2/action/citation_signature","submit_replication":"https://pith.science/pith/TZEEMXL5DFUG3SOQZZFI65YFZ2/action/replication_record"}},"created_at":"2026-07-05T11:14:05.875623+00:00","updated_at":"2026-07-05T11:14:05.875623+00:00"}