{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FCXIMANMCLSPRRDCPP7KP4R2Y3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"281c53746db79c4cb7beceedd939c5c58cb2390183ba7506d0a68cb75be547ec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T15:45:36Z","title_canon_sha256":"3be32dc780dd623c0ba5a06003533c42f0c494005b9871de6c16ee6cbad7a7b4"},"schema_version":"1.0","source":{"id":"2507.09323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09323","created_at":"2026-07-05T11:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09323v1","created_at":"2026-07-05T11:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09323","created_at":"2026-07-05T11:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"FCXIMANMCLSP","created_at":"2026-07-05T11:36:07Z"},{"alias_kind":"pith_short_16","alias_value":"FCXIMANMCLSPRRDC","created_at":"2026-07-05T11:36:07Z"},{"alias_kind":"pith_short_8","alias_value":"FCXIMANM","created_at":"2026-07-05T11:36:07Z"}],"graph_snapshots":[{"event_id":"sha256:9bc80caf7e7dc17175988c38fd29f0dcafc0d3ce759fe139a9d4ca491c73df83","target":"graph","created_at":"2026-07-05T11:36:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.09323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans do not understand individual events in isolation; rather, they generalize concepts within classes and compare them to others. Existing audio-video pre-training paradigms only focus on the alignment of the overall audio-video modalities, without considering the reinforcement of distinguishing easily confused classes through cognitive induction and contrast during training. This paper proposes the Dynamic Inter-Class Confusion-Aware Encoder (DICCAE), an encoder that aligns audio-video representations at a fine-grained, category-level. DICCAE addresses category confusion by dynamically adj","authors_text":"Jing Yang, Kaixuan Cong, Rongkun Xue, Yifan Wang, Yiming Feng, Yuyang Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T15:45:36Z","title":"Dynamic Inter-Class Confusion-Aware Encoder for Audio-Visual Fusion in Human Activity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09323","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:54395dc9591bfddb7243f58c710a3f7c1b66486ab17f063c0ac1e55c3a8425f0","target":"record","created_at":"2026-07-05T11:36:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"281c53746db79c4cb7beceedd939c5c58cb2390183ba7506d0a68cb75be547ec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T15:45:36Z","title_canon_sha256":"3be32dc780dd623c0ba5a06003533c42f0c494005b9871de6c16ee6cbad7a7b4"},"schema_version":"1.0","source":{"id":"2507.09323","kind":"arxiv","version":1}},"canonical_sha256":"28ae8601ac12e4f8c4627bfea7f23ac6c3cee14cb16a20c3700fbb0ae771498b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28ae8601ac12e4f8c4627bfea7f23ac6c3cee14cb16a20c3700fbb0ae771498b","first_computed_at":"2026-07-05T11:36:07.268780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:07.268780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KLGOt+CKpjyK3bbnZvp54oPzKYu1llSJeRDyB/BdhVpBQZbM85MfUmdxxvnjJBl+OST2bRa84tE1x40qCPdbBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:07.269196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54395dc9591bfddb7243f58c710a3f7c1b66486ab17f063c0ac1e55c3a8425f0","sha256:9bc80caf7e7dc17175988c38fd29f0dcafc0d3ce759fe139a9d4ca491c73df83"],"state_sha256":"def9afb87a12f1c47a0e63410fa142004f5eaaae643a116cdcd51b27c13f20fc"}