{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6HXAL5WYIS3LWICYJIMKMTODL6","short_pith_number":"pith:6HXAL5WY","canonical_record":{"source":{"id":"2605.08945","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T13:33:16Z","cross_cats_sorted":[],"title_canon_sha256":"6689d8425c432d424484ede860a0dc996f665b7dbd0d2379e1be52f958c937ca","abstract_canon_sha256":"75b30d735b0dba6f1be240f6530dcbc273471cebcd907cb093f72d7853efe718"},"schema_version":"1.0"},"canonical_sha256":"f1ee05f6d844b6bb20584a18a64dc35f842805c574219a2bf10627bd6d979c58","source":{"kind":"arxiv","id":"2605.08945","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08945","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08945v2","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08945","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"6HXAL5WYIS3L","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"6HXAL5WYIS3LWICY","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"6HXAL5WY","created_at":"2026-06-23T03:13:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6HXAL5WYIS3LWICYJIMKMTODL6","target":"record","payload":{"canonical_record":{"source":{"id":"2605.08945","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T13:33:16Z","cross_cats_sorted":[],"title_canon_sha256":"6689d8425c432d424484ede860a0dc996f665b7dbd0d2379e1be52f958c937ca","abstract_canon_sha256":"75b30d735b0dba6f1be240f6530dcbc273471cebcd907cb093f72d7853efe718"},"schema_version":"1.0"},"canonical_sha256":"f1ee05f6d844b6bb20584a18a64dc35f842805c574219a2bf10627bd6d979c58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:57.826584Z","signature_b64":"gK8wY7Mh0ZVghBwqIrqyUqiZox/MUofKx4di4OGNFbOc3wU4hWRO0ExXtLkt5wIJ/WR3lxnnRWUV9XStarTbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1ee05f6d844b6bb20584a18a64dc35f842805c574219a2bf10627bd6d979c58","last_reissued_at":"2026-06-23T03:13:57.826174Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:57.826174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.08945","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohuzWgvfynXb1G03AMk4Vpmbd8SVPW6N3pwnHD//OQUny1IkX2dGdhgogutMzbppzYJqxmy2lttf5+DhUcU/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:25:57.491996Z"},"content_sha256":"25056ae2ffd33f49f0d2e63ca6557c9962d6271842e8f6395d8069e1072cc150","schema_version":"1.0","event_id":"sha256:25056ae2ffd33f49f0d2e63ca6557c9962d6271842e8f6395d8069e1072cc150"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6HXAL5WYIS3LWICYJIMKMTODL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLCR: Multi-Level Cue Refinement for Long-Term Multimodal Action Quality Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PIDNet progressively decouples and fuses RGB, flow and audio features to assess action quality more accurately than prior multimodal methods.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Chen, Nenggan Zheng, Pengfei Wang, Qiqi Li","submitted_at":"2026-05-09T13:33:16Z","abstract_excerpt":"Long-term multimodal action quality assessment (AQA) evaluates action execution in several-minute audiovisual sequences by mining discriminative quality cues for score prediction. Existing multimodal methods usually model entire sequences with a single temporal encoder and fuse modality features by direct alignment or concatenation, causing key cues to be obscured by global trends, weakened by modal redundancy, and distorted during one-shot score mapping. To address this issue, we reformulate long-term multimodal AQA as a quality cue organization problem and propose MLCR, a multi-level cue ref"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on the Rhythmic Gymnastics and Fis-V datasets show that PIDNet achieves highly competitive score correlation with favorable error control compared with existing unimodal and multimodal methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The premise that quality evidence from modalities is heterogeneous and evolves progressively, requiring specific implicit decoupling and staged fusion rather than coarse or unified modeling, which may not generalize beyond the tested gymnastics actions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PIDNet uses progressive implicit decoupling with iMambaWave and Group3M blocks to fuse multimodal cues for improved action quality assessment on gymnastics datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PIDNet progressively decouples and fuses RGB, flow and audio features to assess action quality more accurately than prior multimodal methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c178cb36642cd9a908af6cfc9d1629bfeca37083828d89ce25453c7add4e0c65"},"source":{"id":"2605.08945","kind":"arxiv","version":2},"verdict":{"id":"8c875dcd-a519-4776-a194-64077edc9ba6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T02:27:05.956018Z","strongest_claim":"Experiments on the Rhythmic Gymnastics and Fis-V datasets show that PIDNet achieves highly competitive score correlation with favorable error control compared with existing unimodal and multimodal methods.","one_line_summary":"PIDNet uses progressive implicit decoupling with iMambaWave and Group3M blocks to fuse multimodal cues for improved action quality assessment on gymnastics datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The premise that quality evidence from modalities is heterogeneous and evolves progressively, requiring specific implicit decoupling and staged fusion rather than coarse or unified modeling, which may not generalize beyond the tested gymnastics actions.","pith_extraction_headline":"PIDNet progressively decouples and fuses RGB, flow and audio features to assess action quality more accurately than prior multimodal methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08945/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T08:42:01.916249Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T20:40:51.430171Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:19.720343Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:40:06.191927Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a8832ecd2d3c137f2c1ae88529bfc190d2f8259eb1f1778e9f4e59d4f7c458b2"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8736a315dcb2edd99767863bf90e493a21dbe6ed149df777512c662c0da23d52"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"8c875dcd-a519-4776-a194-64077edc9ba6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NcQMGpnNunjCvt6plzksHs7SxpjZN3vlaK8H/rqoGX2jav642jNue9MyaAlteq8f9C91ztJkpYwvPBpW5QJrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:25:57.492734Z"},"content_sha256":"60997221467659e0b7dd7dc336e4785c1cfe55d1db12e0a3680105506a5902e1","schema_version":"1.0","event_id":"sha256:60997221467659e0b7dd7dc336e4785c1cfe55d1db12e0a3680105506a5902e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HXAL5WYIS3LWICYJIMKMTODL6/bundle.json","state_url":"https://pith.science/pith/6HXAL5WYIS3LWICYJIMKMTODL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HXAL5WYIS3LWICYJIMKMTODL6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T17:25:57Z","links":{"resolver":"https://pith.science/pith/6HXAL5WYIS3LWICYJIMKMTODL6","bundle":"https://pith.science/pith/6HXAL5WYIS3LWICYJIMKMTODL6/bundle.json","state":"https://pith.science/pith/6HXAL5WYIS3LWICYJIMKMTODL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HXAL5WYIS3LWICYJIMKMTODL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6HXAL5WYIS3LWICYJIMKMTODL6","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":"75b30d735b0dba6f1be240f6530dcbc273471cebcd907cb093f72d7853efe718","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T13:33:16Z","title_canon_sha256":"6689d8425c432d424484ede860a0dc996f665b7dbd0d2379e1be52f958c937ca"},"schema_version":"1.0","source":{"id":"2605.08945","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08945","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08945v2","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08945","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"6HXAL5WYIS3L","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"6HXAL5WYIS3LWICY","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"6HXAL5WY","created_at":"2026-06-23T03:13:57Z"}],"graph_snapshots":[{"event_id":"sha256:60997221467659e0b7dd7dc336e4785c1cfe55d1db12e0a3680105506a5902e1","target":"graph","created_at":"2026-06-23T03:13:57Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on the Rhythmic Gymnastics and Fis-V datasets show that PIDNet achieves highly competitive score correlation with favorable error control compared with existing unimodal and multimodal methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The premise that quality evidence from modalities is heterogeneous and evolves progressively, requiring specific implicit decoupling and staged fusion rather than coarse or unified modeling, which may not generalize beyond the tested gymnastics actions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PIDNet uses progressive implicit decoupling with iMambaWave and Group3M blocks to fuse multimodal cues for improved action quality assessment on gymnastics datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PIDNet progressively decouples and fuses RGB, flow and audio features to assess action quality more accurately than prior multimodal methods."}],"snapshot_sha256":"c178cb36642cd9a908af6cfc9d1629bfeca37083828d89ce25453c7add4e0c65"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8736a315dcb2edd99767863bf90e493a21dbe6ed149df777512c662c0da23d52"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T08:42:01.916249Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T20:40:51.430171Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:19.720343Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T10:40:06.191927Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.08945/integrity.json","findings":[],"snapshot_sha256":"a8832ecd2d3c137f2c1ae88529bfc190d2f8259eb1f1778e9f4e59d4f7c458b2","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-term multimodal action quality assessment (AQA) evaluates action execution in several-minute audiovisual sequences by mining discriminative quality cues for score prediction. Existing multimodal methods usually model entire sequences with a single temporal encoder and fuse modality features by direct alignment or concatenation, causing key cues to be obscured by global trends, weakened by modal redundancy, and distorted during one-shot score mapping. To address this issue, we reformulate long-term multimodal AQA as a quality cue organization problem and propose MLCR, a multi-level cue ref","authors_text":"Hongyu Chen, Nenggan Zheng, Pengfei Wang, Qiqi Li","cross_cats":[],"headline":"PIDNet progressively decouples and fuses RGB, flow and audio features to assess action quality more accurately than prior multimodal methods.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T13:33:16Z","title":"MLCR: Multi-Level Cue Refinement for Long-Term Multimodal Action Quality Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08945","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T02:27:05.956018Z","id":"8c875dcd-a519-4776-a194-64077edc9ba6","model_set":{"reader":"grok-4.3"},"one_line_summary":"PIDNet uses progressive implicit decoupling with iMambaWave and Group3M blocks to fuse multimodal cues for improved action quality assessment on gymnastics datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PIDNet progressively decouples and fuses RGB, flow and audio features to assess action quality more accurately than prior multimodal methods.","strongest_claim":"Experiments on the Rhythmic Gymnastics and Fis-V datasets show that PIDNet achieves highly competitive score correlation with favorable error control compared with existing unimodal and multimodal methods.","weakest_assumption":"The premise that quality evidence from modalities is heterogeneous and evolves progressively, requiring specific implicit decoupling and staged fusion rather than coarse or unified modeling, which may not generalize beyond the tested gymnastics actions."}},"verdict_id":"8c875dcd-a519-4776-a194-64077edc9ba6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:25056ae2ffd33f49f0d2e63ca6557c9962d6271842e8f6395d8069e1072cc150","target":"record","created_at":"2026-06-23T03:13:57Z","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":"75b30d735b0dba6f1be240f6530dcbc273471cebcd907cb093f72d7853efe718","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T13:33:16Z","title_canon_sha256":"6689d8425c432d424484ede860a0dc996f665b7dbd0d2379e1be52f958c937ca"},"schema_version":"1.0","source":{"id":"2605.08945","kind":"arxiv","version":2}},"canonical_sha256":"f1ee05f6d844b6bb20584a18a64dc35f842805c574219a2bf10627bd6d979c58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1ee05f6d844b6bb20584a18a64dc35f842805c574219a2bf10627bd6d979c58","first_computed_at":"2026-06-23T03:13:57.826174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:57.826174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gK8wY7Mh0ZVghBwqIrqyUqiZox/MUofKx4di4OGNFbOc3wU4hWRO0ExXtLkt5wIJ/WR3lxnnRWUV9XStarTbDg==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:57.826584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08945","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25056ae2ffd33f49f0d2e63ca6557c9962d6271842e8f6395d8069e1072cc150","sha256:60997221467659e0b7dd7dc336e4785c1cfe55d1db12e0a3680105506a5902e1"],"state_sha256":"69a071bc82dfdbe6b60f80bcb3d25d6813794bf97b239055103fb67ea7223fbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlPKfoi7+kLWuas54wlx5JLDBIlwkf/Lnjw0aw/3GvzTAMWKWjBRLmtaIruAn9NZuMCYV+QtUg3iyWlHjJJ9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:25:57.497563Z","bundle_sha256":"13b55a1d8f28190b831a2e6fe496475e4e54a354842c5a7323eec39694a086ff"}}