{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VLWNTSMLFYEUQEE2MFU7MLUZRU","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":"a25e182a8eeb7536a45de553f363127f77cab72ea678dab328a3a357c0f68b28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:58:33Z","title_canon_sha256":"a45cde2fc901e345f8a64f3e90786433d14db5a24c4f81782501e2091e8b9c82"},"schema_version":"1.0","source":{"id":"2506.05328","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05328","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05328v2","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05328","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"VLWNTSMLFYEU","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"VLWNTSMLFYEUQEE2","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"VLWNTSML","created_at":"2026-07-05T11:40:55Z"}],"graph_snapshots":[{"event_id":"sha256:963b01911f1e6d891b0d9f3e55bcafff13e13cb53c9c4ff8f7d54f0a4728bf00","target":"graph","created_at":"2026-07-05T11:40:55Z","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/2506.05328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite progress in video understanding, current MLLMs struggle with counting tasks. Existing benchmarks are limited by short videos, close-set queries, lack of clue annotations, and weak multimodal coverage. In this paper, we introduce CG-AV-Counting, a manually-annotated clue-grounded counting benchmark with 1,027 multimodal questions and 5,845 annotated clues over 497 long videos. It supports both black-box and white-box evaluation, serving as a comprehensive testbed for both end-to-end and reasoning-based counting. To explore ways to improve model's counting capability, we propose AV-Reaso","authors_text":"Guo Chen, Lidong Lu, Tong Lu, Yicheng Liu, Zhiqi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:58:33Z","title":"AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05328","kind":"arxiv","version":2},"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":"sha256:2666c2bec7370729245bec0b7e9906d3027aa80a3a68ab112ffa9bf6ddeb0ca3","target":"record","created_at":"2026-07-05T11:40:55Z","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":"a25e182a8eeb7536a45de553f363127f77cab72ea678dab328a3a357c0f68b28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:58:33Z","title_canon_sha256":"a45cde2fc901e345f8a64f3e90786433d14db5a24c4f81782501e2091e8b9c82"},"schema_version":"1.0","source":{"id":"2506.05328","kind":"arxiv","version":2}},"canonical_sha256":"aaecd9c98b2e0948109a6169f62e998d27135dadde20c67356d0786cc984d66e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaecd9c98b2e0948109a6169f62e998d27135dadde20c67356d0786cc984d66e","first_computed_at":"2026-07-05T11:40:55.284005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:55.284005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ovT7ffqddHCE3tUzNsmGnx7mvowOdhhIN3IvwMQBjvmPTMFEYLzaC5+0p4bdxyxlwrtVunmcRTX0IYxcvk9eDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:55.284629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05328","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2666c2bec7370729245bec0b7e9906d3027aa80a3a68ab112ffa9bf6ddeb0ca3","sha256:963b01911f1e6d891b0d9f3e55bcafff13e13cb53c9c4ff8f7d54f0a4728bf00"],"state_sha256":"5c1cf853830d9bd7fb41be93b8032ae36b26def0117d3167eadb8f98153ebf5a"}