{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VLWNTSMLFYEUQEE2MFU7MLUZRU","short_pith_number":"pith:VLWNTSML","canonical_record":{"source":{"id":"2506.05328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"a45cde2fc901e345f8a64f3e90786433d14db5a24c4f81782501e2091e8b9c82","abstract_canon_sha256":"a25e182a8eeb7536a45de553f363127f77cab72ea678dab328a3a357c0f68b28"},"schema_version":"1.0"},"canonical_sha256":"aaecd9c98b2e0948109a6169f62e998d27135dadde20c67356d0786cc984d66e","source":{"kind":"arxiv","id":"2506.05328","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VLWNTSMLFYEUQEE2MFU7MLUZRU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"a45cde2fc901e345f8a64f3e90786433d14db5a24c4f81782501e2091e8b9c82","abstract_canon_sha256":"a25e182a8eeb7536a45de553f363127f77cab72ea678dab328a3a357c0f68b28"},"schema_version":"1.0"},"canonical_sha256":"aaecd9c98b2e0948109a6169f62e998d27135dadde20c67356d0786cc984d66e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:55.284629Z","signature_b64":"ovT7ffqddHCE3tUzNsmGnx7mvowOdhhIN3IvwMQBjvmPTMFEYLzaC5+0p4bdxyxlwrtVunmcRTX0IYxcvk9eDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aaecd9c98b2e0948109a6169f62e998d27135dadde20c67356d0786cc984d66e","last_reissued_at":"2026-07-05T11:40:55.284005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:55.284005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05328","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":"2026-07-05T11:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G+T3HeaufgQVndX/SoJlh2Nd7ZcKqYhxwD2onxoRzczfpyy1kNUYhHlajITL5Qdtq/n2yFYR3mdpEzuOGy8xDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:36:05.031245Z"},"content_sha256":"2666c2bec7370729245bec0b7e9906d3027aa80a3a68ab112ffa9bf6ddeb0ca3","schema_version":"1.0","event_id":"sha256:2666c2bec7370729245bec0b7e9906d3027aa80a3a68ab112ffa9bf6ddeb0ca3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VLWNTSMLFYEUQEE2MFU7MLUZRU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Chen, Lidong Lu, Tong Lu, Yicheng Liu, Zhiqi Li","submitted_at":"2025-06-05T17:58:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05328","kind":"arxiv","version":2},"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/2506.05328/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+pf4aygyMs6D0jBK5hyqMKnbhxzKLxZT0E49N/z3Bf8gUcVn47psadFBnBIE+zwdzC1CL3LWQdysR4lrp6EeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:36:05.031844Z"},"content_sha256":"963b01911f1e6d891b0d9f3e55bcafff13e13cb53c9c4ff8f7d54f0a4728bf00","schema_version":"1.0","event_id":"sha256:963b01911f1e6d891b0d9f3e55bcafff13e13cb53c9c4ff8f7d54f0a4728bf00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLWNTSMLFYEUQEE2MFU7MLUZRU/bundle.json","state_url":"https://pith.science/pith/VLWNTSMLFYEUQEE2MFU7MLUZRU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLWNTSMLFYEUQEE2MFU7MLUZRU/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":"2026-08-08T00:36:05Z","links":{"resolver":"https://pith.science/pith/VLWNTSMLFYEUQEE2MFU7MLUZRU","bundle":"https://pith.science/pith/VLWNTSMLFYEUQEE2MFU7MLUZRU/bundle.json","state":"https://pith.science/pith/VLWNTSMLFYEUQEE2MFU7MLUZRU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLWNTSMLFYEUQEE2MFU7MLUZRU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6eAPGtq+sk9pbVcRTEW5uVY8hD6IzWzYkHZuGo+zdTdNpdVYbzQuexLLB8denbbOO0QENLs4XtViC0VTkY9BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:36:05.038817Z","bundle_sha256":"cd4aa80e94b106291c4c3db2c71281db129f23064f4d2ca4be7679edeb313832"}}