{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:B5WYZOL4NR7NQUCNVUAXJZVXGU","short_pith_number":"pith:B5WYZOL4","canonical_record":{"source":{"id":"2605.28192","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T09:11:59Z","cross_cats_sorted":[],"title_canon_sha256":"ae46831945d101e045cf9a7b0b9eeed0d56ba96f08bb0c20553f67b23583c731","abstract_canon_sha256":"35ba513bd54bf945f677ad532cd0583e226e9e402b8e85cc3b2085b224ce12ae"},"schema_version":"1.0"},"canonical_sha256":"0f6d8cb97c6c7ed8504dad0174e6b7352a9ca54ed64ffa2fde2ebc5cc9060005","source":{"kind":"arxiv","id":"2605.28192","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28192","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28192v1","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28192","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"B5WYZOL4NR7N","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"B5WYZOL4NR7NQUCN","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"B5WYZOL4","created_at":"2026-05-28T01:05:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:B5WYZOL4NR7NQUCNVUAXJZVXGU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28192","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T09:11:59Z","cross_cats_sorted":[],"title_canon_sha256":"ae46831945d101e045cf9a7b0b9eeed0d56ba96f08bb0c20553f67b23583c731","abstract_canon_sha256":"35ba513bd54bf945f677ad532cd0583e226e9e402b8e85cc3b2085b224ce12ae"},"schema_version":"1.0"},"canonical_sha256":"0f6d8cb97c6c7ed8504dad0174e6b7352a9ca54ed64ffa2fde2ebc5cc9060005","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:01.795862Z","signature_b64":"ZYPp0jYBCo4Yp+Se3/rsFp7aeiRhcYr9IRX0Mca1XWDUB9WJ0lvZ2GOXS5TmLKdColq7EUfBnGwLXn+CElRHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f6d8cb97c6c7ed8504dad0174e6b7352a9ca54ed64ffa2fde2ebc5cc9060005","last_reissued_at":"2026-05-28T01:05:01.795443Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:01.795443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28192","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tLKHNsyJjGvMkA+bwBMps8kamcWWJDVSBSbphE58p53vYaHEBYht7fEAFo5aGqx4OoLh9IkbT8/Q44fUQ5WAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:29:33.400394Z"},"content_sha256":"625533086fe5106a240f763e4522e1b41d3e8e39e46de6f286f692b4a2211a87","schema_version":"1.0","event_id":"sha256:625533086fe5106a240f763e4522e1b41d3e8e39e46de6f286f692b4a2211a87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:B5WYZOL4NR7NQUCNVUAXJZVXGU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongcheng Liu, Ke Xu, Yanfeng Wang, Yuhao Wang, Yu Wang, Ziyang Cheng","submitted_at":"2026-05-27T09:11:59Z","abstract_excerpt":"Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often sparse, temporally dispersed, and distributed across both audio and visual streams. Existing benchmarks provide limited investigation of this setting, typically involving only a limited number of modalities, relevant temporal segments, or reasoning steps. In this work, we introduce MOV-Bench, a benchmark containing 519 carefully curated questions that require multi-hop reasoning over temporally dispersed audio-visual evidence. Evaluations on MOV-Bench reveal that current Omni-LLMs still struggle w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28192","kind":"arxiv","version":1},"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/2605.28192/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":"2026-05-28T01:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mixBNdWzxNPePtEvyhrDl36IqjE07PYpXAvwGmA8z8frEnrH0IEacVKXtUejkbN8VMJ+F+tC6DIrAMRelUaFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:29:33.400782Z"},"content_sha256":"5b041faff48499ebf2739345a87e0421dc2e4b7b54266a85909bc41d788a2403","schema_version":"1.0","event_id":"sha256:5b041faff48499ebf2739345a87e0421dc2e4b7b54266a85909bc41d788a2403"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B5WYZOL4NR7NQUCNVUAXJZVXGU/bundle.json","state_url":"https://pith.science/pith/B5WYZOL4NR7NQUCNVUAXJZVXGU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B5WYZOL4NR7NQUCNVUAXJZVXGU/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":"2026-06-04T20:29:33Z","links":{"resolver":"https://pith.science/pith/B5WYZOL4NR7NQUCNVUAXJZVXGU","bundle":"https://pith.science/pith/B5WYZOL4NR7NQUCNVUAXJZVXGU/bundle.json","state":"https://pith.science/pith/B5WYZOL4NR7NQUCNVUAXJZVXGU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B5WYZOL4NR7NQUCNVUAXJZVXGU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B5WYZOL4NR7NQUCNVUAXJZVXGU","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":"35ba513bd54bf945f677ad532cd0583e226e9e402b8e85cc3b2085b224ce12ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T09:11:59Z","title_canon_sha256":"ae46831945d101e045cf9a7b0b9eeed0d56ba96f08bb0c20553f67b23583c731"},"schema_version":"1.0","source":{"id":"2605.28192","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28192","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28192v1","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28192","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"B5WYZOL4NR7N","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"B5WYZOL4NR7NQUCN","created_at":"2026-05-28T01:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"B5WYZOL4","created_at":"2026-05-28T01:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:5b041faff48499ebf2739345a87e0421dc2e4b7b54266a85909bc41d788a2403","target":"graph","created_at":"2026-05-28T01:05:01Z","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/2605.28192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often sparse, temporally dispersed, and distributed across both audio and visual streams. Existing benchmarks provide limited investigation of this setting, typically involving only a limited number of modalities, relevant temporal segments, or reasoning steps. In this work, we introduce MOV-Bench, a benchmark containing 519 carefully curated questions that require multi-hop reasoning over temporally dispersed audio-visual evidence. Evaluations on MOV-Bench reveal that current Omni-LLMs still struggle w","authors_text":"Hongcheng Liu, Ke Xu, Yanfeng Wang, Yuhao Wang, Yu Wang, Ziyang Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T09:11:59Z","title":"Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28192","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":"sha256:625533086fe5106a240f763e4522e1b41d3e8e39e46de6f286f692b4a2211a87","target":"record","created_at":"2026-05-28T01:05:01Z","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":"35ba513bd54bf945f677ad532cd0583e226e9e402b8e85cc3b2085b224ce12ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T09:11:59Z","title_canon_sha256":"ae46831945d101e045cf9a7b0b9eeed0d56ba96f08bb0c20553f67b23583c731"},"schema_version":"1.0","source":{"id":"2605.28192","kind":"arxiv","version":1}},"canonical_sha256":"0f6d8cb97c6c7ed8504dad0174e6b7352a9ca54ed64ffa2fde2ebc5cc9060005","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f6d8cb97c6c7ed8504dad0174e6b7352a9ca54ed64ffa2fde2ebc5cc9060005","first_computed_at":"2026-05-28T01:05:01.795443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:01.795443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZYPp0jYBCo4Yp+Se3/rsFp7aeiRhcYr9IRX0Mca1XWDUB9WJ0lvZ2GOXS5TmLKdColq7EUfBnGwLXn+CElRHCw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:01.795862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28192","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:625533086fe5106a240f763e4522e1b41d3e8e39e46de6f286f692b4a2211a87","sha256:5b041faff48499ebf2739345a87e0421dc2e4b7b54266a85909bc41d788a2403"],"state_sha256":"58c5ca5ee4799e83715aac0c6a2603098671e2911d314f2e9b95d2a7aa3949df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j99no/4Lkesvb+BVFgDVZQsEg/YZOzXlZ6l4M92Hy3dmsMn3+CvHRogJQBYnAoWXV0lNBy95AbBKsS5iTR0KAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T20:29:33.402803Z","bundle_sha256":"8dbe38ced9af68d07ab1cdadfa275d26606d785190ad3647c7838ce62eac8414"}}