{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OCNKSYC3W3QE4FKUHC5UNU7E4W","short_pith_number":"pith:OCNKSYC3","canonical_record":{"source":{"id":"2506.07016","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T06:34:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17171a6bdf017c2816d837c87727eb9111ec0868381fe0f92c341767735f47bf","abstract_canon_sha256":"fd49b60c3c8323d756ba112d9d20b6842ff024737ba4e065544319332fe53501"},"schema_version":"1.0"},"canonical_sha256":"709aa9605bb6e04e155438bb46d3e4e5ac029acd235b2656c9051e8040b02066","source":{"kind":"arxiv","id":"2506.07016","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07016","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07016v2","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07016","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"OCNKSYC3W3QE","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"OCNKSYC3W3QE4FKU","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"OCNKSYC3","created_at":"2026-07-05T11:21:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OCNKSYC3W3QE4FKUHC5UNU7E4W","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07016","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T06:34:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17171a6bdf017c2816d837c87727eb9111ec0868381fe0f92c341767735f47bf","abstract_canon_sha256":"fd49b60c3c8323d756ba112d9d20b6842ff024737ba4e065544319332fe53501"},"schema_version":"1.0"},"canonical_sha256":"709aa9605bb6e04e155438bb46d3e4e5ac029acd235b2656c9051e8040b02066","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:15.590272Z","signature_b64":"IVwpXk/JYZRfwVD3SettuRh6ihEeVpnx6odp9LnKfXcuRIRoTwHsQAJlhS51+F+BH+/hjO9G8R9YVUMV01kIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"709aa9605bb6e04e155438bb46d3e4e5ac029acd235b2656c9051e8040b02066","last_reissued_at":"2026-07-05T11:21:15.589639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:15.589639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07016","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":"2026-07-05T11:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XoutSyqdAipA77SAlonB8L9Im4g4bLyAKW0UG0LjEJdFNZEXOSEKt8XxRhb6Upz4qu8F75LbAMdPQ2oIFwRLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:12:19.576968Z"},"content_sha256":"9ac3a34ba5068935941a83009fcfe9264aa492ba9e0b101059f989e762fc3ca8","schema_version":"1.0","event_id":"sha256:9ac3a34ba5068935941a83009fcfe9264aa492ba9e0b101059f989e762fc3ca8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OCNKSYC3W3QE4FKUHC5UNU7E4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Junjie Fei, Mohamed Elhoseiny, Mohamed Elmoghany, Salman Khan, Sanjoy Chowdhury, Sayan Nag, Yohan Abeysinghe","submitted_at":"2025-06-08T06:34:29Z","abstract_excerpt":"Large multimodal models (LMMs) have shown remarkable progress in audio-visual understanding, yet they struggle with real-world scenarios that require complex reasoning across extensive video collections. Existing benchmarks for video question answering remain limited in scope, typically involving one clip per query, which falls short of representing the challenges of large-scale, audio-visual retrieval and reasoning encountered in practical applications. To bridge this gap, we introduce a novel task named AV-HaystacksQA, where the goal is to identify salient segments across different videos in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07016","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/2506.07016/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":"2026-07-05T11:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZ58+z8c3w9UyDU5VoYBvcKIwJtz6h8FuSyv7StqT5rKwqSoDh7MYtdgsJ0LVoMxLCb8VBlYJjg4+54pZuJRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:12:19.577581Z"},"content_sha256":"9af8181a6daeba7bc3a883e2ecb35132af593341126ecab870e63c98d2ea3b42","schema_version":"1.0","event_id":"sha256:9af8181a6daeba7bc3a883e2ecb35132af593341126ecab870e63c98d2ea3b42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCNKSYC3W3QE4FKUHC5UNU7E4W/bundle.json","state_url":"https://pith.science/pith/OCNKSYC3W3QE4FKUHC5UNU7E4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCNKSYC3W3QE4FKUHC5UNU7E4W/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":"2026-08-10T02:12:19Z","links":{"resolver":"https://pith.science/pith/OCNKSYC3W3QE4FKUHC5UNU7E4W","bundle":"https://pith.science/pith/OCNKSYC3W3QE4FKUHC5UNU7E4W/bundle.json","state":"https://pith.science/pith/OCNKSYC3W3QE4FKUHC5UNU7E4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCNKSYC3W3QE4FKUHC5UNU7E4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OCNKSYC3W3QE4FKUHC5UNU7E4W","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":"fd49b60c3c8323d756ba112d9d20b6842ff024737ba4e065544319332fe53501","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T06:34:29Z","title_canon_sha256":"17171a6bdf017c2816d837c87727eb9111ec0868381fe0f92c341767735f47bf"},"schema_version":"1.0","source":{"id":"2506.07016","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07016","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07016v2","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07016","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"OCNKSYC3W3QE","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"OCNKSYC3W3QE4FKU","created_at":"2026-07-05T11:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"OCNKSYC3","created_at":"2026-07-05T11:21:15Z"}],"graph_snapshots":[{"event_id":"sha256:9af8181a6daeba7bc3a883e2ecb35132af593341126ecab870e63c98d2ea3b42","target":"graph","created_at":"2026-07-05T11:21:15Z","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/2506.07016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multimodal models (LMMs) have shown remarkable progress in audio-visual understanding, yet they struggle with real-world scenarios that require complex reasoning across extensive video collections. Existing benchmarks for video question answering remain limited in scope, typically involving one clip per query, which falls short of representing the challenges of large-scale, audio-visual retrieval and reasoning encountered in practical applications. To bridge this gap, we introduce a novel task named AV-HaystacksQA, where the goal is to identify salient segments across different videos in","authors_text":"Dinesh Manocha, Junjie Fei, Mohamed Elhoseiny, Mohamed Elmoghany, Salman Khan, Sanjoy Chowdhury, Sayan Nag, Yohan Abeysinghe","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T06:34:29Z","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07016","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":"sha256:9ac3a34ba5068935941a83009fcfe9264aa492ba9e0b101059f989e762fc3ca8","target":"record","created_at":"2026-07-05T11:21:15Z","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":"fd49b60c3c8323d756ba112d9d20b6842ff024737ba4e065544319332fe53501","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T06:34:29Z","title_canon_sha256":"17171a6bdf017c2816d837c87727eb9111ec0868381fe0f92c341767735f47bf"},"schema_version":"1.0","source":{"id":"2506.07016","kind":"arxiv","version":2}},"canonical_sha256":"709aa9605bb6e04e155438bb46d3e4e5ac029acd235b2656c9051e8040b02066","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"709aa9605bb6e04e155438bb46d3e4e5ac029acd235b2656c9051e8040b02066","first_computed_at":"2026-07-05T11:21:15.589639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:15.589639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IVwpXk/JYZRfwVD3SettuRh6ihEeVpnx6odp9LnKfXcuRIRoTwHsQAJlhS51+F+BH+/hjO9G8R9YVUMV01kIAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:15.590272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07016","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ac3a34ba5068935941a83009fcfe9264aa492ba9e0b101059f989e762fc3ca8","sha256:9af8181a6daeba7bc3a883e2ecb35132af593341126ecab870e63c98d2ea3b42"],"state_sha256":"2a05609154cb39dda0f5dda927781a94c88d41afec9096d5ef41e47826bd7dfe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4WTpctqVCV4ob25DlCE/buaztCmlYZUfJxvrvtXvpPLy5xR3FqQvbkAPmDTwwLRkVjThGaPA8eISuUtTBPt1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:12:19.583072Z","bundle_sha256":"02ebb3d8dd2cd2eb581730bfa8cfe233699ecd885edf544c6953bba99822c841"}}