{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PHNZ4YTIN3IRCZBDQBXDCXOQ2U","short_pith_number":"pith:PHNZ4YTI","canonical_record":{"source":{"id":"2506.18071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T15:39:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9769583ff64c3e323d539a2ec053801268feee5d14d1b252691a4b60c7bf896","abstract_canon_sha256":"6e2b4604be7b7fedb924fd0d213f907659f654b00cef8a2696df5276843a9370"},"schema_version":"1.0"},"canonical_sha256":"79db9e62686ed1116423806e315dd0d5108b0ab8449447d5962171c654694776","source":{"kind":"arxiv","id":"2506.18071","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18071","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18071v2","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18071","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"pith_short_12","alias_value":"PHNZ4YTIN3IR","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"pith_short_16","alias_value":"PHNZ4YTIN3IRCZBD","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"pith_short_8","alias_value":"PHNZ4YTI","created_at":"2026-07-05T11:28:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PHNZ4YTIN3IRCZBDQBXDCXOQ2U","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T15:39:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9769583ff64c3e323d539a2ec053801268feee5d14d1b252691a4b60c7bf896","abstract_canon_sha256":"6e2b4604be7b7fedb924fd0d213f907659f654b00cef8a2696df5276843a9370"},"schema_version":"1.0"},"canonical_sha256":"79db9e62686ed1116423806e315dd0d5108b0ab8449447d5962171c654694776","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:17.808963Z","signature_b64":"vW25PdsqdPg67J4TWUwiLgA8+gGpNgrBCKWNlzR2vFhtUM8ZQjlCkrPBUvYo0EDqXKaWN5fQj7IjNK0zaSEtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79db9e62686ed1116423806e315dd0d5108b0ab8449447d5962171c654694776","last_reissued_at":"2026-07-05T11:28:17.808478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:17.808478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18071","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":"2026-07-05T11:28:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogED2p7S8Y7tyRrNlJ8D2av+Tb72E5Hu+d02l1DG5ziYKWaTjv739PcOnSc3hgQN+R+NfJ7JzFQtvQQq4T+BCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:11:52.325838Z"},"content_sha256":"959521e2ce1280a41daa6bc8c725a8093b6aee18591369d23f3e4e291e3c3843","schema_version":"1.0","event_id":"sha256:959521e2ce1280a41daa6bc8c725a8093b6aee18591369d23f3e4e291e3c3843"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PHNZ4YTIN3IRCZBDQBXDCXOQ2U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bimei Wang, Han Peng, Haoxuan Li, Huilin Song, Jisheng Dang, Junbin Xiao, Meng Wang, Tat-Seng Chua, Xun Yang","submitted_at":"2025-06-22T15:39:02Z","abstract_excerpt":"Grounded Video Question Answering (Grounded VideoQA) requires aligning textual answers with explicit visual evidence. However, modern multimodal models often rely on linguistic priors and spurious correlations, resulting in poorly grounded predictions. In this work, we propose MUPA, a cooperative MUlti-Path Agentic approach that unifies video grounding, question answering, answer reflection and aggregation to tackle Grounded VideoQA. MUPA features three distinct reasoning paths on the interplay of grounding and QA agents in different chronological orders, along with a dedicated reflection agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18071","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/2506.18071/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":"2026-07-05T11:28:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wAguqGTvyAqjgs0b7UCLVjN4tSfmKCPmB351j6foxG1xA8hJ2SpyHP0W0f7Hjs7YeiAYqs87poyooyLqcOO6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:11:52.326331Z"},"content_sha256":"8548be6969270d5dbe2c32c90e5f6af5e700483556b9ad19e4d2c2512f734618","schema_version":"1.0","event_id":"sha256:8548be6969270d5dbe2c32c90e5f6af5e700483556b9ad19e4d2c2512f734618"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PHNZ4YTIN3IRCZBDQBXDCXOQ2U/bundle.json","state_url":"https://pith.science/pith/PHNZ4YTIN3IRCZBDQBXDCXOQ2U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PHNZ4YTIN3IRCZBDQBXDCXOQ2U/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":"2026-08-03T21:11:52Z","links":{"resolver":"https://pith.science/pith/PHNZ4YTIN3IRCZBDQBXDCXOQ2U","bundle":"https://pith.science/pith/PHNZ4YTIN3IRCZBDQBXDCXOQ2U/bundle.json","state":"https://pith.science/pith/PHNZ4YTIN3IRCZBDQBXDCXOQ2U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PHNZ4YTIN3IRCZBDQBXDCXOQ2U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PHNZ4YTIN3IRCZBDQBXDCXOQ2U","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":"6e2b4604be7b7fedb924fd0d213f907659f654b00cef8a2696df5276843a9370","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T15:39:02Z","title_canon_sha256":"e9769583ff64c3e323d539a2ec053801268feee5d14d1b252691a4b60c7bf896"},"schema_version":"1.0","source":{"id":"2506.18071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18071","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18071v2","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18071","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"pith_short_12","alias_value":"PHNZ4YTIN3IR","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"pith_short_16","alias_value":"PHNZ4YTIN3IRCZBD","created_at":"2026-07-05T11:28:17Z"},{"alias_kind":"pith_short_8","alias_value":"PHNZ4YTI","created_at":"2026-07-05T11:28:17Z"}],"graph_snapshots":[{"event_id":"sha256:8548be6969270d5dbe2c32c90e5f6af5e700483556b9ad19e4d2c2512f734618","target":"graph","created_at":"2026-07-05T11:28:17Z","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/2506.18071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grounded Video Question Answering (Grounded VideoQA) requires aligning textual answers with explicit visual evidence. However, modern multimodal models often rely on linguistic priors and spurious correlations, resulting in poorly grounded predictions. In this work, we propose MUPA, a cooperative MUlti-Path Agentic approach that unifies video grounding, question answering, answer reflection and aggregation to tackle Grounded VideoQA. MUPA features three distinct reasoning paths on the interplay of grounding and QA agents in different chronological orders, along with a dedicated reflection agen","authors_text":"Bimei Wang, Han Peng, Haoxuan Li, Huilin Song, Jisheng Dang, Junbin Xiao, Meng Wang, Tat-Seng Chua, Xun Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T15:39:02Z","title":"MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18071","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":"sha256:959521e2ce1280a41daa6bc8c725a8093b6aee18591369d23f3e4e291e3c3843","target":"record","created_at":"2026-07-05T11:28:17Z","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":"6e2b4604be7b7fedb924fd0d213f907659f654b00cef8a2696df5276843a9370","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T15:39:02Z","title_canon_sha256":"e9769583ff64c3e323d539a2ec053801268feee5d14d1b252691a4b60c7bf896"},"schema_version":"1.0","source":{"id":"2506.18071","kind":"arxiv","version":2}},"canonical_sha256":"79db9e62686ed1116423806e315dd0d5108b0ab8449447d5962171c654694776","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79db9e62686ed1116423806e315dd0d5108b0ab8449447d5962171c654694776","first_computed_at":"2026-07-05T11:28:17.808478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:17.808478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vW25PdsqdPg67J4TWUwiLgA8+gGpNgrBCKWNlzR2vFhtUM8ZQjlCkrPBUvYo0EDqXKaWN5fQj7IjNK0zaSEtAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:17.808963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:959521e2ce1280a41daa6bc8c725a8093b6aee18591369d23f3e4e291e3c3843","sha256:8548be6969270d5dbe2c32c90e5f6af5e700483556b9ad19e4d2c2512f734618"],"state_sha256":"4b0316d814c874640f4d2496975b65c7e702503288b27f7354d817143692ae63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/YSVjUJDojGA1gQD7WqlP9lMAgWVGd2qgqrNxq/FOervJW5L8KTyrE7TcE38mIpQE4zl4uXIqj6VvbDh90PCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:11:52.329706Z","bundle_sha256":"8f48370098a66e3e3ede9cf9bf40834e97bf79e947c2f12d258ebb2cf6133aca"}}