{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DG5H4TJQVFXASQKJG5TGQHIRL2","short_pith_number":"pith:DG5H4TJQ","canonical_record":{"source":{"id":"2512.10359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T07:17:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"839d17d4c082a48b7d261a65337818febc8c3ffe1e4ab3cd37a119eefe3874ab","abstract_canon_sha256":"342358233017ecc188bfe106166a5f9ec32ad9cab26c6cfb623dc21412cca0f4"},"schema_version":"1.0"},"canonical_sha256":"19ba7e4d30a96e0941493766681d115ebd01d8b1622df24e55034de5415920e5","source":{"kind":"arxiv","id":"2512.10359","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10359","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10359v1","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10359","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"DG5H4TJQVFXA","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"DG5H4TJQVFXASQKJ","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"DG5H4TJQ","created_at":"2026-06-30T01:17:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DG5H4TJQVFXASQKJG5TGQHIRL2","target":"record","payload":{"canonical_record":{"source":{"id":"2512.10359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T07:17:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"839d17d4c082a48b7d261a65337818febc8c3ffe1e4ab3cd37a119eefe3874ab","abstract_canon_sha256":"342358233017ecc188bfe106166a5f9ec32ad9cab26c6cfb623dc21412cca0f4"},"schema_version":"1.0"},"canonical_sha256":"19ba7e4d30a96e0941493766681d115ebd01d8b1622df24e55034de5415920e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:30.666965Z","signature_b64":"+Q/8fAwF6CYxdRuRxaB7iBu4lt25GEv3JbI0xfU4uLcw9LdPw2vpA5fywSKgpdNwqEBnmc95+jZayKf8G3jWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19ba7e4d30a96e0941493766681d115ebd01d8b1622df24e55034de5415920e5","last_reissued_at":"2026-06-30T01:17:30.666221Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:30.666221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.10359","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":"2026-06-30T01:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NF2T1CbECXbe6Oq4gpWyHdkcdWnz9tJtID+bD3FwMDHUwKxCUydoW9nwNM+Fn5iLxiPuAdAMx7SeeGaHV3uSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T06:46:07.442348Z"},"content_sha256":"2c632f7195aece9ba2d93eae9cea506f9ae05ae3a30a43e55a6f83d65c92d612","schema_version":"1.0","event_id":"sha256:2c632f7195aece9ba2d93eae9cea506f9ae05ae3a30a43e55a6f83d65c92d612"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DG5H4TJQVFXASQKJG5TGQHIRL2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiashuo Cui, Meng-Hao Guo, Shuojin Yang, Sunqi Fan","submitted_at":"2025-12-11T07:17:57Z","abstract_excerpt":"Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large Language Models (MLLMs) struggle with simultaneously modeling spatial relationships within video frames and understanding the causal dynamics of temporal evolution on complex and reasoning-intensive VideoQA task. In this work, we equip MLLM with a comprehensive and extensible Video Toolkit, to enhance MLLM's spatiotemporal reasoning capabilities and ensure the harm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10359","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/2512.10359/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":"2026-06-30T01:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mFdnuTgpaaOukhllq8Iw42rti9TmwYcAjiDgXUd2nfCfWqc6kGhCXFuZ+/w81WO+bCRgHVIwVG77O1u+bQSqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T06:46:07.442744Z"},"content_sha256":"59caff3832c0b9807961cb568c0cbbaa01d9b308b964b3172f6153eae8d204ec","schema_version":"1.0","event_id":"sha256:59caff3832c0b9807961cb568c0cbbaa01d9b308b964b3172f6153eae8d204ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/bundle.json","state_url":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/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":"2026-07-01T06:46:07Z","links":{"resolver":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2","bundle":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/bundle.json","state":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DG5H4TJQVFXASQKJG5TGQHIRL2","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":"342358233017ecc188bfe106166a5f9ec32ad9cab26c6cfb623dc21412cca0f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T07:17:57Z","title_canon_sha256":"839d17d4c082a48b7d261a65337818febc8c3ffe1e4ab3cd37a119eefe3874ab"},"schema_version":"1.0","source":{"id":"2512.10359","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10359","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10359v1","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10359","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"DG5H4TJQVFXA","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"DG5H4TJQVFXASQKJ","created_at":"2026-06-30T01:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"DG5H4TJQ","created_at":"2026-06-30T01:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:59caff3832c0b9807961cb568c0cbbaa01d9b308b964b3172f6153eae8d204ec","target":"graph","created_at":"2026-06-30T01:17:30Z","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/2512.10359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large Language Models (MLLMs) struggle with simultaneously modeling spatial relationships within video frames and understanding the causal dynamics of temporal evolution on complex and reasoning-intensive VideoQA task. In this work, we equip MLLM with a comprehensive and extensible Video Toolkit, to enhance MLLM's spatiotemporal reasoning capabilities and ensure the harm","authors_text":"Jiashuo Cui, Meng-Hao Guo, Shuojin Yang, Sunqi Fan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T07:17:57Z","title":"Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10359","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":"sha256:2c632f7195aece9ba2d93eae9cea506f9ae05ae3a30a43e55a6f83d65c92d612","target":"record","created_at":"2026-06-30T01:17:30Z","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":"342358233017ecc188bfe106166a5f9ec32ad9cab26c6cfb623dc21412cca0f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T07:17:57Z","title_canon_sha256":"839d17d4c082a48b7d261a65337818febc8c3ffe1e4ab3cd37a119eefe3874ab"},"schema_version":"1.0","source":{"id":"2512.10359","kind":"arxiv","version":1}},"canonical_sha256":"19ba7e4d30a96e0941493766681d115ebd01d8b1622df24e55034de5415920e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19ba7e4d30a96e0941493766681d115ebd01d8b1622df24e55034de5415920e5","first_computed_at":"2026-06-30T01:17:30.666221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:30.666221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Q/8fAwF6CYxdRuRxaB7iBu4lt25GEv3JbI0xfU4uLcw9LdPw2vpA5fywSKgpdNwqEBnmc95+jZayKf8G3jWCQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:30.666965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.10359","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c632f7195aece9ba2d93eae9cea506f9ae05ae3a30a43e55a6f83d65c92d612","sha256:59caff3832c0b9807961cb568c0cbbaa01d9b308b964b3172f6153eae8d204ec"],"state_sha256":"69e0489ba04fa2629f7b2385fcf181803c3d45e166d3f2499e4ed3dea7203a1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pLisMZPwASnTuc75dmMqasNHItm4Gl3AVQJlueo4bdgLz8HzZkUZ8053GPAbxFOrxTIblY7M8ukLqkcNMnPVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T06:46:07.445418Z","bundle_sha256":"0ede12fac5bd96f4ba81e7d533e687e214e574b7570e4d28eb5f570ef466608b"}}