{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AZBQ5LRZMKYPJP6I7CDZ5UMEJY","short_pith_number":"pith:AZBQ5LRZ","canonical_record":{"source":{"id":"2508.04416","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T13:03:21Z","cross_cats_sorted":[],"title_canon_sha256":"9132807405b68c064196635658abbc1e2beb1d6338510ac952a9bfd1f32e04d2","abstract_canon_sha256":"b329c0757a26a0801fea10b5b4caaf250fd3813be3c064343b20ad89fa67915a"},"schema_version":"1.0"},"canonical_sha256":"06430eae3962b0f4bfc8f8879ed1844e347093ac45d282b0853e3d44f872648c","source":{"kind":"arxiv","id":"2508.04416","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04416","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04416v2","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04416","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"AZBQ5LRZMKYP","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"AZBQ5LRZMKYPJP6I","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"AZBQ5LRZ","created_at":"2026-07-05T12:03:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AZBQ5LRZMKYPJP6I7CDZ5UMEJY","target":"record","payload":{"canonical_record":{"source":{"id":"2508.04416","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T13:03:21Z","cross_cats_sorted":[],"title_canon_sha256":"9132807405b68c064196635658abbc1e2beb1d6338510ac952a9bfd1f32e04d2","abstract_canon_sha256":"b329c0757a26a0801fea10b5b4caaf250fd3813be3c064343b20ad89fa67915a"},"schema_version":"1.0"},"canonical_sha256":"06430eae3962b0f4bfc8f8879ed1844e347093ac45d282b0853e3d44f872648c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:50.867534Z","signature_b64":"RG//MKs5plG+8WHkI4uXH5Jb08JF920ONj9ZzH9m6vYu1NM6de3OP2tZBhGEN95t7fdUgYsbZVd6t6Oh10rIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06430eae3962b0f4bfc8f8879ed1844e347093ac45d282b0853e3d44f872648c","last_reissued_at":"2026-07-05T12:03:50.866938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:50.866938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.04416","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":"2026-07-05T12:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sl6KbgYcMgVpEArmoQTxGFOfQVo1G93f6DnPNqbq5umVYZQA2fga/IXmIsqB7wTuiar5l36Wp0NfveyJxv9KAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:39:40.309851Z"},"content_sha256":"dd52441dac3efe950ed1952a2cb4a79bdb309685be1bf25e02812b66ef7e881d","schema_version":"1.0","event_id":"sha256:dd52441dac3efe950ed1952a2cb4a79bdb309685be1bf25e02812b66ef7e881d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AZBQ5LRZMKYPJP6I7CDZ5UMEJY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Chixiang Ma, Chubin Zhang, Dongliang He, Haoji Zhang, Jiawen Li, Sule Bai, Xin Gu, Yansong Tang, Zhichao Zhou","submitted_at":"2025-08-06T13:03:21Z","abstract_excerpt":"The video reasoning ability of multimodal large language models (MLLMs) is crucial for downstream tasks like video question answering and temporal grounding. While recent approaches have explored text-based chain-of-thought (CoT) reasoning for MLLMs, these methods often suffer from limited cross-modal interaction and increased hallucination, especially with longer videos or reasoning chains. To address these challenges, we propose Video Intelligence via Tool-Augmented Learning (VITAL), a novel end-to-end agentic video reasoning framework. With a visual toolbox, the model can densely sample new"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04416","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/2508.04416/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":"2026-07-05T12:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rRWD3tX3ul2ByTmKGGMP8X8/4TRmE7VKZHq8MJhCQqk94O4iTIfzcOk8bl9622SWYf3TS9hKptD7XUbJlam9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:39:40.310394Z"},"content_sha256":"103065d6bd4611aacf5d06191027cdf7fcce218e3576ce7a41c5b2bbd18842ba","schema_version":"1.0","event_id":"sha256:103065d6bd4611aacf5d06191027cdf7fcce218e3576ce7a41c5b2bbd18842ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZBQ5LRZMKYPJP6I7CDZ5UMEJY/bundle.json","state_url":"https://pith.science/pith/AZBQ5LRZMKYPJP6I7CDZ5UMEJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZBQ5LRZMKYPJP6I7CDZ5UMEJY/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":"2026-08-09T17:39:40Z","links":{"resolver":"https://pith.science/pith/AZBQ5LRZMKYPJP6I7CDZ5UMEJY","bundle":"https://pith.science/pith/AZBQ5LRZMKYPJP6I7CDZ5UMEJY/bundle.json","state":"https://pith.science/pith/AZBQ5LRZMKYPJP6I7CDZ5UMEJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZBQ5LRZMKYPJP6I7CDZ5UMEJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AZBQ5LRZMKYPJP6I7CDZ5UMEJY","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":"b329c0757a26a0801fea10b5b4caaf250fd3813be3c064343b20ad89fa67915a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T13:03:21Z","title_canon_sha256":"9132807405b68c064196635658abbc1e2beb1d6338510ac952a9bfd1f32e04d2"},"schema_version":"1.0","source":{"id":"2508.04416","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04416","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04416v2","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04416","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"AZBQ5LRZMKYP","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"AZBQ5LRZMKYPJP6I","created_at":"2026-07-05T12:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"AZBQ5LRZ","created_at":"2026-07-05T12:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:103065d6bd4611aacf5d06191027cdf7fcce218e3576ce7a41c5b2bbd18842ba","target":"graph","created_at":"2026-07-05T12:03:50Z","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/2508.04416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The video reasoning ability of multimodal large language models (MLLMs) is crucial for downstream tasks like video question answering and temporal grounding. While recent approaches have explored text-based chain-of-thought (CoT) reasoning for MLLMs, these methods often suffer from limited cross-modal interaction and increased hallucination, especially with longer videos or reasoning chains. To address these challenges, we propose Video Intelligence via Tool-Augmented Learning (VITAL), a novel end-to-end agentic video reasoning framework. With a visual toolbox, the model can densely sample new","authors_text":"Bowen Zhang, Chixiang Ma, Chubin Zhang, Dongliang He, Haoji Zhang, Jiawen Li, Sule Bai, Xin Gu, Yansong Tang, Zhichao Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T13:03:21Z","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04416","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:dd52441dac3efe950ed1952a2cb4a79bdb309685be1bf25e02812b66ef7e881d","target":"record","created_at":"2026-07-05T12:03:50Z","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":"b329c0757a26a0801fea10b5b4caaf250fd3813be3c064343b20ad89fa67915a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T13:03:21Z","title_canon_sha256":"9132807405b68c064196635658abbc1e2beb1d6338510ac952a9bfd1f32e04d2"},"schema_version":"1.0","source":{"id":"2508.04416","kind":"arxiv","version":2}},"canonical_sha256":"06430eae3962b0f4bfc8f8879ed1844e347093ac45d282b0853e3d44f872648c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06430eae3962b0f4bfc8f8879ed1844e347093ac45d282b0853e3d44f872648c","first_computed_at":"2026-07-05T12:03:50.866938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:50.866938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RG//MKs5plG+8WHkI4uXH5Jb08JF920ONj9ZzH9m6vYu1NM6de3OP2tZBhGEN95t7fdUgYsbZVd6t6Oh10rIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:50.867534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04416","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd52441dac3efe950ed1952a2cb4a79bdb309685be1bf25e02812b66ef7e881d","sha256:103065d6bd4611aacf5d06191027cdf7fcce218e3576ce7a41c5b2bbd18842ba"],"state_sha256":"24ca48c1526c7015164e8660a40224ad0fbb04b75e98bef8c19cae32a76a4b88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+qY/uyhmvhUnP8lV0XpZNxe9XRAjI5I48T7dYm8AzNWG3skDx759bjLlEdbnXUV9geoQ+dzcSVq/jqD3uZ61Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:39:40.314358Z","bundle_sha256":"fabd4e7ccfb2696b3b0a48a2de3415519dbb9dfa6ef916520b4b13a97e15b3d1"}}