{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5IMKO4QD3QCZPPJZ2OASQBIV2E","short_pith_number":"pith:5IMKO4QD","canonical_record":{"source":{"id":"2602.07801","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-08T03:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ab03670dcf76aec7800c5b4452468adf18ea664b8c200f3dd77bb32ae11bb2d","abstract_canon_sha256":"e0183700af3fb4df8075128c796b88aafb47b5503dfeff3218c3f61617d75cf4"},"schema_version":"1.0"},"canonical_sha256":"ea18a77203dc0597bd39d381280515d130b2d554406d5b38c2dfa1de64e75c4e","source":{"kind":"arxiv","id":"2602.07801","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07801","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07801v4","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07801","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"5IMKO4QD3QCZ","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"5IMKO4QD3QCZPPJZ","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"5IMKO4QD","created_at":"2026-05-25T02:01:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5IMKO4QD3QCZPPJZ2OASQBIV2E","target":"record","payload":{"canonical_record":{"source":{"id":"2602.07801","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-08T03:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ab03670dcf76aec7800c5b4452468adf18ea664b8c200f3dd77bb32ae11bb2d","abstract_canon_sha256":"e0183700af3fb4df8075128c796b88aafb47b5503dfeff3218c3f61617d75cf4"},"schema_version":"1.0"},"canonical_sha256":"ea18a77203dc0597bd39d381280515d130b2d554406d5b38c2dfa1de64e75c4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:14.834766Z","signature_b64":"SjUBgIAysZILIRLtkH8aRIm/JNTHPYSWaqlImWVc0zsLx/L3ymKcIY39WZ4sjBnilA2djeD8g1apgnpsvXE8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea18a77203dc0597bd39d381280515d130b2d554406d5b38c2dfa1de64e75c4e","last_reissued_at":"2026-05-25T02:01:14.834043Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:14.834043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.07801","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZvXsRWq1tK98/QqvyDfO+vWGfav8gTwShtjI2x0hQGiBl2Z97nwFXspOA/nvP6S5T1u0k7RJPJVkYxeup16MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:19:59.859242Z"},"content_sha256":"90cf934ee6b7f8eb4a9133999845bed9693a3b491d0ed95d8f3bb21007c0cad9","schema_version":"1.0","event_id":"sha256:90cf934ee6b7f8eb4a9133999845bed9693a3b491d0ed95d8f3bb21007c0cad9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5IMKO4QD3QCZPPJZ2OASQBIV2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Wen, Changyi Liu, Fan Yang, Han Li, Haonan Fan, Jiankang Chen, Kaiyu Jiang, Kaiyu Tang, Meng Liu, Qile Su, Shijie Ma, Tianke Zhang, Tingting Gao, Wenqi Liu, Xuemeng Song, Yinwei Wei, Yunxiao Wang","submitted_at":"2026-02-08T03:45:50Z","abstract_excerpt":"In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07801","kind":"arxiv","version":4},"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/2602.07801/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":"2026-05-25T02:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBJ5Q5hdb03ncO+AGXZWuC365omnfaDIMvCEJGqc0D4mo6tl8S0FTbJE7lEU6qgjD+hfBPq+v45jrxmagZ4uCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:19:59.859686Z"},"content_sha256":"5de09e9bbebd18f14a5a55ea1e090e8bda823a7cfb40d8566170cfe0dadb92ec","schema_version":"1.0","event_id":"sha256:5de09e9bbebd18f14a5a55ea1e090e8bda823a7cfb40d8566170cfe0dadb92ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5IMKO4QD3QCZPPJZ2OASQBIV2E/bundle.json","state_url":"https://pith.science/pith/5IMKO4QD3QCZPPJZ2OASQBIV2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5IMKO4QD3QCZPPJZ2OASQBIV2E/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":"2026-05-26T00:19:59Z","links":{"resolver":"https://pith.science/pith/5IMKO4QD3QCZPPJZ2OASQBIV2E","bundle":"https://pith.science/pith/5IMKO4QD3QCZPPJZ2OASQBIV2E/bundle.json","state":"https://pith.science/pith/5IMKO4QD3QCZPPJZ2OASQBIV2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5IMKO4QD3QCZPPJZ2OASQBIV2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5IMKO4QD3QCZPPJZ2OASQBIV2E","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":"e0183700af3fb4df8075128c796b88aafb47b5503dfeff3218c3f61617d75cf4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-08T03:45:50Z","title_canon_sha256":"9ab03670dcf76aec7800c5b4452468adf18ea664b8c200f3dd77bb32ae11bb2d"},"schema_version":"1.0","source":{"id":"2602.07801","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07801","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07801v4","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07801","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"5IMKO4QD3QCZ","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"5IMKO4QD3QCZPPJZ","created_at":"2026-05-25T02:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"5IMKO4QD","created_at":"2026-05-25T02:01:14Z"}],"graph_snapshots":[{"event_id":"sha256:5de09e9bbebd18f14a5a55ea1e090e8bda823a7cfb40d8566170cfe0dadb92ec","target":"graph","created_at":"2026-05-25T02:01:14Z","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/2602.07801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic th","authors_text":"Bin Wen, Changyi Liu, Fan Yang, Han Li, Haonan Fan, Jiankang Chen, Kaiyu Jiang, Kaiyu Tang, Meng Liu, Qile Su, Shijie Ma, Tianke Zhang, Tingting Gao, Wenqi Liu, Xuemeng Song, Yinwei Wei, Yunxiao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-08T03:45:50Z","title":"VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07801","kind":"arxiv","version":4},"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":"sha256:90cf934ee6b7f8eb4a9133999845bed9693a3b491d0ed95d8f3bb21007c0cad9","target":"record","created_at":"2026-05-25T02:01:14Z","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":"e0183700af3fb4df8075128c796b88aafb47b5503dfeff3218c3f61617d75cf4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-08T03:45:50Z","title_canon_sha256":"9ab03670dcf76aec7800c5b4452468adf18ea664b8c200f3dd77bb32ae11bb2d"},"schema_version":"1.0","source":{"id":"2602.07801","kind":"arxiv","version":4}},"canonical_sha256":"ea18a77203dc0597bd39d381280515d130b2d554406d5b38c2dfa1de64e75c4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea18a77203dc0597bd39d381280515d130b2d554406d5b38c2dfa1de64e75c4e","first_computed_at":"2026-05-25T02:01:14.834043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:14.834043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SjUBgIAysZILIRLtkH8aRIm/JNTHPYSWaqlImWVc0zsLx/L3ymKcIY39WZ4sjBnilA2djeD8g1apgnpsvXE8CA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:14.834766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.07801","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90cf934ee6b7f8eb4a9133999845bed9693a3b491d0ed95d8f3bb21007c0cad9","sha256:5de09e9bbebd18f14a5a55ea1e090e8bda823a7cfb40d8566170cfe0dadb92ec"],"state_sha256":"270e23426c5122e1f6386d76f0311a5f788feef3a9218261fd96514b4cee84c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVc412t46bP4K64zOVgj9Bb3ILLnCMFHmPpIsRpk8FgNpjQTaMClCsZkGwEw5SMFe/PhG8jITTYz/T5FC6CPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:19:59.863595Z","bundle_sha256":"4174fc38d5b2e38b52cdbb4467d899e0e28ef68fe83cf1910ef37c8b05d2f57f"}}