{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RXKT4C55X6BVYOHDSRWGCQZWUY","short_pith_number":"pith:RXKT4C55","canonical_record":{"source":{"id":"2601.23224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T17:47:30Z","cross_cats_sorted":[],"title_canon_sha256":"5342ee12539ba6634a421e3111fe8b40ba6b981fb8ec43af5c874ad294482eb1","abstract_canon_sha256":"8e48402bd1fad021b68f5ceb6287f22887b88d8bbb964ef1db601ce64a01c003"},"schema_version":"1.0"},"canonical_sha256":"8dd53e0bbdbf835c38e3946c614336a60f995598a96960f744bedfd4740d6ed8","source":{"kind":"arxiv","id":"2601.23224","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.23224","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"2601.23224v2","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23224","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"RXKT4C55X6BV","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"RXKT4C55X6BVYOHD","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"RXKT4C55","created_at":"2026-05-22T01:03:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RXKT4C55X6BVYOHDSRWGCQZWUY","target":"record","payload":{"canonical_record":{"source":{"id":"2601.23224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T17:47:30Z","cross_cats_sorted":[],"title_canon_sha256":"5342ee12539ba6634a421e3111fe8b40ba6b981fb8ec43af5c874ad294482eb1","abstract_canon_sha256":"8e48402bd1fad021b68f5ceb6287f22887b88d8bbb964ef1db601ce64a01c003"},"schema_version":"1.0"},"canonical_sha256":"8dd53e0bbdbf835c38e3946c614336a60f995598a96960f744bedfd4740d6ed8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:55.183810Z","signature_b64":"Lo7h7wCTLUWvG5qdnbP1PH13vB9ik7IB0py8zxf2h2KJsHFlp2MYpl1KRFPcAIg7P5BzqxJjwdaW3owiQ0OvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dd53e0bbdbf835c38e3946c614336a60f995598a96960f744bedfd4740d6ed8","last_reissued_at":"2026-05-22T01:03:55.182915Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:55.182915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.23224","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":"2026-05-22T01:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KUUGP2RcDgi1vzXH+a2mge186D7zqDz9vAiC2dDJcoGCcXz3um8mFwT7ooloTuM/Zxkc8MjgeOz4q98VWJe1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T03:28:05.493922Z"},"content_sha256":"68b674de6e696f99c75d810b82c5cc1d988deb195e8c01b9259e206f5fecccce","schema_version":"1.0","event_id":"sha256:68b674de6e696f99c75d810b82c5cc1d988deb195e8c01b9259e206f5fecccce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RXKT4C55X6BVYOHDSRWGCQZWUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changlian Ma, Hongjie Zhang, Kun Ouyang, Limin Wang, Qingyu Zhang, Tianxiang Jiang, Xiangyu Zeng, Xinhao Li, Yali Wang, Yi Wang, Yuhan Zhu, Zhiqiu Zhang, Ziang Yan, Zikang Wang, Zizheng Huang","submitted_at":"2026-01-30T17:47:30Z","abstract_excerpt":"Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability to identify sparse yet critical evidence amid extensive redundancy. We introduce Video-o3, a novel framework that supports iterative discovery of salient visual clues, fine-grained inspection of key segments, and adaptive termination once sufficient evidence is acquired. Technically, we address two core challenges in interleaved tool invocation. First, to mitigate attention dispersion induced by the heterogeneity of reasoning and tool-c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23224","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/2601.23224/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":"2026-05-22T01:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3MSdSDd3GCUz0ZK5i0mD5T1g5+HLucCSP0CZvzljGjkiES1qhO/sD8LIhQNj7HYD3cvkQ9OfD2zdwOz7bhVYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T03:28:05.494631Z"},"content_sha256":"09ff27c639ff5e3267db2b86169738711f1c97e8ddf644c486ca9fdd318071d5","schema_version":"1.0","event_id":"sha256:09ff27c639ff5e3267db2b86169738711f1c97e8ddf644c486ca9fdd318071d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXKT4C55X6BVYOHDSRWGCQZWUY/bundle.json","state_url":"https://pith.science/pith/RXKT4C55X6BVYOHDSRWGCQZWUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXKT4C55X6BVYOHDSRWGCQZWUY/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":"2026-06-05T03:28:05Z","links":{"resolver":"https://pith.science/pith/RXKT4C55X6BVYOHDSRWGCQZWUY","bundle":"https://pith.science/pith/RXKT4C55X6BVYOHDSRWGCQZWUY/bundle.json","state":"https://pith.science/pith/RXKT4C55X6BVYOHDSRWGCQZWUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXKT4C55X6BVYOHDSRWGCQZWUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RXKT4C55X6BVYOHDSRWGCQZWUY","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":"8e48402bd1fad021b68f5ceb6287f22887b88d8bbb964ef1db601ce64a01c003","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T17:47:30Z","title_canon_sha256":"5342ee12539ba6634a421e3111fe8b40ba6b981fb8ec43af5c874ad294482eb1"},"schema_version":"1.0","source":{"id":"2601.23224","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.23224","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"2601.23224v2","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23224","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"RXKT4C55X6BV","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"RXKT4C55X6BVYOHD","created_at":"2026-05-22T01:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"RXKT4C55","created_at":"2026-05-22T01:03:55Z"}],"graph_snapshots":[{"event_id":"sha256:09ff27c639ff5e3267db2b86169738711f1c97e8ddf644c486ca9fdd318071d5","target":"graph","created_at":"2026-05-22T01:03:55Z","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/2601.23224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability to identify sparse yet critical evidence amid extensive redundancy. We introduce Video-o3, a novel framework that supports iterative discovery of salient visual clues, fine-grained inspection of key segments, and adaptive termination once sufficient evidence is acquired. Technically, we address two core challenges in interleaved tool invocation. First, to mitigate attention dispersion induced by the heterogeneity of reasoning and tool-c","authors_text":"Changlian Ma, Hongjie Zhang, Kun Ouyang, Limin Wang, Qingyu Zhang, Tianxiang Jiang, Xiangyu Zeng, Xinhao Li, Yali Wang, Yi Wang, Yuhan Zhu, Zhiqiu Zhang, Ziang Yan, Zikang Wang, Zizheng Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T17:47:30Z","title":"Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23224","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":"sha256:68b674de6e696f99c75d810b82c5cc1d988deb195e8c01b9259e206f5fecccce","target":"record","created_at":"2026-05-22T01:03:55Z","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":"8e48402bd1fad021b68f5ceb6287f22887b88d8bbb964ef1db601ce64a01c003","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T17:47:30Z","title_canon_sha256":"5342ee12539ba6634a421e3111fe8b40ba6b981fb8ec43af5c874ad294482eb1"},"schema_version":"1.0","source":{"id":"2601.23224","kind":"arxiv","version":2}},"canonical_sha256":"8dd53e0bbdbf835c38e3946c614336a60f995598a96960f744bedfd4740d6ed8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dd53e0bbdbf835c38e3946c614336a60f995598a96960f744bedfd4740d6ed8","first_computed_at":"2026-05-22T01:03:55.182915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:55.182915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lo7h7wCTLUWvG5qdnbP1PH13vB9ik7IB0py8zxf2h2KJsHFlp2MYpl1KRFPcAIg7P5BzqxJjwdaW3owiQ0OvBw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:55.183810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.23224","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68b674de6e696f99c75d810b82c5cc1d988deb195e8c01b9259e206f5fecccce","sha256:09ff27c639ff5e3267db2b86169738711f1c97e8ddf644c486ca9fdd318071d5"],"state_sha256":"d8df018c9d90187e299ec17bba89991d5a16b3425f9d83264655a0a67e6b4820"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d6xXEVouFGMcRfzjc5M9iKVm3w/bT+GG703OX13d9MVjgMP8EcedIVieG4IyOhqR2aVxE/C013/vLJe4UK7uBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T03:28:05.498268Z","bundle_sha256":"2a6c0fac46f2ac4e0d79849fdf3c3d7a51c4bbd18f4824ae252cdf5d3467ab0a"}}