{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YB43P2XZE5OHPSQBVHOTWJD2DI","short_pith_number":"pith:YB43P2XZ","canonical_record":{"source":{"id":"2604.14692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-16T06:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"dea5e11d196ad376ab465763318eb017b53ceffc5867e5b09fc282eb4fedf5de","abstract_canon_sha256":"ab2fe4d66c30a2175231238e2d603870b78bf7ec2b23da5ebb43683443f1adf6"},"schema_version":"1.0"},"canonical_sha256":"c079b7eaf9275c77ca01a9dd3b247a1a36a188fdff3d484ffc760e4ccba23a98","source":{"kind":"arxiv","id":"2604.14692","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.14692","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"arxiv_version","alias_value":"2604.14692v2","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.14692","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"pith_short_12","alias_value":"YB43P2XZE5OH","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"pith_short_16","alias_value":"YB43P2XZE5OHPSQB","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"pith_short_8","alias_value":"YB43P2XZ","created_at":"2026-05-20T00:00:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YB43P2XZE5OHPSQBVHOTWJD2DI","target":"record","payload":{"canonical_record":{"source":{"id":"2604.14692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-16T06:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"dea5e11d196ad376ab465763318eb017b53ceffc5867e5b09fc282eb4fedf5de","abstract_canon_sha256":"ab2fe4d66c30a2175231238e2d603870b78bf7ec2b23da5ebb43683443f1adf6"},"schema_version":"1.0"},"canonical_sha256":"c079b7eaf9275c77ca01a9dd3b247a1a36a188fdff3d484ffc760e4ccba23a98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:38.048932Z","signature_b64":"8Gziyptr+A4kRz/z7R1OXoDxCvL/QEgy39WDelAhfbjfXvxld0CZ6RkuvbdTdm+jUVAe2Eu8nrby14RUrDcNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c079b7eaf9275c77ca01a9dd3b247a1a36a188fdff3d484ffc760e4ccba23a98","last_reissued_at":"2026-05-20T00:00:38.048308Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:38.048308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.14692","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":"2026-05-20T00:00:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJs1W43WlbztufwaS0oOTrrIbUib1or5VYFAfuSYDP2NHb+M+XVIBJP952TLg84wFJmyq2QczeerZFrHurhdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:20:49.295835Z"},"content_sha256":"b31cce7a131694c3ef4b49c12dc239645beb94241811ff942d03204e1958b766","schema_version":"1.0","event_id":"sha256:b31cce7a131694c3ef4b49c12dc239645beb94241811ff942d03204e1958b766"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YB43P2XZE5OHPSQBVHOTWJD2DI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"Video reasoning improves when each step anchors explicitly to specific visual objects in the frames.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Cheng, Genbao Xu, Nan Ma, Quanxing Zha, Soujanya Poria, Teng Wang, Wei Rao, Wenyuan Gu, Zhixuan Wu","submitted_at":"2026-04-16T06:50:20Z","abstract_excerpt":"Video understanding requires identifying and reasoning over semantically discriminative visual objects across frames, yet existing object-agnostic solutions struggle to effectively handle substantial object variations over time. To address this, we introduce Chain-of-Glimpse, a search-guided progressive object-grounded reasoning framework that explicitly anchors each reasoning step to specific visual evidence regions, enabling compositional and multi-step decision-making. Formally, Chain-of-Glimpse formulates video reasoning as a step-by-step process that incrementally builds spatially grounde"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Chain-of-Glimpse formulates video reasoning as a step-by-step process that incrementally builds spatially grounded traces around task-relevant visual objects, yielding accurate and interpretable multi-step decisions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That optimizing a search-guided controller via reinforcement learning with a format reward will reliably produce grounding capability that improves compositional reasoning over object-agnostic baselines.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Chain-of-Glimpse is a reinforcement-learning-based framework that iteratively grounds visual evidence regions to enable multi-step object-aware reasoning in videos.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Video reasoning improves when each step anchors explicitly to specific visual objects in the frames.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9a5a68a61c873ca5566f1a3804cafce6fe6a53a1f2ff7bb83173ab35727ccbd6"},"source":{"id":"2604.14692","kind":"arxiv","version":2},"verdict":{"id":"714feb40-eea7-4a6d-b7eb-b480a879c38c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:30:00.450691Z","strongest_claim":"Chain-of-Glimpse formulates video reasoning as a step-by-step process that incrementally builds spatially grounded traces around task-relevant visual objects, yielding accurate and interpretable multi-step decisions.","one_line_summary":"Chain-of-Glimpse is a reinforcement-learning-based framework that iteratively grounds visual evidence regions to enable multi-step object-aware reasoning in videos.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That optimizing a search-guided controller via reinforcement learning with a format reward will reliably produce grounding capability that improves compositional reasoning over object-agnostic baselines.","pith_extraction_headline":"Video reasoning improves when each step anchors explicitly to specific visual objects in the frames."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.14692/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":56,"sample":[{"doi":"","year":2024,"title":"A simple llm framework for long-range video question- answering,","work_id":"c0b0c9c5-0466-4223-a181-5209bd0c7b6b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Understanding long videos in one multimodal language model pass","work_id":"a0d8f834-29b0-4597-ad47-382843695ca9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Stimuvar: Spatiotemporal stimuli-aware video affective reasoning with multimodal large language models,","work_id":"83621f58-c138-4c3d-8c5c-f9efbec7184e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Dycoke: Dynamic com- pression of tokens for fast video large language models,","work_id":"6cf93b3f-d9fb-480c-8916-bb03104c64fa","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Vtimellm: Empower llm to grasp video moments,","work_id":"069d139b-0388-4f7e-91b5-de76a3623585","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":56,"snapshot_sha256":"9d6eecbd6e0680a2159ecc4cdd8c72256c80ebb3230bca373ee344d6e5f50e60","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bed1e382e55644c1628f5545de3cced90f0996a5b6c681db8aa00abedbdaffce"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"714feb40-eea7-4a6d-b7eb-b480a879c38c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sYTgmd64wBh6o7S4sGI6XgWQX2edKDyrcjzljcg82Be0mdK0eda+uzakZ+897TAiXICrCZNY6hequ4wM8PHeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:20:49.296606Z"},"content_sha256":"1304c5ebaa54c08799377ec083b814ed004a92ae68d92eeb7ac73fca43e377b5","schema_version":"1.0","event_id":"sha256:1304c5ebaa54c08799377ec083b814ed004a92ae68d92eeb7ac73fca43e377b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YB43P2XZE5OHPSQBVHOTWJD2DI/bundle.json","state_url":"https://pith.science/pith/YB43P2XZE5OHPSQBVHOTWJD2DI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YB43P2XZE5OHPSQBVHOTWJD2DI/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":"2026-06-01T05:20:49Z","links":{"resolver":"https://pith.science/pith/YB43P2XZE5OHPSQBVHOTWJD2DI","bundle":"https://pith.science/pith/YB43P2XZE5OHPSQBVHOTWJD2DI/bundle.json","state":"https://pith.science/pith/YB43P2XZE5OHPSQBVHOTWJD2DI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YB43P2XZE5OHPSQBVHOTWJD2DI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YB43P2XZE5OHPSQBVHOTWJD2DI","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":"ab2fe4d66c30a2175231238e2d603870b78bf7ec2b23da5ebb43683443f1adf6","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-16T06:50:20Z","title_canon_sha256":"dea5e11d196ad376ab465763318eb017b53ceffc5867e5b09fc282eb4fedf5de"},"schema_version":"1.0","source":{"id":"2604.14692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.14692","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"arxiv_version","alias_value":"2604.14692v2","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.14692","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"pith_short_12","alias_value":"YB43P2XZE5OH","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"pith_short_16","alias_value":"YB43P2XZE5OHPSQB","created_at":"2026-05-20T00:00:38Z"},{"alias_kind":"pith_short_8","alias_value":"YB43P2XZ","created_at":"2026-05-20T00:00:38Z"}],"graph_snapshots":[{"event_id":"sha256:1304c5ebaa54c08799377ec083b814ed004a92ae68d92eeb7ac73fca43e377b5","target":"graph","created_at":"2026-05-20T00:00:38Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Chain-of-Glimpse formulates video reasoning as a step-by-step process that incrementally builds spatially grounded traces around task-relevant visual objects, yielding accurate and interpretable multi-step decisions."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That optimizing a search-guided controller via reinforcement learning with a format reward will reliably produce grounding capability that improves compositional reasoning over object-agnostic baselines."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Chain-of-Glimpse is a reinforcement-learning-based framework that iteratively grounds visual evidence regions to enable multi-step object-aware reasoning in videos."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Video reasoning improves when each step anchors explicitly to specific visual objects in the frames."}],"snapshot_sha256":"9a5a68a61c873ca5566f1a3804cafce6fe6a53a1f2ff7bb83173ab35727ccbd6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bed1e382e55644c1628f5545de3cced90f0996a5b6c681db8aa00abedbdaffce"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.14692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video understanding requires identifying and reasoning over semantically discriminative visual objects across frames, yet existing object-agnostic solutions struggle to effectively handle substantial object variations over time. To address this, we introduce Chain-of-Glimpse, a search-guided progressive object-grounded reasoning framework that explicitly anchors each reasoning step to specific visual evidence regions, enabling compositional and multi-step decision-making. Formally, Chain-of-Glimpse formulates video reasoning as a step-by-step process that incrementally builds spatially grounde","authors_text":"Bo Cheng, Genbao Xu, Nan Ma, Quanxing Zha, Soujanya Poria, Teng Wang, Wei Rao, Wenyuan Gu, Zhixuan Wu","cross_cats":[],"headline":"Video reasoning improves when each step anchors explicitly to specific visual objects in the frames.","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-16T06:50:20Z","title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding"},"references":{"count":56,"internal_anchors":13,"resolved_work":56,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A simple llm framework for long-range video question- answering,","work_id":"c0b0c9c5-0466-4223-a181-5209bd0c7b6b","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Understanding long videos in one multimodal language model pass","work_id":"a0d8f834-29b0-4597-ad47-382843695ca9","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Stimuvar: Spatiotemporal stimuli-aware video affective reasoning with multimodal large language models,","work_id":"83621f58-c138-4c3d-8c5c-f9efbec7184e","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Dycoke: Dynamic com- pression of tokens for fast video large language models,","work_id":"6cf93b3f-d9fb-480c-8916-bb03104c64fa","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Vtimellm: Empower llm to grasp video moments,","work_id":"069d139b-0388-4f7e-91b5-de76a3623585","year":2024}],"snapshot_sha256":"9d6eecbd6e0680a2159ecc4cdd8c72256c80ebb3230bca373ee344d6e5f50e60"},"source":{"id":"2604.14692","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-19T17:30:00.450691Z","id":"714feb40-eea7-4a6d-b7eb-b480a879c38c","model_set":{"reader":"grok-4.3"},"one_line_summary":"Chain-of-Glimpse is a reinforcement-learning-based framework that iteratively grounds visual evidence regions to enable multi-step object-aware reasoning in videos.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Video reasoning improves when each step anchors explicitly to specific visual objects in the frames.","strongest_claim":"Chain-of-Glimpse formulates video reasoning as a step-by-step process that incrementally builds spatially grounded traces around task-relevant visual objects, yielding accurate and interpretable multi-step decisions.","weakest_assumption":"That optimizing a search-guided controller via reinforcement learning with a format reward will reliably produce grounding capability that improves compositional reasoning over object-agnostic baselines."}},"verdict_id":"714feb40-eea7-4a6d-b7eb-b480a879c38c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b31cce7a131694c3ef4b49c12dc239645beb94241811ff942d03204e1958b766","target":"record","created_at":"2026-05-20T00:00:38Z","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":"ab2fe4d66c30a2175231238e2d603870b78bf7ec2b23da5ebb43683443f1adf6","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-16T06:50:20Z","title_canon_sha256":"dea5e11d196ad376ab465763318eb017b53ceffc5867e5b09fc282eb4fedf5de"},"schema_version":"1.0","source":{"id":"2604.14692","kind":"arxiv","version":2}},"canonical_sha256":"c079b7eaf9275c77ca01a9dd3b247a1a36a188fdff3d484ffc760e4ccba23a98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c079b7eaf9275c77ca01a9dd3b247a1a36a188fdff3d484ffc760e4ccba23a98","first_computed_at":"2026-05-20T00:00:38.048308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:38.048308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Gziyptr+A4kRz/z7R1OXoDxCvL/QEgy39WDelAhfbjfXvxld0CZ6RkuvbdTdm+jUVAe2Eu8nrby14RUrDcNAg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:38.048932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.14692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b31cce7a131694c3ef4b49c12dc239645beb94241811ff942d03204e1958b766","sha256:1304c5ebaa54c08799377ec083b814ed004a92ae68d92eeb7ac73fca43e377b5"],"state_sha256":"ddabe1b6cd1722ae1a0f0910efe29d60a08ea06cbb49c6942211edad04f1041a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PfLq5tRJAdHX5K73br7HRITJls0KT02dCUEpLgiv7B83x+LBGYssMpdejPf1flCet03CBa0lMlEpGOq10/YhCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:20:49.299233Z","bundle_sha256":"adec7a35bc29e61ca0595c2a55173b37f3564022f260881f8217d7f840f0b754"}}