{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RUOVSYBEFDJ3EUVEGKZ6C7RWTG","short_pith_number":"pith:RUOVSYBE","canonical_record":{"source":{"id":"2502.06428","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:03:05Z","cross_cats_sorted":[],"title_canon_sha256":"217cb83a9587c80dfc9725485a34722bf4d6b4bcc891d1032e388e584e6f0a6e","abstract_canon_sha256":"57cb6141dbe405ab9ca21b0c5b6a3c5af046dfe4ca62b88d4176f04c066a3d01"},"schema_version":"1.0"},"canonical_sha256":"8d1d59602428d3b252a432b3e17e3699a76bcbf34cbe4afac674d743530a64cb","source":{"kind":"arxiv","id":"2502.06428","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06428","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06428v2","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06428","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"RUOVSYBEFDJ3","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"RUOVSYBEFDJ3EUVE","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"RUOVSYBE","created_at":"2026-07-05T10:12:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RUOVSYBEFDJ3EUVEGKZ6C7RWTG","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06428","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:03:05Z","cross_cats_sorted":[],"title_canon_sha256":"217cb83a9587c80dfc9725485a34722bf4d6b4bcc891d1032e388e584e6f0a6e","abstract_canon_sha256":"57cb6141dbe405ab9ca21b0c5b6a3c5af046dfe4ca62b88d4176f04c066a3d01"},"schema_version":"1.0"},"canonical_sha256":"8d1d59602428d3b252a432b3e17e3699a76bcbf34cbe4afac674d743530a64cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:27.810856Z","signature_b64":"v1fbw1wveyN2UInfYRWj2VGUiGr67LERS05r2Kt2I4FHb/VxPw87ee0zYjuGiDjyxWJ4AOm7jYizwSgeV6KrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d1d59602428d3b252a432b3e17e3699a76bcbf34cbe4afac674d743530a64cb","last_reissued_at":"2026-07-05T10:12:27.810414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:27.810414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06428","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":"2026-07-05T10:12:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJfHAgXNmUWpUkIYT6m2w4BzXm7KkUG6Sftnv8HIX4F5fVpDxFrctpFhlrsa+lc+gqoxefLHyi8xoEOxK+LNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:00:23.108910Z"},"content_sha256":"9415334c48e1c8e0d78d56d67c5c31878c2ecd621ab623e1208e5b6011880ed3","schema_version":"1.0","event_id":"sha256:9415334c48e1c8e0d78d56d67c5c31878c2ecd621ab623e1208e5b6011880ed3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RUOVSYBEFDJ3EUVEGKZ6C7RWTG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoS: Chain-of-Shot Prompting for Long Video Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Si, Jian Hu, Shaogang Gong, Wei Li, Zixu Cheng","submitted_at":"2025-02-10T13:03:05Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) struggle with long videos due to the need for excessive visual tokens. These tokens exceed massively the context length of MLLMs, resulting in filled by redundant task-irrelevant shots. How to select shots is an unsolved critical problem: sparse sampling risks missing key details, while exhaustive sampling overwhelms the model with irrelevant content, leading to video misunderstanding. To solve this problem, we propose Chain-of-Shot prompting (CoS). The key idea is to frame shot selection as test-time visual prompt optimisation, choosing shots adaptive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06428","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/2502.06428/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":"2026-07-05T10:12:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PYSf3SdRQWxGZPAU7i2iqQUmCevNyu6At6w8bMEMVQQdlcJR3YJrrs54enp376n3jnBKArMxYhyUmBhprpQLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:00:23.109432Z"},"content_sha256":"9d22f436d177c7c4055b5cc9f5de27c06fbb57d40e625456d18deaa3602b566d","schema_version":"1.0","event_id":"sha256:9d22f436d177c7c4055b5cc9f5de27c06fbb57d40e625456d18deaa3602b566d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUOVSYBEFDJ3EUVEGKZ6C7RWTG/bundle.json","state_url":"https://pith.science/pith/RUOVSYBEFDJ3EUVEGKZ6C7RWTG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUOVSYBEFDJ3EUVEGKZ6C7RWTG/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":"2026-08-07T16:00:23Z","links":{"resolver":"https://pith.science/pith/RUOVSYBEFDJ3EUVEGKZ6C7RWTG","bundle":"https://pith.science/pith/RUOVSYBEFDJ3EUVEGKZ6C7RWTG/bundle.json","state":"https://pith.science/pith/RUOVSYBEFDJ3EUVEGKZ6C7RWTG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUOVSYBEFDJ3EUVEGKZ6C7RWTG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RUOVSYBEFDJ3EUVEGKZ6C7RWTG","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":"57cb6141dbe405ab9ca21b0c5b6a3c5af046dfe4ca62b88d4176f04c066a3d01","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:03:05Z","title_canon_sha256":"217cb83a9587c80dfc9725485a34722bf4d6b4bcc891d1032e388e584e6f0a6e"},"schema_version":"1.0","source":{"id":"2502.06428","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06428","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06428v2","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06428","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"RUOVSYBEFDJ3","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"RUOVSYBEFDJ3EUVE","created_at":"2026-07-05T10:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"RUOVSYBE","created_at":"2026-07-05T10:12:27Z"}],"graph_snapshots":[{"event_id":"sha256:9d22f436d177c7c4055b5cc9f5de27c06fbb57d40e625456d18deaa3602b566d","target":"graph","created_at":"2026-07-05T10:12:27Z","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/2502.06428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal Large Language Models (MLLMs) struggle with long videos due to the need for excessive visual tokens. These tokens exceed massively the context length of MLLMs, resulting in filled by redundant task-irrelevant shots. How to select shots is an unsolved critical problem: sparse sampling risks missing key details, while exhaustive sampling overwhelms the model with irrelevant content, leading to video misunderstanding. To solve this problem, we propose Chain-of-Shot prompting (CoS). The key idea is to frame shot selection as test-time visual prompt optimisation, choosing shots adaptive","authors_text":"Chenyang Si, Jian Hu, Shaogang Gong, Wei Li, Zixu Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:03:05Z","title":"CoS: Chain-of-Shot Prompting for Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06428","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":"sha256:9415334c48e1c8e0d78d56d67c5c31878c2ecd621ab623e1208e5b6011880ed3","target":"record","created_at":"2026-07-05T10:12:27Z","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":"57cb6141dbe405ab9ca21b0c5b6a3c5af046dfe4ca62b88d4176f04c066a3d01","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:03:05Z","title_canon_sha256":"217cb83a9587c80dfc9725485a34722bf4d6b4bcc891d1032e388e584e6f0a6e"},"schema_version":"1.0","source":{"id":"2502.06428","kind":"arxiv","version":2}},"canonical_sha256":"8d1d59602428d3b252a432b3e17e3699a76bcbf34cbe4afac674d743530a64cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d1d59602428d3b252a432b3e17e3699a76bcbf34cbe4afac674d743530a64cb","first_computed_at":"2026-07-05T10:12:27.810414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:27.810414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v1fbw1wveyN2UInfYRWj2VGUiGr67LERS05r2Kt2I4FHb/VxPw87ee0zYjuGiDjyxWJ4AOm7jYizwSgeV6KrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:27.810856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06428","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9415334c48e1c8e0d78d56d67c5c31878c2ecd621ab623e1208e5b6011880ed3","sha256:9d22f436d177c7c4055b5cc9f5de27c06fbb57d40e625456d18deaa3602b566d"],"state_sha256":"1d9af9fe79674b2255dad394a94be7611857c39ba3028ddd4e3e44a2cb1ac35b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o+9bniWDn/9Fu50rsCBBDF6o7MxFx65nxgJ8MWkfyWePZbGEZ7OdKVDG9oxMqn0tnwUcb8jA0GZ0Q+2gDCGEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:00:23.127968Z","bundle_sha256":"3ddd2f3e75331777a39bd637538604ed45f32d27d72dbc4e2b82e8953593586e"}}