{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OQUHLTYZRBI2NSPNEDEOPD3YBR","short_pith_number":"pith:OQUHLTYZ","canonical_record":{"source":{"id":"2411.14401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:30:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"70a38f519245c1755000153517482a0d699639d3eb5e12d5f67f57a6099b8558","abstract_canon_sha256":"f338f7c4a155166a1af546396741cb317740d85aaa8e051358ab699255d550f8"},"schema_version":"1.0"},"canonical_sha256":"742875cf198851a6c9ed20c8e78f780c4480e25553f53fe46d839e0f80cc554e","source":{"kind":"arxiv","id":"2411.14401","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14401","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14401v2","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14401","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"pith_short_12","alias_value":"OQUHLTYZRBI2","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"pith_short_16","alias_value":"OQUHLTYZRBI2NSPN","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"pith_short_8","alias_value":"OQUHLTYZ","created_at":"2026-07-05T10:38:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OQUHLTYZRBI2NSPNEDEOPD3YBR","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:30:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"70a38f519245c1755000153517482a0d699639d3eb5e12d5f67f57a6099b8558","abstract_canon_sha256":"f338f7c4a155166a1af546396741cb317740d85aaa8e051358ab699255d550f8"},"schema_version":"1.0"},"canonical_sha256":"742875cf198851a6c9ed20c8e78f780c4480e25553f53fe46d839e0f80cc554e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:21.850237Z","signature_b64":"dumCXmgXrRoLHab2FLnMm/9MRFFfLcRt6x8IOpifF6EYRuSZHWb8vow6tRoI+85zzKQCnraXw0oSjWOzsWd+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"742875cf198851a6c9ed20c8e78f780c4480e25553f53fe46d839e0f80cc554e","last_reissued_at":"2026-07-05T10:38:21.849774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:21.849774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14401","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":"2026-07-05T10:38:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1MpyNPwY1BDkvVbz+0Z13p5nvCfFg6TgACF7Ubqic8KfPdSZAFWng75Bf5J3n4dPQQkOHkQNc3nhdnuEdyn6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:00:23.736631Z"},"content_sha256":"4fbe3d638fdb52b3f5dc947aa13e627808cdd51b43ce9bf2e1af7fa98f7031a8","schema_version":"1.0","event_id":"sha256:4fbe3d638fdb52b3f5dc947aa13e627808cdd51b43ce9bf2e1af7fa98f7031a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OQUHLTYZRBI2NSPNEDEOPD3YBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Xianjun Yang, Yiming Zhang, Yining Sun, Zenghui Ding, Zhaorun Chen, Zhuokai Zhao","submitted_at":"2024-11-21T18:30:11Z","abstract_excerpt":"Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains challenging. Traditional video processing methods rely heavily on fine-tuning to capture nuanced spatial-temporal details, which incurs significant data and computation costs. In contrast, training-free approaches, though efficient, often lack robustness in preserving context-rich features across complex video content. To this end, we propose DYTO, a novel dynamic token merging framework for zero-shot video understand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14401","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/2411.14401/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":"2026-07-05T10:38:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pwTfzutOSfW0KbQB/HhiMFAumLPP5ewddN2ufEe8YbUnma6pwoatEy0Lprkqr9gyNIpxGP/q/6JMWU1WiNtyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:00:23.737184Z"},"content_sha256":"974aee81cf6b14435ad95aa67c1eed28ac31b5872189fdc80b8da8c8df8b0f9e","schema_version":"1.0","event_id":"sha256:974aee81cf6b14435ad95aa67c1eed28ac31b5872189fdc80b8da8c8df8b0f9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQUHLTYZRBI2NSPNEDEOPD3YBR/bundle.json","state_url":"https://pith.science/pith/OQUHLTYZRBI2NSPNEDEOPD3YBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQUHLTYZRBI2NSPNEDEOPD3YBR/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":"2026-08-12T12:00:23Z","links":{"resolver":"https://pith.science/pith/OQUHLTYZRBI2NSPNEDEOPD3YBR","bundle":"https://pith.science/pith/OQUHLTYZRBI2NSPNEDEOPD3YBR/bundle.json","state":"https://pith.science/pith/OQUHLTYZRBI2NSPNEDEOPD3YBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQUHLTYZRBI2NSPNEDEOPD3YBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OQUHLTYZRBI2NSPNEDEOPD3YBR","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":"f338f7c4a155166a1af546396741cb317740d85aaa8e051358ab699255d550f8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:30:11Z","title_canon_sha256":"70a38f519245c1755000153517482a0d699639d3eb5e12d5f67f57a6099b8558"},"schema_version":"1.0","source":{"id":"2411.14401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14401","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14401v2","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14401","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"pith_short_12","alias_value":"OQUHLTYZRBI2","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"pith_short_16","alias_value":"OQUHLTYZRBI2NSPN","created_at":"2026-07-05T10:38:21Z"},{"alias_kind":"pith_short_8","alias_value":"OQUHLTYZ","created_at":"2026-07-05T10:38:21Z"}],"graph_snapshots":[{"event_id":"sha256:974aee81cf6b14435ad95aa67c1eed28ac31b5872189fdc80b8da8c8df8b0f9e","target":"graph","created_at":"2026-07-05T10:38:21Z","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/2411.14401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains challenging. Traditional video processing methods rely heavily on fine-tuning to capture nuanced spatial-temporal details, which incurs significant data and computation costs. In contrast, training-free approaches, though efficient, often lack robustness in preserving context-rich features across complex video content. To this end, we propose DYTO, a novel dynamic token merging framework for zero-shot video understand","authors_text":"Xianjun Yang, Yiming Zhang, Yining Sun, Zenghui Ding, Zhaorun Chen, Zhuokai Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:30:11Z","title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14401","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":"sha256:4fbe3d638fdb52b3f5dc947aa13e627808cdd51b43ce9bf2e1af7fa98f7031a8","target":"record","created_at":"2026-07-05T10:38:21Z","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":"f338f7c4a155166a1af546396741cb317740d85aaa8e051358ab699255d550f8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:30:11Z","title_canon_sha256":"70a38f519245c1755000153517482a0d699639d3eb5e12d5f67f57a6099b8558"},"schema_version":"1.0","source":{"id":"2411.14401","kind":"arxiv","version":2}},"canonical_sha256":"742875cf198851a6c9ed20c8e78f780c4480e25553f53fe46d839e0f80cc554e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"742875cf198851a6c9ed20c8e78f780c4480e25553f53fe46d839e0f80cc554e","first_computed_at":"2026-07-05T10:38:21.849774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:21.849774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dumCXmgXrRoLHab2FLnMm/9MRFFfLcRt6x8IOpifF6EYRuSZHWb8vow6tRoI+85zzKQCnraXw0oSjWOzsWd+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:21.850237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fbe3d638fdb52b3f5dc947aa13e627808cdd51b43ce9bf2e1af7fa98f7031a8","sha256:974aee81cf6b14435ad95aa67c1eed28ac31b5872189fdc80b8da8c8df8b0f9e"],"state_sha256":"83768bb8ba3510e4707e4b3c37e0bc7468ff23fd80f0b9be1de4a3936b35cf54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nZbAWwdAGWy3QLJHy8RoA8iZbgFkixqmRjdlWN0c4Q2+/pibTtFK/jrH3aHbCwy6pSFJdB45dimweMgdfVpvDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:00:23.745581Z","bundle_sha256":"504296f7034dc67fd844ecc07c6934ff90ed253aa9c3a28983971f80ce5933b5"}}