{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:O5FPJH7I2B4HNHMA5SHOEQKEEE","short_pith_number":"pith:O5FPJH7I","canonical_record":{"source":{"id":"2602.22779","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T09:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"72079029b17a646fb5973a5cdd367d3c100b454490f0e26fa12335cd158e1b76","abstract_canon_sha256":"7c063636c3c98fd927b376d4a70fb97379984d7bda9b537f2c7cdd773ad63a2d"},"schema_version":"1.0"},"canonical_sha256":"774af49fe8d078769d80ec8ee24144212348484984fc484b38ae6301fddf0def","source":{"kind":"arxiv","id":"2602.22779","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.22779","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"arxiv_version","alias_value":"2602.22779v3","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22779","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"pith_short_12","alias_value":"O5FPJH7I2B4H","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"pith_short_16","alias_value":"O5FPJH7I2B4HNHMA","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"pith_short_8","alias_value":"O5FPJH7I","created_at":"2026-06-04T01:08:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:O5FPJH7I2B4HNHMA5SHOEQKEEE","target":"record","payload":{"canonical_record":{"source":{"id":"2602.22779","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T09:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"72079029b17a646fb5973a5cdd367d3c100b454490f0e26fa12335cd158e1b76","abstract_canon_sha256":"7c063636c3c98fd927b376d4a70fb97379984d7bda9b537f2c7cdd773ad63a2d"},"schema_version":"1.0"},"canonical_sha256":"774af49fe8d078769d80ec8ee24144212348484984fc484b38ae6301fddf0def","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:46.330549Z","signature_b64":"Uhmyq2YOnoggC/IXu9YZH70ZoAbj8kMesSSA3z2vgMH5EawmNeFAOnv5/i5o+2zFOpZCkCscXh02ftJ6tQCDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"774af49fe8d078769d80ec8ee24144212348484984fc484b38ae6301fddf0def","last_reissued_at":"2026-06-04T01:08:46.329945Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:46.329945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.22779","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uwuj2bEJ3f5qPnzA7BJfloZ7vzyc8aQ3F7eZljqb/fEu5l4SauNCuz3+XhJTasd0x/hl8omi2NL/EyaeAq41BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T01:24:31.148024Z"},"content_sha256":"9ec8c0e9d4010d0ffe467da634d6aed6827e1c1c5866b9fbe0ccaeded6ea3c91","schema_version":"1.0","event_id":"sha256:9ec8c0e9d4010d0ffe467da634d6aed6827e1c1c5866b9fbe0ccaeded6ea3c91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:O5FPJH7I2B4HNHMA5SHOEQKEEE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TrajTok: Learning Trajectory Tokens enables better Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TrajTok learns trajectory tokens end-to-end through implicit space-time clustering to improve video model accuracy and efficiency.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashutosh Kumar, Chenhao Zheng, Chun-Liang Li, Jianing Zhang, Jieyu Zhang, Oncel Tuzel, Quan Kong, Ranjay Krishna, Weikai Huang","submitted_at":"2026-02-26T09:15:34Z","abstract_excerpt":"Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising solution by decoupling video duration from token count, they rely on complex external segmentation and tracking pipelines that are slow and task-agnostic. We propose TrajTok, an end-to-end video tokenizer module that is fully integrated and co-trained with video models for a downstream objective, dynamically adapting its token granularity to semantic complexity, in"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With TrajTok, we implement a video CLIP model trained from scratch (TrajViT2). It achieves the best accuracy at scale across both classification and retrieval benchmarks, while maintaining efficiency comparable to the best token-merging methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That implicit clustering of pixels in space and time will produce trajectories that are semantically useful for downstream video understanding tasks when the segmenter is co-trained only for adaptability rather than pixel-level fidelity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TrajTok learns adaptive trajectory tokens for videos through a unified end-to-end segmenter, improving understanding performance and efficiency over patch-based or external-pipeline tokenizers.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TrajTok learns trajectory tokens end-to-end through implicit space-time clustering to improve video model accuracy and efficiency.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fb3d03326b4bab152b6eb6a052f46efbb6b21779496465b5da1faf5b21816447"},"source":{"id":"2602.22779","kind":"arxiv","version":3},"verdict":{"id":"36578a04-2a7a-4bf2-a3dc-589019cfb825","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T19:09:34.106646Z","strongest_claim":"With TrajTok, we implement a video CLIP model trained from scratch (TrajViT2). It achieves the best accuracy at scale across both classification and retrieval benchmarks, while maintaining efficiency comparable to the best token-merging methods.","one_line_summary":"TrajTok learns adaptive trajectory tokens for videos through a unified end-to-end segmenter, improving understanding performance and efficiency over patch-based or external-pipeline tokenizers.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That implicit clustering of pixels in space and time will produce trajectories that are semantically useful for downstream video understanding tasks when the segmenter is co-trained only for adaptability rather than pixel-level fidelity.","pith_extraction_headline":"TrajTok learns trajectory tokens end-to-end through implicit space-time clustering to improve video model accuracy and efficiency."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.22779/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":2,"snapshot_sha256":"4ce750f8c498ee634682461a650164d2639b67f339e7b1fc3a5b36892539e714"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"36578a04-2a7a-4bf2-a3dc-589019cfb825"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jGtZC7ZxriDKbhFQZDACe4Qs/nZqkD2jHg1FKuvoTjoB1sajw0NsS1V1vepWsEk5t10Tg+OLhoGyxjpB0uAMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T01:24:31.149038Z"},"content_sha256":"a5485945f687f18f99337093b19a189c42ff236bf10d0a297386f5cac29965e2","schema_version":"1.0","event_id":"sha256:a5485945f687f18f99337093b19a189c42ff236bf10d0a297386f5cac29965e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5FPJH7I2B4HNHMA5SHOEQKEEE/bundle.json","state_url":"https://pith.science/pith/O5FPJH7I2B4HNHMA5SHOEQKEEE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5FPJH7I2B4HNHMA5SHOEQKEEE/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":"2026-06-10T01:24:31Z","links":{"resolver":"https://pith.science/pith/O5FPJH7I2B4HNHMA5SHOEQKEEE","bundle":"https://pith.science/pith/O5FPJH7I2B4HNHMA5SHOEQKEEE/bundle.json","state":"https://pith.science/pith/O5FPJH7I2B4HNHMA5SHOEQKEEE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5FPJH7I2B4HNHMA5SHOEQKEEE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O5FPJH7I2B4HNHMA5SHOEQKEEE","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":"7c063636c3c98fd927b376d4a70fb97379984d7bda9b537f2c7cdd773ad63a2d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T09:15:34Z","title_canon_sha256":"72079029b17a646fb5973a5cdd367d3c100b454490f0e26fa12335cd158e1b76"},"schema_version":"1.0","source":{"id":"2602.22779","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.22779","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"arxiv_version","alias_value":"2602.22779v3","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22779","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"pith_short_12","alias_value":"O5FPJH7I2B4H","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"pith_short_16","alias_value":"O5FPJH7I2B4HNHMA","created_at":"2026-06-04T01:08:46Z"},{"alias_kind":"pith_short_8","alias_value":"O5FPJH7I","created_at":"2026-06-04T01:08:46Z"}],"graph_snapshots":[{"event_id":"sha256:a5485945f687f18f99337093b19a189c42ff236bf10d0a297386f5cac29965e2","target":"graph","created_at":"2026-06-04T01:08:46Z","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":"With TrajTok, we implement a video CLIP model trained from scratch (TrajViT2). It achieves the best accuracy at scale across both classification and retrieval benchmarks, while maintaining efficiency comparable to the best token-merging methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That implicit clustering of pixels in space and time will produce trajectories that are semantically useful for downstream video understanding tasks when the segmenter is co-trained only for adaptability rather than pixel-level fidelity."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TrajTok learns adaptive trajectory tokens for videos through a unified end-to-end segmenter, improving understanding performance and efficiency over patch-based or external-pipeline tokenizers."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"TrajTok learns trajectory tokens end-to-end through implicit space-time clustering to improve video model accuracy and efficiency."}],"snapshot_sha256":"fb3d03326b4bab152b6eb6a052f46efbb6b21779496465b5da1faf5b21816447"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4ce750f8c498ee634682461a650164d2639b67f339e7b1fc3a5b36892539e714"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.22779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising solution by decoupling video duration from token count, they rely on complex external segmentation and tracking pipelines that are slow and task-agnostic. We propose TrajTok, an end-to-end video tokenizer module that is fully integrated and co-trained with video models for a downstream objective, dynamically adapting its token granularity to semantic complexity, in","authors_text":"Ashutosh Kumar, Chenhao Zheng, Chun-Liang Li, Jianing Zhang, Jieyu Zhang, Oncel Tuzel, Quan Kong, Ranjay Krishna, Weikai Huang","cross_cats":[],"headline":"TrajTok learns trajectory tokens end-to-end through implicit space-time clustering to improve video model accuracy and efficiency.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T09:15:34Z","title":"TrajTok: Learning Trajectory Tokens enables better Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22779","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T19:09:34.106646Z","id":"36578a04-2a7a-4bf2-a3dc-589019cfb825","model_set":{"reader":"grok-4.3"},"one_line_summary":"TrajTok learns adaptive trajectory tokens for videos through a unified end-to-end segmenter, improving understanding performance and efficiency over patch-based or external-pipeline tokenizers.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"TrajTok learns trajectory tokens end-to-end through implicit space-time clustering to improve video model accuracy and efficiency.","strongest_claim":"With TrajTok, we implement a video CLIP model trained from scratch (TrajViT2). It achieves the best accuracy at scale across both classification and retrieval benchmarks, while maintaining efficiency comparable to the best token-merging methods.","weakest_assumption":"That implicit clustering of pixels in space and time will produce trajectories that are semantically useful for downstream video understanding tasks when the segmenter is co-trained only for adaptability rather than pixel-level fidelity."}},"verdict_id":"36578a04-2a7a-4bf2-a3dc-589019cfb825"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9ec8c0e9d4010d0ffe467da634d6aed6827e1c1c5866b9fbe0ccaeded6ea3c91","target":"record","created_at":"2026-06-04T01:08:46Z","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":"7c063636c3c98fd927b376d4a70fb97379984d7bda9b537f2c7cdd773ad63a2d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T09:15:34Z","title_canon_sha256":"72079029b17a646fb5973a5cdd367d3c100b454490f0e26fa12335cd158e1b76"},"schema_version":"1.0","source":{"id":"2602.22779","kind":"arxiv","version":3}},"canonical_sha256":"774af49fe8d078769d80ec8ee24144212348484984fc484b38ae6301fddf0def","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"774af49fe8d078769d80ec8ee24144212348484984fc484b38ae6301fddf0def","first_computed_at":"2026-06-04T01:08:46.329945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:46.329945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uhmyq2YOnoggC/IXu9YZH70ZoAbj8kMesSSA3z2vgMH5EawmNeFAOnv5/i5o+2zFOpZCkCscXh02ftJ6tQCDCA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:46.330549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.22779","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ec8c0e9d4010d0ffe467da634d6aed6827e1c1c5866b9fbe0ccaeded6ea3c91","sha256:a5485945f687f18f99337093b19a189c42ff236bf10d0a297386f5cac29965e2"],"state_sha256":"bb3adc3bf72569d36c7d5dc0441f85f8cba88c5d4a7bdeab1f2c29355ec58915"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OroZMlDAp0eJL8WigGXuShV3cKZ29nVsgq5/tE6QFEySTxur4CtIPhhjXk4+YsShqwVID9BOgix1OkFqCzD+Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T01:24:31.153398Z","bundle_sha256":"7e8b21ee4b72ef18c8465d030edc84271636351ef0b6b1e4cab50d7c851a11cc"}}