{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:32RKI6PKEJQLX24AVUNI7FOE5V","short_pith_number":"pith:32RKI6PK","canonical_record":{"source":{"id":"2506.19651","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T14:14:52Z","cross_cats_sorted":["cs.LG","cs.PF"],"title_canon_sha256":"8688fc5ac4a374b2085ff3517964274796da180699e41094e4bfa7553376de99","abstract_canon_sha256":"0907e9c9604a96fd2c52fd47a60524736152d363dbcf9e39323cb184940fd8ae"},"schema_version":"1.0"},"canonical_sha256":"dea2a479ea2260bbeb80ad1a8f95c4ed40cd7c77c0f428f6e8c519f9c3302d8d","source":{"kind":"arxiv","id":"2506.19651","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19651","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19651v3","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19651","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"32RKI6PKEJQL","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"32RKI6PKEJQLX24A","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"32RKI6PK","created_at":"2026-07-05T11:44:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:32RKI6PKEJQLX24AVUNI7FOE5V","target":"record","payload":{"canonical_record":{"source":{"id":"2506.19651","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T14:14:52Z","cross_cats_sorted":["cs.LG","cs.PF"],"title_canon_sha256":"8688fc5ac4a374b2085ff3517964274796da180699e41094e4bfa7553376de99","abstract_canon_sha256":"0907e9c9604a96fd2c52fd47a60524736152d363dbcf9e39323cb184940fd8ae"},"schema_version":"1.0"},"canonical_sha256":"dea2a479ea2260bbeb80ad1a8f95c4ed40cd7c77c0f428f6e8c519f9c3302d8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:50.361861Z","signature_b64":"s/9MEpAqTH+j7kCdkdUHKryHI/EnDP0LyJ3Qhv8kKK5ZwF+fig7urMkA0KvCUAfX5c23NKJYZwxsSqtHCExyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea2a479ea2260bbeb80ad1a8f95c4ed40cd7c77c0f428f6e8c519f9c3302d8d","last_reissued_at":"2026-07-05T11:44:50.361387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:50.361387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.19651","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":"2026-07-05T11:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wCNkTx160gQ/d9/buqhez3NE0b51JZIHN2jM83JW4AjpB2KiNDjiBYSJCJ+veIT0aXrwkxZpV4NSHHdz1SSHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:01:58.117048Z"},"content_sha256":"68aebfd86edb7d04bbd72ed64c5fbdbd320167ab9515bb6bcf6f75da273a8d21","schema_version":"1.0","event_id":"sha256:68aebfd86edb7d04bbd72ed64c5fbdbd320167ab9515bb6bcf6f75da273a8d21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:32RKI6PKEJQLX24AVUNI7FOE5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PEVLM: Parallel Encoding for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PF"],"primary_cat":"cs.CV","authors_text":"Jin Yang, Letian Kang, Shenxuan Zhou, Shixian Luo, Xiaoyang Yu, Yiqiang Li, Yong Wu, Yuxin Yin","submitted_at":"2025-06-24T14:14:52Z","abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention mechanisms. In this work, we introduce \\textbf{PEVLM}, a fine-tuning-free parallel encoding method designed to enhance the prefilling efficiency of VLMs in long video scenarios. PEVLM partitions the input video into context blocks with a shared sink block, while preserving sequential position embeddings to align the attention weight distribution with that of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19651","kind":"arxiv","version":3},"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/2506.19651/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":"2026-07-05T11:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wLqJB4MXAW6nPl+c5KqoVX/iMZUICtOjHqRFKHyl2Iz3lfldTiqALMcGbmBsdMnYaEJr2gNvwXfj1Zmd424YDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:01:58.118039Z"},"content_sha256":"5faba2fe8b7554bb0ac36fee9f672bb5cc7e987cc5df8beb1347dab3d4adbf97","schema_version":"1.0","event_id":"sha256:5faba2fe8b7554bb0ac36fee9f672bb5cc7e987cc5df8beb1347dab3d4adbf97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32RKI6PKEJQLX24AVUNI7FOE5V/bundle.json","state_url":"https://pith.science/pith/32RKI6PKEJQLX24AVUNI7FOE5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32RKI6PKEJQLX24AVUNI7FOE5V/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":"2026-08-18T23:01:58Z","links":{"resolver":"https://pith.science/pith/32RKI6PKEJQLX24AVUNI7FOE5V","bundle":"https://pith.science/pith/32RKI6PKEJQLX24AVUNI7FOE5V/bundle.json","state":"https://pith.science/pith/32RKI6PKEJQLX24AVUNI7FOE5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32RKI6PKEJQLX24AVUNI7FOE5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:32RKI6PKEJQLX24AVUNI7FOE5V","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":"0907e9c9604a96fd2c52fd47a60524736152d363dbcf9e39323cb184940fd8ae","cross_cats_sorted":["cs.LG","cs.PF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T14:14:52Z","title_canon_sha256":"8688fc5ac4a374b2085ff3517964274796da180699e41094e4bfa7553376de99"},"schema_version":"1.0","source":{"id":"2506.19651","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19651","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19651v3","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19651","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"32RKI6PKEJQL","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"32RKI6PKEJQLX24A","created_at":"2026-07-05T11:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"32RKI6PK","created_at":"2026-07-05T11:44:50Z"}],"graph_snapshots":[{"event_id":"sha256:5faba2fe8b7554bb0ac36fee9f672bb5cc7e987cc5df8beb1347dab3d4adbf97","target":"graph","created_at":"2026-07-05T11:44:50Z","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/2506.19651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention mechanisms. In this work, we introduce \\textbf{PEVLM}, a fine-tuning-free parallel encoding method designed to enhance the prefilling efficiency of VLMs in long video scenarios. PEVLM partitions the input video into context blocks with a shared sink block, while preserving sequential position embeddings to align the attention weight distribution with that of","authors_text":"Jin Yang, Letian Kang, Shenxuan Zhou, Shixian Luo, Xiaoyang Yu, Yiqiang Li, Yong Wu, Yuxin Yin","cross_cats":["cs.LG","cs.PF"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T14:14:52Z","title":"PEVLM: Parallel Encoding for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19651","kind":"arxiv","version":3},"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":"sha256:68aebfd86edb7d04bbd72ed64c5fbdbd320167ab9515bb6bcf6f75da273a8d21","target":"record","created_at":"2026-07-05T11:44:50Z","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":"0907e9c9604a96fd2c52fd47a60524736152d363dbcf9e39323cb184940fd8ae","cross_cats_sorted":["cs.LG","cs.PF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T14:14:52Z","title_canon_sha256":"8688fc5ac4a374b2085ff3517964274796da180699e41094e4bfa7553376de99"},"schema_version":"1.0","source":{"id":"2506.19651","kind":"arxiv","version":3}},"canonical_sha256":"dea2a479ea2260bbeb80ad1a8f95c4ed40cd7c77c0f428f6e8c519f9c3302d8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dea2a479ea2260bbeb80ad1a8f95c4ed40cd7c77c0f428f6e8c519f9c3302d8d","first_computed_at":"2026-07-05T11:44:50.361387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:50.361387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s/9MEpAqTH+j7kCdkdUHKryHI/EnDP0LyJ3Qhv8kKK5ZwF+fig7urMkA0KvCUAfX5c23NKJYZwxsSqtHCExyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:50.361861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19651","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68aebfd86edb7d04bbd72ed64c5fbdbd320167ab9515bb6bcf6f75da273a8d21","sha256:5faba2fe8b7554bb0ac36fee9f672bb5cc7e987cc5df8beb1347dab3d4adbf97"],"state_sha256":"e9f1359b793e79efd1a93f64cca5895b4367ed2e7723bf22d6947f14f9d55d2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y5BNX005NTh429pNWbHf0QC6o4RmYVw1N0AWbbahPVlkpCq+xxrzXyTYVUGJHmq/kbaM9LcVq6ob2RVEyqr3DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:01:58.122925Z","bundle_sha256":"25fa9da31ef4ea297e5eaad4f1d99c38258b3a962abdc4deeba743ad0e9e7b3c"}}