{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Q4ZOZNPU4BCSRRHBJT7O27DYT7","short_pith_number":"pith:Q4ZOZNPU","canonical_record":{"source":{"id":"2607.20389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T17:17:33Z","cross_cats_sorted":[],"title_canon_sha256":"aa06e62211e30669fb3381533a6ebf91ba133768ce824ebec3b9bfe7435a700a","abstract_canon_sha256":"07b862543180f909b600c253fd54ecf6d7bc1d67fc2f4bbb916a9fdf82ec23cf"},"schema_version":"1.0"},"canonical_sha256":"8732ecb5f4e04528c4e14cfeed7c789fec3a8225184e38ae597196a700e5d78a","source":{"kind":"arxiv","id":"2607.20389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20389","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20389v1","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20389","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"pith_short_12","alias_value":"Q4ZOZNPU4BCS","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"pith_short_16","alias_value":"Q4ZOZNPU4BCSRRHB","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"pith_short_8","alias_value":"Q4ZOZNPU","created_at":"2026-07-23T01:25:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Q4ZOZNPU4BCSRRHBJT7O27DYT7","target":"record","payload":{"canonical_record":{"source":{"id":"2607.20389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T17:17:33Z","cross_cats_sorted":[],"title_canon_sha256":"aa06e62211e30669fb3381533a6ebf91ba133768ce824ebec3b9bfe7435a700a","abstract_canon_sha256":"07b862543180f909b600c253fd54ecf6d7bc1d67fc2f4bbb916a9fdf82ec23cf"},"schema_version":"1.0"},"canonical_sha256":"8732ecb5f4e04528c4e14cfeed7c789fec3a8225184e38ae597196a700e5d78a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:25:18.307373Z","signature_b64":"Msdf8F7C79BJtT5i9vC/ohwdFFopNycs4KxZkJ/T1pMaUSoc6B3Nd56wnKq8RDPfZwhZVCEIIhkHvoVqLKAjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8732ecb5f4e04528c4e14cfeed7c789fec3a8225184e38ae597196a700e5d78a","last_reissued_at":"2026-07-23T01:25:18.306489Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:25:18.306489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.20389","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-23T01:25:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uOvqFf5AaqhA2kMrVqNHugOxY4coOEyM2b8qOUe58L+IajWeO/X/FHF0u718DhWKRe3Pds0Hag62OZIbiimGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:56:28.424148Z"},"content_sha256":"c6a68eec01fd2ee9c559c8a6eec4da14b9553fdaf17183dd9230474d0f92b9d2","schema_version":"1.0","event_id":"sha256:c6a68eec01fd2ee9c559c8a6eec4da14b9553fdaf17183dd9230474d0f92b9d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Q4ZOZNPU4BCSRRHBJT7O27DYT7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PercepCap: Video Captioner with Structured Spatio-Temporal Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Desen Meng, Jiaming Zhang, Limin Wang, Pengfei Wan, Yichun Yang, Yifan Xu, Yuanxing Zhang, Zhixiao Wang, Zihao Wang","submitted_at":"2026-07-22T17:17:33Z","abstract_excerpt":"Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal perception of when events occur. Existing MLLMs usually generate captions directly from video inputs without exposing the perceptual evidence behind descriptions. As a result, mistakes in spatiotemporal perception are only observed in the final caption, making it difficult to identify the underlying perceptual errors directly. To address these issues, we present PercepCap, a perception-aware video captioning framework that makes perceptual evide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20389","kind":"arxiv","version":1},"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/2607.20389/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":"2026-07-23T01:25:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ir1w9YVV8cNDKZHfoHSeS3pNb6R0d3pKr4MSGW/PWnv4xc0SinJO0x+j8IBoW7itPzpXT7Kshwd5s2IUGyGuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:56:28.424526Z"},"content_sha256":"5010368f88595749e4b96b68aa423d5fce8f5326386c8b46ba1fc801590741c9","schema_version":"1.0","event_id":"sha256:5010368f88595749e4b96b68aa423d5fce8f5326386c8b46ba1fc801590741c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4ZOZNPU4BCSRRHBJT7O27DYT7/bundle.json","state_url":"https://pith.science/pith/Q4ZOZNPU4BCSRRHBJT7O27DYT7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4ZOZNPU4BCSRRHBJT7O27DYT7/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":"2026-08-04T11:56:28Z","links":{"resolver":"https://pith.science/pith/Q4ZOZNPU4BCSRRHBJT7O27DYT7","bundle":"https://pith.science/pith/Q4ZOZNPU4BCSRRHBJT7O27DYT7/bundle.json","state":"https://pith.science/pith/Q4ZOZNPU4BCSRRHBJT7O27DYT7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4ZOZNPU4BCSRRHBJT7O27DYT7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q4ZOZNPU4BCSRRHBJT7O27DYT7","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":"07b862543180f909b600c253fd54ecf6d7bc1d67fc2f4bbb916a9fdf82ec23cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T17:17:33Z","title_canon_sha256":"aa06e62211e30669fb3381533a6ebf91ba133768ce824ebec3b9bfe7435a700a"},"schema_version":"1.0","source":{"id":"2607.20389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20389","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20389v1","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20389","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"pith_short_12","alias_value":"Q4ZOZNPU4BCS","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"pith_short_16","alias_value":"Q4ZOZNPU4BCSRRHB","created_at":"2026-07-23T01:25:18Z"},{"alias_kind":"pith_short_8","alias_value":"Q4ZOZNPU","created_at":"2026-07-23T01:25:18Z"}],"graph_snapshots":[{"event_id":"sha256:5010368f88595749e4b96b68aa423d5fce8f5326386c8b46ba1fc801590741c9","target":"graph","created_at":"2026-07-23T01:25:18Z","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/2607.20389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal perception of when events occur. Existing MLLMs usually generate captions directly from video inputs without exposing the perceptual evidence behind descriptions. As a result, mistakes in spatiotemporal perception are only observed in the final caption, making it difficult to identify the underlying perceptual errors directly. To address these issues, we present PercepCap, a perception-aware video captioning framework that makes perceptual evide","authors_text":"Desen Meng, Jiaming Zhang, Limin Wang, Pengfei Wan, Yichun Yang, Yifan Xu, Yuanxing Zhang, Zhixiao Wang, Zihao Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T17:17:33Z","title":"PercepCap: Video Captioner with Structured Spatio-Temporal Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20389","kind":"arxiv","version":1},"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:c6a68eec01fd2ee9c559c8a6eec4da14b9553fdaf17183dd9230474d0f92b9d2","target":"record","created_at":"2026-07-23T01:25:18Z","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":"07b862543180f909b600c253fd54ecf6d7bc1d67fc2f4bbb916a9fdf82ec23cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T17:17:33Z","title_canon_sha256":"aa06e62211e30669fb3381533a6ebf91ba133768ce824ebec3b9bfe7435a700a"},"schema_version":"1.0","source":{"id":"2607.20389","kind":"arxiv","version":1}},"canonical_sha256":"8732ecb5f4e04528c4e14cfeed7c789fec3a8225184e38ae597196a700e5d78a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8732ecb5f4e04528c4e14cfeed7c789fec3a8225184e38ae597196a700e5d78a","first_computed_at":"2026-07-23T01:25:18.306489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:25:18.306489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Msdf8F7C79BJtT5i9vC/ohwdFFopNycs4KxZkJ/T1pMaUSoc6B3Nd56wnKq8RDPfZwhZVCEIIhkHvoVqLKAjAg==","signature_status":"signed_v1","signed_at":"2026-07-23T01:25:18.307373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6a68eec01fd2ee9c559c8a6eec4da14b9553fdaf17183dd9230474d0f92b9d2","sha256:5010368f88595749e4b96b68aa423d5fce8f5326386c8b46ba1fc801590741c9"],"state_sha256":"a73c9cd7c711b00310de393b2af2076b697a4cfbffe70930cd884b6b84be7168"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8YOJ4VI5j+QMq/PhhmKtU7NcQumu7flFr7fae3RegcZhdg+vGVRdPFoYNMLcMpEDZMB46MFaw5M9lvZJnKx5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:56:28.427070Z","bundle_sha256":"053c49af9d7953e6da11aeb64c5596a06406a7e2c45dae685ec4842754991d79"}}