{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CBKQNC54YUMW3J674T4P3DMBLX","short_pith_number":"pith:CBKQNC54","canonical_record":{"source":{"id":"2508.07330","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-10T13:03:40Z","cross_cats_sorted":[],"title_canon_sha256":"9a31fe8ff078a55fb70aed13fe1857689424dcce6014ebc6c0dbed2f547c0f17","abstract_canon_sha256":"790748b2dabdeb9b907d7cf38423e193fc66c164fa32864dc4d7db7768a45427"},"schema_version":"1.0"},"canonical_sha256":"1055068bbcc5196da7dfe4f8fd8d815dcccb7585ee7ccd01d62164d32d626db0","source":{"kind":"arxiv","id":"2508.07330","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07330","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07330v2","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07330","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_12","alias_value":"CBKQNC54YUMW","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_16","alias_value":"CBKQNC54YUMW3J67","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_8","alias_value":"CBKQNC54","created_at":"2026-07-05T11:54:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CBKQNC54YUMW3J674T4P3DMBLX","target":"record","payload":{"canonical_record":{"source":{"id":"2508.07330","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-10T13:03:40Z","cross_cats_sorted":[],"title_canon_sha256":"9a31fe8ff078a55fb70aed13fe1857689424dcce6014ebc6c0dbed2f547c0f17","abstract_canon_sha256":"790748b2dabdeb9b907d7cf38423e193fc66c164fa32864dc4d7db7768a45427"},"schema_version":"1.0"},"canonical_sha256":"1055068bbcc5196da7dfe4f8fd8d815dcccb7585ee7ccd01d62164d32d626db0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:50.661765Z","signature_b64":"R4YHaCeTt1+Dn/1+dAcZBYrToYgaIG2SVgex7zuVtHDYmhQTT+TXcehnxlF+wrSXzPkwbAam9W0lwb4qBSx3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1055068bbcc5196da7dfe4f8fd8d815dcccb7585ee7ccd01d62164d32d626db0","last_reissued_at":"2026-07-05T11:54:50.661278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:50.661278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.07330","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":"2026-07-05T11:54:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0V9vdlu7rBlqQusRql0JzHx1enVjUeF7e1U0B+Le3k9RCB7XjPRx69IkgnpjeZ/CfYEFPUbv+CIzMiPcXJVhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:17:33.385077Z"},"content_sha256":"6c6f53c3245508c5aeaa913c5b4ad26b132a4b9b7729eef4234d77099473a29f","schema_version":"1.0","event_id":"sha256:6c6f53c3245508c5aeaa913c5b4ad26b132a4b9b7729eef4234d77099473a29f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CBKQNC54YUMW3J674T4P3DMBLX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Quang-Hung Le, Thao Minh Le, Truyen Tran, Tuyen Tran","submitted_at":"2025-08-10T13:03:40Z","abstract_excerpt":"Vision-language alignment in video must address the complexity of language, evolving interacting entities, their action chains, and semantic gaps between language and vision. This work introduces Planner-Refiner, a framework to overcome these challenges. Planner-Refiner bridges the semantic gap by iteratively refining visual elements' space-time representation, guided by language until semantic gaps are minimal. A Planner module schedules language guidance by decomposing complex linguistic prompts into short sentence chains. The Refiner processes each short sentence, a noun-phrase and verb-phr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07330","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/2508.07330/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":"2026-07-05T11:54:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tWAlUBvVESsuItTtWCBvq62DJYwSDezB0MKR3GS2q/N1yt22SpMU5HrUDhUkOioZUz/TnBGQLIZscZoeIwUIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:17:33.385600Z"},"content_sha256":"fe4bfc07d9eebbb65c56d7bd1477fff819c275a116de1b4088a854e66d062c2a","schema_version":"1.0","event_id":"sha256:fe4bfc07d9eebbb65c56d7bd1477fff819c275a116de1b4088a854e66d062c2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBKQNC54YUMW3J674T4P3DMBLX/bundle.json","state_url":"https://pith.science/pith/CBKQNC54YUMW3J674T4P3DMBLX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBKQNC54YUMW3J674T4P3DMBLX/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":"2026-08-07T11:17:33Z","links":{"resolver":"https://pith.science/pith/CBKQNC54YUMW3J674T4P3DMBLX","bundle":"https://pith.science/pith/CBKQNC54YUMW3J674T4P3DMBLX/bundle.json","state":"https://pith.science/pith/CBKQNC54YUMW3J674T4P3DMBLX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBKQNC54YUMW3J674T4P3DMBLX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CBKQNC54YUMW3J674T4P3DMBLX","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":"790748b2dabdeb9b907d7cf38423e193fc66c164fa32864dc4d7db7768a45427","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-10T13:03:40Z","title_canon_sha256":"9a31fe8ff078a55fb70aed13fe1857689424dcce6014ebc6c0dbed2f547c0f17"},"schema_version":"1.0","source":{"id":"2508.07330","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07330","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07330v2","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07330","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_12","alias_value":"CBKQNC54YUMW","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_16","alias_value":"CBKQNC54YUMW3J67","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_8","alias_value":"CBKQNC54","created_at":"2026-07-05T11:54:50Z"}],"graph_snapshots":[{"event_id":"sha256:fe4bfc07d9eebbb65c56d7bd1477fff819c275a116de1b4088a854e66d062c2a","target":"graph","created_at":"2026-07-05T11:54:50Z","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/2508.07330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language alignment in video must address the complexity of language, evolving interacting entities, their action chains, and semantic gaps between language and vision. This work introduces Planner-Refiner, a framework to overcome these challenges. Planner-Refiner bridges the semantic gap by iteratively refining visual elements' space-time representation, guided by language until semantic gaps are minimal. A Planner module schedules language guidance by decomposing complex linguistic prompts into short sentence chains. The Refiner processes each short sentence, a noun-phrase and verb-phr","authors_text":"Quang-Hung Le, Thao Minh Le, Truyen Tran, Tuyen Tran","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-10T13:03:40Z","title":"Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07330","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":"sha256:6c6f53c3245508c5aeaa913c5b4ad26b132a4b9b7729eef4234d77099473a29f","target":"record","created_at":"2026-07-05T11:54:50Z","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":"790748b2dabdeb9b907d7cf38423e193fc66c164fa32864dc4d7db7768a45427","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-10T13:03:40Z","title_canon_sha256":"9a31fe8ff078a55fb70aed13fe1857689424dcce6014ebc6c0dbed2f547c0f17"},"schema_version":"1.0","source":{"id":"2508.07330","kind":"arxiv","version":2}},"canonical_sha256":"1055068bbcc5196da7dfe4f8fd8d815dcccb7585ee7ccd01d62164d32d626db0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1055068bbcc5196da7dfe4f8fd8d815dcccb7585ee7ccd01d62164d32d626db0","first_computed_at":"2026-07-05T11:54:50.661278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:50.661278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R4YHaCeTt1+Dn/1+dAcZBYrToYgaIG2SVgex7zuVtHDYmhQTT+TXcehnxlF+wrSXzPkwbAam9W0lwb4qBSx3DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:50.661765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07330","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c6f53c3245508c5aeaa913c5b4ad26b132a4b9b7729eef4234d77099473a29f","sha256:fe4bfc07d9eebbb65c56d7bd1477fff819c275a116de1b4088a854e66d062c2a"],"state_sha256":"5d9104e217a328611f688639157a50975b26fbf46d75dba0f0c0b0e884010ed7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7sdsk0fEjL13GyIvyavPb2aFzLhdM58F4OSD7VOIkjOgyPmQB2h/14jj7pX24mxdjqjd9qI9bXrkyBHmvsMpCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T11:17:33.389343Z","bundle_sha256":"95c792fa392b08485280ac878fef3e30d0d4fbf7e67bd461af7a092fce2bfb97"}}