{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LJE5N6M3XPGMQRCNN47BJRR7RS","short_pith_number":"pith:LJE5N6M3","canonical_record":{"source":{"id":"2608.13037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T10:05:16Z","cross_cats_sorted":[],"title_canon_sha256":"19e385d2f1e8260797a9e8615f96a025afd9d36a7ba8ec0d847040c3922eab9e","abstract_canon_sha256":"5eaac17e4c915674996270e89b26b527782eddcd571747e41f5f44b217ec6842"},"schema_version":"1.0"},"canonical_sha256":"5a49d6f99bbbccc8444d6f3e14c63f8cbd4a921d37b969ceabf22359e1dcaf48","source":{"kind":"arxiv","id":"2608.13037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13037","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13037v1","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13037","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"LJE5N6M3XPGM","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_16","alias_value":"LJE5N6M3XPGMQRCN","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_8","alias_value":"LJE5N6M3","created_at":"2026-08-14T01:00:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LJE5N6M3XPGMQRCNN47BJRR7RS","target":"record","payload":{"canonical_record":{"source":{"id":"2608.13037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T10:05:16Z","cross_cats_sorted":[],"title_canon_sha256":"19e385d2f1e8260797a9e8615f96a025afd9d36a7ba8ec0d847040c3922eab9e","abstract_canon_sha256":"5eaac17e4c915674996270e89b26b527782eddcd571747e41f5f44b217ec6842"},"schema_version":"1.0"},"canonical_sha256":"5a49d6f99bbbccc8444d6f3e14c63f8cbd4a921d37b969ceabf22359e1dcaf48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:11.217502Z","signature_b64":"xXS64IRiXB5CWGYhzRimNPGjgnlVvFwUM9Kde6Ud14EGD0vxyzyWcex3g2NGDarQjgWmBeMg7PzvunSKnVJCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a49d6f99bbbccc8444d6f3e14c63f8cbd4a921d37b969ceabf22359e1dcaf48","last_reissued_at":"2026-08-14T01:00:11.215412Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:11.215412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.13037","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":"2026-08-14T01:00:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BtqZR2g7Jo/JMj4MJThTXLYfKXcyGdO21EJXhkMBbSB9xRZ1Y7AWPpo/kVr3ExnJydcoe9CPxmpSt924w/NvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:58:45.602246Z"},"content_sha256":"931b487af4244219b81146462d0fcac658264eb13b9f3300bde547f1248c6403","schema_version":"1.0","event_id":"sha256:931b487af4244219b81146462d0fcac658264eb13b9f3300bde547f1248c6403"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LJE5N6M3XPGMQRCNN47BJRR7RS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnaud Dapogny, Guillaume Jeanneret, Hugo Caselles-Dupr\\'e, Mathis Koroglu, Matthieu Cord","submitted_at":"2026-08-13T10:05:16Z","abstract_excerpt":"Diffusion Transformer Text-to-Video models have achieved remarkable synthesis quality, yet fine-grained spatial controllability remains a significant challenge. While existing training-free methods produce solid overall results in spatially grounded generation, \\ie, placing a specific object in a designated location, they rely on gradient-based optimization techniques that incur prohibitive computational overhead, a bottleneck amplified in modern large-scale architectures. To address this limitation, we present Gradient-free Analytical Trajectory Optimization Video Generation (GATO-Vid), a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13037","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/2608.13037/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":"2026-08-14T01:00:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+ms45Tufk7/u3Qj+RX4HUC1CX3D3AUiLEyQeI/vw7I+jbak/7Nz5BWH7OcL2N7XhJ5fwyPE7Vx1MTlMS5NZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:58:45.603293Z"},"content_sha256":"06a9ce6d65a3cfe3d0ee4b8bba9c99bd017a460f45addc9b8eb922a3d19cc44b","schema_version":"1.0","event_id":"sha256:06a9ce6d65a3cfe3d0ee4b8bba9c99bd017a460f45addc9b8eb922a3d19cc44b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:LJE5N6M3XPGMQRCNN47BJRR7RS","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1609/aaai.v38i6.28364) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Wang, R., Chen, Z., Chen, C., Ma, J., Lu, H., Lin, X.: Compositional text- to-image synthesis with attention map control of diffusion models. In: Pro- ceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth","arxiv_id":"2608.13037","detector":"doi_compliance","evidence":{"ref_index":41,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1609/aaai.v38","reconstructed_doi":"10.1609/aaai.v38i6.28364"},"severity":"advisory","ref_index":41,"audited_at":"2026-08-15T18:18:03.838017Z","event_type":"pith.integrity.v1","detected_doi":"10.1609/aaai.v38i6.28364","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"515ac8bba2c17099f4e6cf2f2ccf7cd3f5ad80e03f30bd0aa708de150ae5ccdc","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":20012,"payload_sha256":"dfcff008413843ecbd90427577a761a37123f572d5f0d5291179ec1c0ebb4924","signature_b64":"jkPTibAR0Z0r4HhXvXP3QZT86FDhESMnDgd5ganGv6rZzpDSZiRzpO7XznfUUikQm+3LZKvHHlMVwpg1wdyEAg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-15T18:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7ojS7UW57kUbH/XIzeiNfvZcLfO/IFOyydMlpYsfgwhQzb2lzvKl5eREIUjpbNYrj95PdxPPOoAWcW/VPxKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:58:45.630836Z"},"content_sha256":"afb3e51969f500841f051637ddb1040f59688452224838673a341cd00d94a547","schema_version":"1.0","event_id":"sha256:afb3e51969f500841f051637ddb1040f59688452224838673a341cd00d94a547"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJE5N6M3XPGMQRCNN47BJRR7RS/bundle.json","state_url":"https://pith.science/pith/LJE5N6M3XPGMQRCNN47BJRR7RS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJE5N6M3XPGMQRCNN47BJRR7RS/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":"2026-08-18T04:58:45Z","links":{"resolver":"https://pith.science/pith/LJE5N6M3XPGMQRCNN47BJRR7RS","bundle":"https://pith.science/pith/LJE5N6M3XPGMQRCNN47BJRR7RS/bundle.json","state":"https://pith.science/pith/LJE5N6M3XPGMQRCNN47BJRR7RS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJE5N6M3XPGMQRCNN47BJRR7RS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LJE5N6M3XPGMQRCNN47BJRR7RS","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5eaac17e4c915674996270e89b26b527782eddcd571747e41f5f44b217ec6842","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T10:05:16Z","title_canon_sha256":"19e385d2f1e8260797a9e8615f96a025afd9d36a7ba8ec0d847040c3922eab9e"},"schema_version":"1.0","source":{"id":"2608.13037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13037","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13037v1","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13037","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"LJE5N6M3XPGM","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_16","alias_value":"LJE5N6M3XPGMQRCN","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_8","alias_value":"LJE5N6M3","created_at":"2026-08-14T01:00:11Z"}],"graph_snapshots":[{"event_id":"sha256:06a9ce6d65a3cfe3d0ee4b8bba9c99bd017a460f45addc9b8eb922a3d19cc44b","target":"graph","created_at":"2026-08-14T01:00:11Z","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/2608.13037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion Transformer Text-to-Video models have achieved remarkable synthesis quality, yet fine-grained spatial controllability remains a significant challenge. While existing training-free methods produce solid overall results in spatially grounded generation, \\ie, placing a specific object in a designated location, they rely on gradient-based optimization techniques that incur prohibitive computational overhead, a bottleneck amplified in modern large-scale architectures. To address this limitation, we present Gradient-free Analytical Trajectory Optimization Video Generation (GATO-Vid), a nov","authors_text":"Arnaud Dapogny, Guillaume Jeanneret, Hugo Caselles-Dupr\\'e, Mathis Koroglu, Matthieu Cord","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T10:05:16Z","title":"Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13037","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":"sha256:931b487af4244219b81146462d0fcac658264eb13b9f3300bde547f1248c6403","target":"record","created_at":"2026-08-14T01:00:11Z","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":"5eaac17e4c915674996270e89b26b527782eddcd571747e41f5f44b217ec6842","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T10:05:16Z","title_canon_sha256":"19e385d2f1e8260797a9e8615f96a025afd9d36a7ba8ec0d847040c3922eab9e"},"schema_version":"1.0","source":{"id":"2608.13037","kind":"arxiv","version":1}},"canonical_sha256":"5a49d6f99bbbccc8444d6f3e14c63f8cbd4a921d37b969ceabf22359e1dcaf48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a49d6f99bbbccc8444d6f3e14c63f8cbd4a921d37b969ceabf22359e1dcaf48","first_computed_at":"2026-08-14T01:00:11.215412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:11.215412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xXS64IRiXB5CWGYhzRimNPGjgnlVvFwUM9Kde6Ud14EGD0vxyzyWcex3g2NGDarQjgWmBeMg7PzvunSKnVJCCg==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:11.217502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:931b487af4244219b81146462d0fcac658264eb13b9f3300bde547f1248c6403","sha256:06a9ce6d65a3cfe3d0ee4b8bba9c99bd017a460f45addc9b8eb922a3d19cc44b","sha256:afb3e51969f500841f051637ddb1040f59688452224838673a341cd00d94a547"],"state_sha256":"509700215710efa70a8eb98a2a70cf94ff77cf30e6d44f8e314ef4811ef936d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dyC5SjmUQiZVKVo45vTSUIC5oVAh6GyCbNhJBwa3EgK9X3jH74t/WiAXxjVtCw4EkqhocdRJMglAc27ZVf/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:58:45.633071Z","bundle_sha256":"1bfdb5fb0e86424f8df8961a66c4d5da52ed77ff2f771a0c22d27c49ceb469cc"}}