{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JSC5ZZF3IAJK7RWSJ5QX2SGT5U","short_pith_number":"pith:JSC5ZZF3","canonical_record":{"source":{"id":"2209.13959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T09:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"6c4b9cb0b0e66e01108852e0e9baa64e0cb9f0babadd29108c1a3c45c3910827","abstract_canon_sha256":"1a0157c0088c56eac9e0fa8719074ec47ddd7b6fe90089638d46f9ba0d1c8937"},"schema_version":"1.0"},"canonical_sha256":"4c85dce4bb4012afc6d24f617d48d3ed073b7d933a365aa04aaa62605e9077dc","source":{"kind":"arxiv","id":"2209.13959","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.13959","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.13959v2","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13959","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"JSC5ZZF3IAJK","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"JSC5ZZF3IAJK7RWS","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"JSC5ZZF3","created_at":"2026-07-05T07:05:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JSC5ZZF3IAJK7RWSJ5QX2SGT5U","target":"record","payload":{"canonical_record":{"source":{"id":"2209.13959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T09:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"6c4b9cb0b0e66e01108852e0e9baa64e0cb9f0babadd29108c1a3c45c3910827","abstract_canon_sha256":"1a0157c0088c56eac9e0fa8719074ec47ddd7b6fe90089638d46f9ba0d1c8937"},"schema_version":"1.0"},"canonical_sha256":"4c85dce4bb4012afc6d24f617d48d3ed073b7d933a365aa04aaa62605e9077dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:05.203632Z","signature_b64":"dOasFXTbBZ7RchlSsPl1praXrM+00hcc4aXdBsEJMy1mZGcnFdywbh80jdCoD/zv9yJLdjtDTAM1lNafDQU5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c85dce4bb4012afc6d24f617d48d3ed073b7d933a365aa04aaa62605e9077dc","last_reissued_at":"2026-07-05T07:05:05.203110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:05.203110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.13959","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":"2026-07-05T07:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dgvKWbHx7XKG+4hvnfWnCsPbTw6aEj6kWnQ17s9rvQ9PYR72vuZqg7GW3G71C4pic0D4Fq+KPCZm9vgiQ7IWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:03:59.467816Z"},"content_sha256":"cbced77931a47683a21a2b392e7229fe00c4485df701346ed51eec3af5432956","schema_version":"1.0","event_id":"sha256:cbced77931a47683a21a2b392e7229fe00c4485df701346ed51eec3af5432956"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JSC5ZZF3IAJK7RWSJ5QX2SGT5U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengyuan Shi, Limin Wang, Ruopeng Gao, Weilin Huang","submitted_at":"2022-09-28T09:43:02Z","abstract_excerpt":"Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention operation with quadratic time complexity. To address this issue, we present a new multimodal transformer architecture, coined as Dynamic Mutilmodal DETR (Dynamic MDETR), by decoupling the whole grounding process into encoding and decoding phases. The key observation is that there exists high spatial redundancy in images. Thus, we devise a new dynamic multimodal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13959","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/2209.13959/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":"2026-07-05T07:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J0s3gTD3guRaLlzJjVLEzVHUadZB4a9dTdQ6Ib/CyCXWDqKaCwwO4cmsGpnk2wjox1lV1slYdpb6WmAOe4+CBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:03:59.468641Z"},"content_sha256":"154bc5ea4eb0ab6656c3a11a3d57d0ff16c2b8e337a2e63c45537e41ac042cfb","schema_version":"1.0","event_id":"sha256:154bc5ea4eb0ab6656c3a11a3d57d0ff16c2b8e337a2e63c45537e41ac042cfb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JSC5ZZF3IAJK7RWSJ5QX2SGT5U/bundle.json","state_url":"https://pith.science/pith/JSC5ZZF3IAJK7RWSJ5QX2SGT5U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JSC5ZZF3IAJK7RWSJ5QX2SGT5U/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":"2026-08-11T08:03:59Z","links":{"resolver":"https://pith.science/pith/JSC5ZZF3IAJK7RWSJ5QX2SGT5U","bundle":"https://pith.science/pith/JSC5ZZF3IAJK7RWSJ5QX2SGT5U/bundle.json","state":"https://pith.science/pith/JSC5ZZF3IAJK7RWSJ5QX2SGT5U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JSC5ZZF3IAJK7RWSJ5QX2SGT5U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JSC5ZZF3IAJK7RWSJ5QX2SGT5U","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":"1a0157c0088c56eac9e0fa8719074ec47ddd7b6fe90089638d46f9ba0d1c8937","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T09:43:02Z","title_canon_sha256":"6c4b9cb0b0e66e01108852e0e9baa64e0cb9f0babadd29108c1a3c45c3910827"},"schema_version":"1.0","source":{"id":"2209.13959","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.13959","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.13959v2","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13959","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"JSC5ZZF3IAJK","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"JSC5ZZF3IAJK7RWS","created_at":"2026-07-05T07:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"JSC5ZZF3","created_at":"2026-07-05T07:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:154bc5ea4eb0ab6656c3a11a3d57d0ff16c2b8e337a2e63c45537e41ac042cfb","target":"graph","created_at":"2026-07-05T07:05:05Z","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/2209.13959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention operation with quadratic time complexity. To address this issue, we present a new multimodal transformer architecture, coined as Dynamic Mutilmodal DETR (Dynamic MDETR), by decoupling the whole grounding process into encoding and decoding phases. The key observation is that there exists high spatial redundancy in images. Thus, we devise a new dynamic multimodal ","authors_text":"Fengyuan Shi, Limin Wang, Ruopeng Gao, Weilin Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T09:43:02Z","title":"Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13959","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:cbced77931a47683a21a2b392e7229fe00c4485df701346ed51eec3af5432956","target":"record","created_at":"2026-07-05T07:05:05Z","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":"1a0157c0088c56eac9e0fa8719074ec47ddd7b6fe90089638d46f9ba0d1c8937","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T09:43:02Z","title_canon_sha256":"6c4b9cb0b0e66e01108852e0e9baa64e0cb9f0babadd29108c1a3c45c3910827"},"schema_version":"1.0","source":{"id":"2209.13959","kind":"arxiv","version":2}},"canonical_sha256":"4c85dce4bb4012afc6d24f617d48d3ed073b7d933a365aa04aaa62605e9077dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c85dce4bb4012afc6d24f617d48d3ed073b7d933a365aa04aaa62605e9077dc","first_computed_at":"2026-07-05T07:05:05.203110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:05.203110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dOasFXTbBZ7RchlSsPl1praXrM+00hcc4aXdBsEJMy1mZGcnFdywbh80jdCoD/zv9yJLdjtDTAM1lNafDQU5Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:05.203632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.13959","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbced77931a47683a21a2b392e7229fe00c4485df701346ed51eec3af5432956","sha256:154bc5ea4eb0ab6656c3a11a3d57d0ff16c2b8e337a2e63c45537e41ac042cfb"],"state_sha256":"95a6c10cc64fdce79372612ffd9c8a717d203b91aaccf2c075541edd7eb1af32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUNFWHiPJsS7Or4QxfD8hYMtAyHaz3Cy0bdfgCFOdxdwGVES9AMyZKftOU8uUWJs6YYhHXaVijySOKHERyXFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:03:59.474443Z","bundle_sha256":"720af1943a4cb7b51b3c2bf20bc778f2037841e3627f842fac9dcfe6c0ef4c53"}}