{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B6G2NWKSCBWBPYOQETW3J2LWL2","short_pith_number":"pith:B6G2NWKS","canonical_record":{"source":{"id":"2405.16071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T05:44:55Z","cross_cats_sorted":[],"title_canon_sha256":"2d196d7d28a41fca313aa5a3cb312bbe802317a0f295f69f7538551621f99e43","abstract_canon_sha256":"ada4afd84b6fc8dc0ae25e67d493f2ec68a8f85220b4e3f3f6ef26b8ffb1e3e3"},"schema_version":"1.0"},"canonical_sha256":"0f8da6d952106c17e1d024edb4e9765e9fb7e807f7b17f38e470feb20a4adfe1","source":{"kind":"arxiv","id":"2405.16071","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16071","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16071v2","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16071","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"B6G2NWKSCBWB","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"B6G2NWKSCBWBPYOQ","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"B6G2NWKS","created_at":"2026-07-05T10:21:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B6G2NWKSCBWBPYOQETW3J2LWL2","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T05:44:55Z","cross_cats_sorted":[],"title_canon_sha256":"2d196d7d28a41fca313aa5a3cb312bbe802317a0f295f69f7538551621f99e43","abstract_canon_sha256":"ada4afd84b6fc8dc0ae25e67d493f2ec68a8f85220b4e3f3f6ef26b8ffb1e3e3"},"schema_version":"1.0"},"canonical_sha256":"0f8da6d952106c17e1d024edb4e9765e9fb7e807f7b17f38e470feb20a4adfe1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:59.998533Z","signature_b64":"paABmQt1BxUsGM7roNKSGcZx6cSKp5aSbQHfqkqU7BScEBC1uETHNzUKwsIGlYoI8olgyUGE8tNB1KUVwBPrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f8da6d952106c17e1d024edb4e9765e9fb7e807f7b17f38e470feb20a4adfe1","last_reissued_at":"2026-07-05T10:21:59.998034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:59.998034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16071","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":"2026-07-05T10:21:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/AbrSU5DPx8v0QSP3KQuakjWAjfzIuBlogPf0UPaKOc06opoNFc9bIH2VKdoR8x6DLx0lAp+Rbhq7e55LWhrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:59:02.857973Z"},"content_sha256":"05e66a9c780169a575b846f385b2f5c5e785230ba3c00470a8bbadbd7898005a","schema_version":"1.0","event_id":"sha256:05e66a9c780169a575b846f385b2f5c5e785230ba3c00470a8bbadbd7898005a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B6G2NWKSCBWBPYOQETW3J2LWL2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Gong, Fang Wan, Feng Liu, Mingxiang Liao, Qixiang Ye, Yue Liu, Yuzhong Zhao","submitted_at":"2024-05-25T05:44:55Z","abstract_excerpt":"One fundamental task of multimodal models is to translate referred image regions to human preferred language descriptions. Existing methods, however, ignore the resolution adaptability needs of different tasks, which hinders them to find out precise language descriptions. In this study, we propose a DynRefer approach, to pursue high-accuracy region-level referring through mimicking the resolution adaptability of human visual cognition. During training, DynRefer stochastically aligns language descriptions of multimodal tasks with images of multiple resolutions, which are constructed by nesting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16071","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/2405.16071/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":"2026-07-05T10:21:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZ03RFtwYHssqM03EE7tXg7FQ5Rz/2iE3uZq3qFXxB4iZYbo2Dsnk18AghbOr0ydWCpWoNA6ZQYN+d28ThYRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:59:02.858751Z"},"content_sha256":"6b8700b1a675035226a2d4dc74fcb2e2c9b60c082f1f02a623121674f1862aa0","schema_version":"1.0","event_id":"sha256:6b8700b1a675035226a2d4dc74fcb2e2c9b60c082f1f02a623121674f1862aa0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B6G2NWKSCBWBPYOQETW3J2LWL2/bundle.json","state_url":"https://pith.science/pith/B6G2NWKSCBWBPYOQETW3J2LWL2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B6G2NWKSCBWBPYOQETW3J2LWL2/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":"2026-08-06T04:59:02Z","links":{"resolver":"https://pith.science/pith/B6G2NWKSCBWBPYOQETW3J2LWL2","bundle":"https://pith.science/pith/B6G2NWKSCBWBPYOQETW3J2LWL2/bundle.json","state":"https://pith.science/pith/B6G2NWKSCBWBPYOQETW3J2LWL2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B6G2NWKSCBWBPYOQETW3J2LWL2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B6G2NWKSCBWBPYOQETW3J2LWL2","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":"ada4afd84b6fc8dc0ae25e67d493f2ec68a8f85220b4e3f3f6ef26b8ffb1e3e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T05:44:55Z","title_canon_sha256":"2d196d7d28a41fca313aa5a3cb312bbe802317a0f295f69f7538551621f99e43"},"schema_version":"1.0","source":{"id":"2405.16071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16071","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16071v2","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16071","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"B6G2NWKSCBWB","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"B6G2NWKSCBWBPYOQ","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"B6G2NWKS","created_at":"2026-07-05T10:21:59Z"}],"graph_snapshots":[{"event_id":"sha256:6b8700b1a675035226a2d4dc74fcb2e2c9b60c082f1f02a623121674f1862aa0","target":"graph","created_at":"2026-07-05T10:21:59Z","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/2405.16071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One fundamental task of multimodal models is to translate referred image regions to human preferred language descriptions. Existing methods, however, ignore the resolution adaptability needs of different tasks, which hinders them to find out precise language descriptions. In this study, we propose a DynRefer approach, to pursue high-accuracy region-level referring through mimicking the resolution adaptability of human visual cognition. During training, DynRefer stochastically aligns language descriptions of multimodal tasks with images of multiple resolutions, which are constructed by nesting ","authors_text":"Chen Gong, Fang Wan, Feng Liu, Mingxiang Liao, Qixiang Ye, Yue Liu, Yuzhong Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T05:44:55Z","title":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16071","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":"sha256:05e66a9c780169a575b846f385b2f5c5e785230ba3c00470a8bbadbd7898005a","target":"record","created_at":"2026-07-05T10:21:59Z","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":"ada4afd84b6fc8dc0ae25e67d493f2ec68a8f85220b4e3f3f6ef26b8ffb1e3e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T05:44:55Z","title_canon_sha256":"2d196d7d28a41fca313aa5a3cb312bbe802317a0f295f69f7538551621f99e43"},"schema_version":"1.0","source":{"id":"2405.16071","kind":"arxiv","version":2}},"canonical_sha256":"0f8da6d952106c17e1d024edb4e9765e9fb7e807f7b17f38e470feb20a4adfe1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f8da6d952106c17e1d024edb4e9765e9fb7e807f7b17f38e470feb20a4adfe1","first_computed_at":"2026-07-05T10:21:59.998034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:59.998034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"paABmQt1BxUsGM7roNKSGcZx6cSKp5aSbQHfqkqU7BScEBC1uETHNzUKwsIGlYoI8olgyUGE8tNB1KUVwBPrCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:59.998533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05e66a9c780169a575b846f385b2f5c5e785230ba3c00470a8bbadbd7898005a","sha256:6b8700b1a675035226a2d4dc74fcb2e2c9b60c082f1f02a623121674f1862aa0"],"state_sha256":"b6e0f9db6bb378121876fc6a2191912d2262327eebfd4dc9388904109f686629"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o9327p58g7a/r+ziAR5RnqmBPE9wI3MLEIGLsbF2/aG3/JWI4o8oIUiB4p7g+Mnee4LDJiY169dkqMBSPx2ZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:59:02.864371Z","bundle_sha256":"1e6250d6ef9724c7c8ce9f6a113f1d87f6f54b372f1fa3a52db1f0ea05de0de7"}}