{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2SNO6TNC7OA4UVZQNI5M6WWBV3","short_pith_number":"pith:2SNO6TNC","canonical_record":{"source":{"id":"2412.20206","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-28T16:34:35Z","cross_cats_sorted":[],"title_canon_sha256":"9d5204c623c56911da2785123dcd49aa32ecc1c0ec6e36660cbed8db98d890ab","abstract_canon_sha256":"223b94c8cba730f614f90166ee1c8bb3b08bee849441a4b56ca505d9baf65389"},"schema_version":"1.0"},"canonical_sha256":"d49aef4da2fb81ca57306a3acf5ac1aecc30b0690958ca2e6f2ba2fe6f0dd90c","source":{"kind":"arxiv","id":"2412.20206","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20206","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20206v4","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20206","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"2SNO6TNC7OA4","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"2SNO6TNC7OA4UVZQ","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"2SNO6TNC","created_at":"2026-08-05T01:33:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2SNO6TNC7OA4UVZQNI5M6WWBV3","target":"record","payload":{"canonical_record":{"source":{"id":"2412.20206","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-28T16:34:35Z","cross_cats_sorted":[],"title_canon_sha256":"9d5204c623c56911da2785123dcd49aa32ecc1c0ec6e36660cbed8db98d890ab","abstract_canon_sha256":"223b94c8cba730f614f90166ee1c8bb3b08bee849441a4b56ca505d9baf65389"},"schema_version":"1.0"},"canonical_sha256":"d49aef4da2fb81ca57306a3acf5ac1aecc30b0690958ca2e6f2ba2fe6f0dd90c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:33:16.306550Z","signature_b64":"3WwkoIHCxiwydA7m58gDUelSYHR8GsoCVtmMdP5GLNZlRN27Ivr8pk4hv8s/tsdzeOq5ff3WoDypXe91Lu9vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d49aef4da2fb81ca57306a3acf5ac1aecc30b0690958ca2e6f2ba2fe6f0dd90c","last_reissued_at":"2026-08-05T01:33:16.304882Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:33:16.304882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.20206","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T01:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WnC8DMZJkGjVqlnLSjnZf/LX5U5OMawLFl8s7UQ0B6iSNs6Dch3Dh+yVZ28/bDBZYuQy0BdchZMuRA0GGj03DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:25:27.633435Z"},"content_sha256":"eeaf3d7a811dd011ba5a35f33a67c23d41bf61c4bb5105b4090f824ae3339617","schema_version":"1.0","event_id":"sha256:eeaf3d7a811dd011ba5a35f33a67c23d41bf61c4bb5105b4090f824ae3339617"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2SNO6TNC7OA4UVZQNI5M6WWBV3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Visual Grounding: A Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Linhui Xiao, Xiangyuan Lan, Xiaoshan Yang, Yaowei Wang","submitted_at":"2024-12-28T16:34:35Z","abstract_excerpt":"Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships between visual and linguistic modalities, enabling machines to develop human-like multimodal comprehension capabilities. Consequently, it has extensive applications in various domains. However, since 2021, visual grounding has witnessed significant advancements, with emerging new concepts such as grounded pre-training, grounding multimodal LLMs, generalized "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20206","kind":"arxiv","version":4},"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/2412.20206/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":"2026-08-05T01:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zqjpNzAVt7UyNxXphK0+5VPxUz9SQLGnE+AE+JRtutqh+qWUjZEt3M7y/Y0zYcw9iblwYN3nb2IgkC4EYUDVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:25:27.633936Z"},"content_sha256":"428bd8012eb86cb06602819034b010cbacb0672d269e7fceca9871373b02f32b","schema_version":"1.0","event_id":"sha256:428bd8012eb86cb06602819034b010cbacb0672d269e7fceca9871373b02f32b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2SNO6TNC7OA4UVZQNI5M6WWBV3/bundle.json","state_url":"https://pith.science/pith/2SNO6TNC7OA4UVZQNI5M6WWBV3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2SNO6TNC7OA4UVZQNI5M6WWBV3/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":"2026-08-15T23:25:27Z","links":{"resolver":"https://pith.science/pith/2SNO6TNC7OA4UVZQNI5M6WWBV3","bundle":"https://pith.science/pith/2SNO6TNC7OA4UVZQNI5M6WWBV3/bundle.json","state":"https://pith.science/pith/2SNO6TNC7OA4UVZQNI5M6WWBV3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2SNO6TNC7OA4UVZQNI5M6WWBV3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2SNO6TNC7OA4UVZQNI5M6WWBV3","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":"223b94c8cba730f614f90166ee1c8bb3b08bee849441a4b56ca505d9baf65389","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-28T16:34:35Z","title_canon_sha256":"9d5204c623c56911da2785123dcd49aa32ecc1c0ec6e36660cbed8db98d890ab"},"schema_version":"1.0","source":{"id":"2412.20206","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20206","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20206v4","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20206","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"2SNO6TNC7OA4","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"2SNO6TNC7OA4UVZQ","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"2SNO6TNC","created_at":"2026-08-05T01:33:16Z"}],"graph_snapshots":[{"event_id":"sha256:428bd8012eb86cb06602819034b010cbacb0672d269e7fceca9871373b02f32b","target":"graph","created_at":"2026-08-05T01:33:16Z","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/2412.20206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships between visual and linguistic modalities, enabling machines to develop human-like multimodal comprehension capabilities. Consequently, it has extensive applications in various domains. However, since 2021, visual grounding has witnessed significant advancements, with emerging new concepts such as grounded pre-training, grounding multimodal LLMs, generalized ","authors_text":"Changsheng Xu, Linhui Xiao, Xiangyuan Lan, Xiaoshan Yang, Yaowei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-28T16:34:35Z","title":"Toward Visual Grounding: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20206","kind":"arxiv","version":4},"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:eeaf3d7a811dd011ba5a35f33a67c23d41bf61c4bb5105b4090f824ae3339617","target":"record","created_at":"2026-08-05T01:33:16Z","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":"223b94c8cba730f614f90166ee1c8bb3b08bee849441a4b56ca505d9baf65389","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-28T16:34:35Z","title_canon_sha256":"9d5204c623c56911da2785123dcd49aa32ecc1c0ec6e36660cbed8db98d890ab"},"schema_version":"1.0","source":{"id":"2412.20206","kind":"arxiv","version":4}},"canonical_sha256":"d49aef4da2fb81ca57306a3acf5ac1aecc30b0690958ca2e6f2ba2fe6f0dd90c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d49aef4da2fb81ca57306a3acf5ac1aecc30b0690958ca2e6f2ba2fe6f0dd90c","first_computed_at":"2026-08-05T01:33:16.304882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:33:16.304882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3WwkoIHCxiwydA7m58gDUelSYHR8GsoCVtmMdP5GLNZlRN27Ivr8pk4hv8s/tsdzeOq5ff3WoDypXe91Lu9vDg==","signature_status":"signed_v1","signed_at":"2026-08-05T01:33:16.306550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20206","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeaf3d7a811dd011ba5a35f33a67c23d41bf61c4bb5105b4090f824ae3339617","sha256:428bd8012eb86cb06602819034b010cbacb0672d269e7fceca9871373b02f32b"],"state_sha256":"03664a294dc67eae2bbb50ec78b7bff645ad1c56dfb44e1f774c88dd83c2628d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQdqY2zhtjm4SFWeltrDni/3U6hZyXLVDMagu5WhO4iTQMwO3eeQdV8jMTViyRrr7WODa4LaklOg9OrFSzGwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:25:27.638795Z","bundle_sha256":"6a0a8941cebc66d19230ae0d1f0f7324b0a1def6fb900827c21a6224a8b31d98"}}