{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EPSJ6W6H3PWP5BSSJAAJGZAIV7","short_pith_number":"pith:EPSJ6W6H","canonical_record":{"source":{"id":"2210.11109","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T09:10:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9c4ced88c46000ef33cc78d979e4d2538ab06f663f8d32b1beedcf025349de30","abstract_canon_sha256":"4237bea19ac4e17a121d552fcb34ded14c58463c939a1e4e612bbce5c82c9a92"},"schema_version":"1.0"},"canonical_sha256":"23e49f5bc7dbecfe86524800936408afcf457ee141a628774eec3bab8c9fb365","source":{"kind":"arxiv","id":"2210.11109","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11109","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11109v2","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11109","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"EPSJ6W6H3PWP","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"EPSJ6W6H3PWP5BSS","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"EPSJ6W6H","created_at":"2026-07-05T05:10:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EPSJ6W6H3PWP5BSSJAAJGZAIV7","target":"record","payload":{"canonical_record":{"source":{"id":"2210.11109","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T09:10:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9c4ced88c46000ef33cc78d979e4d2538ab06f663f8d32b1beedcf025349de30","abstract_canon_sha256":"4237bea19ac4e17a121d552fcb34ded14c58463c939a1e4e612bbce5c82c9a92"},"schema_version":"1.0"},"canonical_sha256":"23e49f5bc7dbecfe86524800936408afcf457ee141a628774eec3bab8c9fb365","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:41.316638Z","signature_b64":"fbILFd/Igk6SVu2BLsW4m82F95YdPfJaPQS1J/Gf3JTr6xTWIGY/i4KmMdOcWZYYfU9yBgXo9Dc46BS+lUDkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23e49f5bc7dbecfe86524800936408afcf457ee141a628774eec3bab8c9fb365","last_reissued_at":"2026-07-05T05:10:41.316145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:41.316145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.11109","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":"2026-07-05T05:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1cC6sx5N9GifORmdk16vFytcYoOhqRnpQGchd6uhz90uoA9VATI4tGSLJB1qN9f/FJruAqD5RufeABkAmiyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:24:55.637565Z"},"content_sha256":"b05f6ba685391751d2c93e085cb55dfc3df1924ffa4c30fdb3e45757ffe44c68","schema_version":"1.0","event_id":"sha256:b05f6ba685391751d2c93e085cb55dfc3df1924ffa4c30fdb3e45757ffe44c68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EPSJ6W6H3PWP5BSSJAAJGZAIV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jianguo Wei, Meishan Zhang, Min Zhang, Yueheng Sun, Yu Zhao, Zhichao Lin","submitted_at":"2022-10-20T09:10:17Z","abstract_excerpt":"Image-to-text tasks, such as open-ended image captioning and controllable image description, have received extensive attention for decades. Here, we further advance this line of work by presenting Visual Spatial Description (VSD), a new perspective for image-to-text toward spatial semantics. Given an image and two objects inside it, VSD aims to produce one description focusing on the spatial perspective between the two objects. Accordingly, we manually annotate a dataset to facilitate the investigation of the newly-introduced task and build several benchmark encoder-decoder models by using VL-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11109","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/2210.11109/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":"2026-07-05T05:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZcCRWY5NAOx+Xzod5ytXyVs5MT+ebkj9NrFH3IW4b+XIUUypzQPR3lP5wSP/oIGU0d8I3SZDn7yed2AuHknNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:24:55.638111Z"},"content_sha256":"086f97a1ec9f0c2c77bd49166c0b380c0ecfd790eeda5367f24c6c63367ab46f","schema_version":"1.0","event_id":"sha256:086f97a1ec9f0c2c77bd49166c0b380c0ecfd790eeda5367f24c6c63367ab46f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPSJ6W6H3PWP5BSSJAAJGZAIV7/bundle.json","state_url":"https://pith.science/pith/EPSJ6W6H3PWP5BSSJAAJGZAIV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPSJ6W6H3PWP5BSSJAAJGZAIV7/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":"2026-08-23T15:24:55Z","links":{"resolver":"https://pith.science/pith/EPSJ6W6H3PWP5BSSJAAJGZAIV7","bundle":"https://pith.science/pith/EPSJ6W6H3PWP5BSSJAAJGZAIV7/bundle.json","state":"https://pith.science/pith/EPSJ6W6H3PWP5BSSJAAJGZAIV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPSJ6W6H3PWP5BSSJAAJGZAIV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EPSJ6W6H3PWP5BSSJAAJGZAIV7","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":"4237bea19ac4e17a121d552fcb34ded14c58463c939a1e4e612bbce5c82c9a92","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T09:10:17Z","title_canon_sha256":"9c4ced88c46000ef33cc78d979e4d2538ab06f663f8d32b1beedcf025349de30"},"schema_version":"1.0","source":{"id":"2210.11109","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11109","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11109v2","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11109","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"EPSJ6W6H3PWP","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"EPSJ6W6H3PWP5BSS","created_at":"2026-07-05T05:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"EPSJ6W6H","created_at":"2026-07-05T05:10:41Z"}],"graph_snapshots":[{"event_id":"sha256:086f97a1ec9f0c2c77bd49166c0b380c0ecfd790eeda5367f24c6c63367ab46f","target":"graph","created_at":"2026-07-05T05:10:41Z","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/2210.11109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-to-text tasks, such as open-ended image captioning and controllable image description, have received extensive attention for decades. Here, we further advance this line of work by presenting Visual Spatial Description (VSD), a new perspective for image-to-text toward spatial semantics. Given an image and two objects inside it, VSD aims to produce one description focusing on the spatial perspective between the two objects. Accordingly, we manually annotate a dataset to facilitate the investigation of the newly-introduced task and build several benchmark encoder-decoder models by using VL-","authors_text":"Jianguo Wei, Meishan Zhang, Min Zhang, Yueheng Sun, Yu Zhao, Zhichao Lin","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T09:10:17Z","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11109","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:b05f6ba685391751d2c93e085cb55dfc3df1924ffa4c30fdb3e45757ffe44c68","target":"record","created_at":"2026-07-05T05:10:41Z","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":"4237bea19ac4e17a121d552fcb34ded14c58463c939a1e4e612bbce5c82c9a92","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T09:10:17Z","title_canon_sha256":"9c4ced88c46000ef33cc78d979e4d2538ab06f663f8d32b1beedcf025349de30"},"schema_version":"1.0","source":{"id":"2210.11109","kind":"arxiv","version":2}},"canonical_sha256":"23e49f5bc7dbecfe86524800936408afcf457ee141a628774eec3bab8c9fb365","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23e49f5bc7dbecfe86524800936408afcf457ee141a628774eec3bab8c9fb365","first_computed_at":"2026-07-05T05:10:41.316145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:41.316145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fbILFd/Igk6SVu2BLsW4m82F95YdPfJaPQS1J/Gf3JTr6xTWIGY/i4KmMdOcWZYYfU9yBgXo9Dc46BS+lUDkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:41.316638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11109","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b05f6ba685391751d2c93e085cb55dfc3df1924ffa4c30fdb3e45757ffe44c68","sha256:086f97a1ec9f0c2c77bd49166c0b380c0ecfd790eeda5367f24c6c63367ab46f"],"state_sha256":"27aaaaba9fcece90ab263703d3ceaa705abad7d09e931a8f3a003a48063d8b7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6Q7w0yBKK/BKhWB0tR6P5682MgcRhNZdRUEQDpyXOIJfXjbYrBDYp7hxz7T17NO4aX8sr9xHC2NTk3MP/4ADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T15:24:55.642897Z","bundle_sha256":"557f69c37c0069ccc0577bac620ef58afd94ca9a8f2e632971de72293939c97e"}}