{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MD6UW6X4FP2NAUMBN4FD6Z3VMM","short_pith_number":"pith:MD6UW6X4","canonical_record":{"source":{"id":"2003.00387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-01T03:34:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfa8330175a257c4802540d6186c04968faa933fd4746b82930fa0ac57346905","abstract_canon_sha256":"0413e634d069b532458bf7083ef146b33775bf20ff67eb22c8dd54ccd983cbaf"},"schema_version":"1.0"},"canonical_sha256":"60fd4b7afc2bf4d051816f0a3f677563311ee26f5135d620aa0d19989aa1f491","source":{"kind":"arxiv","id":"2003.00387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.00387","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2003.00387v1","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00387","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"MD6UW6X4FP2N","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"MD6UW6X4FP2NAUMB","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"MD6UW6X4","created_at":"2026-07-05T00:44:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MD6UW6X4FP2NAUMBN4FD6Z3VMM","target":"record","payload":{"canonical_record":{"source":{"id":"2003.00387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-01T03:34:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfa8330175a257c4802540d6186c04968faa933fd4746b82930fa0ac57346905","abstract_canon_sha256":"0413e634d069b532458bf7083ef146b33775bf20ff67eb22c8dd54ccd983cbaf"},"schema_version":"1.0"},"canonical_sha256":"60fd4b7afc2bf4d051816f0a3f677563311ee26f5135d620aa0d19989aa1f491","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:46.440255Z","signature_b64":"SaDl+7tKmj8BTJ7osd1XOJdey2ADERXinOONcJX6bf2VksuDNIoQqgtB12YC4eP1aHWE5nfNtEOzIk0ED78lDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60fd4b7afc2bf4d051816f0a3f677563311ee26f5135d620aa0d19989aa1f491","last_reissued_at":"2026-07-05T00:44:46.439833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:46.439833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.00387","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":"2026-07-05T00:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f7JfXGRSSW1DZXW9jOLljhCaqRqgJd+YVOrlAjI5uQCbMZUzcl2OQ5LiJsWGdFde1l7BGLz+Q7kmzG+XQ6VjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:24:01.263251Z"},"content_sha256":"5e433e4a86e5d74f087d0b87e9edea9827c0d2c0f45e43fe6cdafe0c099db60e","schema_version":"1.0","event_id":"sha256:5e433e4a86e5d74f087d0b87e9edea9827c0d2c0f45e43fe6cdafe0c099db60e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MD6UW6X4FP2NAUMBN4FD6Z3VMM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Peng Wang, Qin Jin, Qi Wu, Shizhe Chen","submitted_at":"2020-03-01T03:34:07Z","abstract_excerpt":"Humans are able to describe image contents with coarse to fine details as they wish. However, most image captioning models are intention-agnostic which can not generate diverse descriptions according to different user intentions initiatively. In this work, we propose the Abstract Scene Graph (ASG) structure to represent user intention in fine-grained level and control what and how detailed the generated description should be. The ASG is a directed graph consisting of three types of \\textbf{abstract nodes} (object, attribute, relationship) grounded in the image without any concrete semantic lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00387","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/2003.00387/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":"2026-07-05T00:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQVn7nHi9FgjV5ufFzC2QN5PoEjPjiWTY9Wmo+yliXkETyc65zPPRYLgTW+jk9mhtzbH3C2kCnNcA+L1dfpWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:24:01.263800Z"},"content_sha256":"46e35446acd26085694b8a5dc9652c74cd7bf484890cc19183afc025fdc39d8f","schema_version":"1.0","event_id":"sha256:46e35446acd26085694b8a5dc9652c74cd7bf484890cc19183afc025fdc39d8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MD6UW6X4FP2NAUMBN4FD6Z3VMM/bundle.json","state_url":"https://pith.science/pith/MD6UW6X4FP2NAUMBN4FD6Z3VMM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MD6UW6X4FP2NAUMBN4FD6Z3VMM/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":"2026-08-18T20:24:01Z","links":{"resolver":"https://pith.science/pith/MD6UW6X4FP2NAUMBN4FD6Z3VMM","bundle":"https://pith.science/pith/MD6UW6X4FP2NAUMBN4FD6Z3VMM/bundle.json","state":"https://pith.science/pith/MD6UW6X4FP2NAUMBN4FD6Z3VMM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MD6UW6X4FP2NAUMBN4FD6Z3VMM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MD6UW6X4FP2NAUMBN4FD6Z3VMM","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":"0413e634d069b532458bf7083ef146b33775bf20ff67eb22c8dd54ccd983cbaf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-01T03:34:07Z","title_canon_sha256":"cfa8330175a257c4802540d6186c04968faa933fd4746b82930fa0ac57346905"},"schema_version":"1.0","source":{"id":"2003.00387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.00387","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2003.00387v1","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00387","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"MD6UW6X4FP2N","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"MD6UW6X4FP2NAUMB","created_at":"2026-07-05T00:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"MD6UW6X4","created_at":"2026-07-05T00:44:46Z"}],"graph_snapshots":[{"event_id":"sha256:46e35446acd26085694b8a5dc9652c74cd7bf484890cc19183afc025fdc39d8f","target":"graph","created_at":"2026-07-05T00:44:46Z","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/2003.00387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans are able to describe image contents with coarse to fine details as they wish. However, most image captioning models are intention-agnostic which can not generate diverse descriptions according to different user intentions initiatively. In this work, we propose the Abstract Scene Graph (ASG) structure to represent user intention in fine-grained level and control what and how detailed the generated description should be. The ASG is a directed graph consisting of three types of \\textbf{abstract nodes} (object, attribute, relationship) grounded in the image without any concrete semantic lab","authors_text":"Peng Wang, Qin Jin, Qi Wu, Shizhe Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-01T03:34:07Z","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00387","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":"sha256:5e433e4a86e5d74f087d0b87e9edea9827c0d2c0f45e43fe6cdafe0c099db60e","target":"record","created_at":"2026-07-05T00:44:46Z","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":"0413e634d069b532458bf7083ef146b33775bf20ff67eb22c8dd54ccd983cbaf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-01T03:34:07Z","title_canon_sha256":"cfa8330175a257c4802540d6186c04968faa933fd4746b82930fa0ac57346905"},"schema_version":"1.0","source":{"id":"2003.00387","kind":"arxiv","version":1}},"canonical_sha256":"60fd4b7afc2bf4d051816f0a3f677563311ee26f5135d620aa0d19989aa1f491","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60fd4b7afc2bf4d051816f0a3f677563311ee26f5135d620aa0d19989aa1f491","first_computed_at":"2026-07-05T00:44:46.439833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:46.439833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SaDl+7tKmj8BTJ7osd1XOJdey2ADERXinOONcJX6bf2VksuDNIoQqgtB12YC4eP1aHWE5nfNtEOzIk0ED78lDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:46.440255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.00387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e433e4a86e5d74f087d0b87e9edea9827c0d2c0f45e43fe6cdafe0c099db60e","sha256:46e35446acd26085694b8a5dc9652c74cd7bf484890cc19183afc025fdc39d8f"],"state_sha256":"dc49f9362286798fb71ff808f66f789ca93ce261ce7922a9e74cc56f297c6a82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uH5AwtkyLl2nVbyBm/oe3npv/Nl2kmqsBYWZ2kesPto42udRH0SUUlzVkCRcxtgrUT4+6yCZSrtFOFCzwvIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:24:01.270274Z","bundle_sha256":"fcd732d3eca84c43d30510f37e539ecbd8702dd1092f3fe51e3d1d480e68a7d5"}}