{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QR2MLIBLLPTJ45EZRDCDXOH6JE","short_pith_number":"pith:QR2MLIBL","canonical_record":{"source":{"id":"2412.11025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T02:37:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37ff1e9669e778c0ec70d4ed3dd981064e4cf2f8f12315392ae3488ea4c9980d","abstract_canon_sha256":"33512ca7f51c227e0840b83282b6ccf55977b82e4ac4d787da4d5993760ebe5d"},"schema_version":"1.0"},"canonical_sha256":"8474c5a02b5be69e749988c43bb8fe49174e5c13ff2a78fa25a4002a5b7f3b64","source":{"kind":"arxiv","id":"2412.11025","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11025","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11025v1","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11025","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"QR2MLIBLLPTJ","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"QR2MLIBLLPTJ45EZ","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"QR2MLIBL","created_at":"2026-07-05T09:59:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QR2MLIBLLPTJ45EZRDCDXOH6JE","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T02:37:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37ff1e9669e778c0ec70d4ed3dd981064e4cf2f8f12315392ae3488ea4c9980d","abstract_canon_sha256":"33512ca7f51c227e0840b83282b6ccf55977b82e4ac4d787da4d5993760ebe5d"},"schema_version":"1.0"},"canonical_sha256":"8474c5a02b5be69e749988c43bb8fe49174e5c13ff2a78fa25a4002a5b7f3b64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:21.353662Z","signature_b64":"vfVf36iEcGkjKuqBUNgBTX84rSZ7dDu1qivweFLXGcV/0zC/FXDDzWkw2YOI4hXXt7RVnwNO5nBn65UBrf53Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8474c5a02b5be69e749988c43bb8fe49174e5c13ff2a78fa25a4002a5b7f3b64","last_reissued_at":"2026-07-05T09:59:21.353168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:21.353168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11025","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":"2026-07-05T09:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5SXok8l8PS6UDCtbOkWQ5I8Wym0x9SwQsZkulViKdTlDmCapVT+7mkPzbSEf6W8YNexRLUHaNLNz7fd+KgbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:17:47.423467Z"},"content_sha256":"593637de179b3dd54686f63cb32dd9e00021e578f018c0b598b482791bd860f1","schema_version":"1.0","event_id":"sha256:593637de179b3dd54686f63cb32dd9e00021e578f018c0b598b482791bd860f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QR2MLIBLLPTJ45EZRDCDXOH6JE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Simple to Professional: A Combinatorial Controllable Image Captioning Agent","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baoteng Li, Haiwen Zhang, Kongming Liang, Muxi Diao, Xinran Wang, Zhanyu Ma","submitted_at":"2024-12-15T02:37:20Z","abstract_excerpt":"The Controllable Image Captioning Agent (CapAgent) is an innovative system designed to bridge the gap between user simplicity and professional-level outputs in image captioning tasks. CapAgent automatically transforms user-provided simple instructions into detailed, professional instructions, enabling precise and context-aware caption generation. By leveraging multimodal large language models (MLLMs) and external tools such as object detection tool and search engines, the system ensures that captions adhere to specified guidelines, including sentiment, keywords, focus, and formatting. CapAgent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11025","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/2412.11025/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":"2026-07-05T09:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ut4z5SUHyIeCfS4T+4Kp308vgXUnKoGYWh0mRxbQQvVd1ZeSnWtzODD4hDF/xk7kw4dcfDO8P4fPI3FRCKA8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:17:47.424384Z"},"content_sha256":"27ed306ae52f463d2f109187a792aa6ec8c751da887ace125469ac2f4a533c34","schema_version":"1.0","event_id":"sha256:27ed306ae52f463d2f109187a792aa6ec8c751da887ace125469ac2f4a533c34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QR2MLIBLLPTJ45EZRDCDXOH6JE/bundle.json","state_url":"https://pith.science/pith/QR2MLIBLLPTJ45EZRDCDXOH6JE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QR2MLIBLLPTJ45EZRDCDXOH6JE/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":"2026-08-18T14:17:47Z","links":{"resolver":"https://pith.science/pith/QR2MLIBLLPTJ45EZRDCDXOH6JE","bundle":"https://pith.science/pith/QR2MLIBLLPTJ45EZRDCDXOH6JE/bundle.json","state":"https://pith.science/pith/QR2MLIBLLPTJ45EZRDCDXOH6JE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QR2MLIBLLPTJ45EZRDCDXOH6JE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QR2MLIBLLPTJ45EZRDCDXOH6JE","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":"33512ca7f51c227e0840b83282b6ccf55977b82e4ac4d787da4d5993760ebe5d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T02:37:20Z","title_canon_sha256":"37ff1e9669e778c0ec70d4ed3dd981064e4cf2f8f12315392ae3488ea4c9980d"},"schema_version":"1.0","source":{"id":"2412.11025","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11025","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11025v1","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11025","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"QR2MLIBLLPTJ","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"QR2MLIBLLPTJ45EZ","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"QR2MLIBL","created_at":"2026-07-05T09:59:21Z"}],"graph_snapshots":[{"event_id":"sha256:27ed306ae52f463d2f109187a792aa6ec8c751da887ace125469ac2f4a533c34","target":"graph","created_at":"2026-07-05T09:59:21Z","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/2412.11025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Controllable Image Captioning Agent (CapAgent) is an innovative system designed to bridge the gap between user simplicity and professional-level outputs in image captioning tasks. CapAgent automatically transforms user-provided simple instructions into detailed, professional instructions, enabling precise and context-aware caption generation. By leveraging multimodal large language models (MLLMs) and external tools such as object detection tool and search engines, the system ensures that captions adhere to specified guidelines, including sentiment, keywords, focus, and formatting. CapAgent","authors_text":"Baoteng Li, Haiwen Zhang, Kongming Liang, Muxi Diao, Xinran Wang, Zhanyu Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T02:37:20Z","title":"From Simple to Professional: A Combinatorial Controllable Image Captioning Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11025","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":"sha256:593637de179b3dd54686f63cb32dd9e00021e578f018c0b598b482791bd860f1","target":"record","created_at":"2026-07-05T09:59:21Z","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":"33512ca7f51c227e0840b83282b6ccf55977b82e4ac4d787da4d5993760ebe5d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T02:37:20Z","title_canon_sha256":"37ff1e9669e778c0ec70d4ed3dd981064e4cf2f8f12315392ae3488ea4c9980d"},"schema_version":"1.0","source":{"id":"2412.11025","kind":"arxiv","version":1}},"canonical_sha256":"8474c5a02b5be69e749988c43bb8fe49174e5c13ff2a78fa25a4002a5b7f3b64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8474c5a02b5be69e749988c43bb8fe49174e5c13ff2a78fa25a4002a5b7f3b64","first_computed_at":"2026-07-05T09:59:21.353168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:21.353168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vfVf36iEcGkjKuqBUNgBTX84rSZ7dDu1qivweFLXGcV/0zC/FXDDzWkw2YOI4hXXt7RVnwNO5nBn65UBrf53Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:21.353662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11025","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:593637de179b3dd54686f63cb32dd9e00021e578f018c0b598b482791bd860f1","sha256:27ed306ae52f463d2f109187a792aa6ec8c751da887ace125469ac2f4a533c34"],"state_sha256":"848880a33073382bc321bb63ca67514413998c5eef1c85e6f92454329811983c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iAWSR5tT/oYGSUYMuc0iAW4cIvzwgiQGNfuWPUWk7mNajEM36rTj0bz6ednPIMedYCiu/gFabFK5bNK+HRbDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:17:47.444965Z","bundle_sha256":"17f3b57ed885f6d0bf6108e9e273dee774db4a8ffcdbeeef5d13e88f361073ac"}}