{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XPS6PH25VERPCHV6SYJ6TWBSHM","short_pith_number":"pith:XPS6PH25","canonical_record":{"source":{"id":"2509.04378","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T16:40:15Z","cross_cats_sorted":[],"title_canon_sha256":"a9e62176241ca3ff9948b047cce53f93a0663a0099c7dd2dda130f267171780d","abstract_canon_sha256":"fdfb755e210f6cd557db6be0c6104c93b0a94771e6653da21d63bb75507a2615"},"schema_version":"1.0"},"canonical_sha256":"bbe5e79f5da922f11ebe9613e9d8323b237c5fb6344cf8664389ee6ddceebee1","source":{"kind":"arxiv","id":"2509.04378","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04378","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04378v3","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04378","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"XPS6PH25VERP","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"XPS6PH25VERPCHV6","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"XPS6PH25","created_at":"2026-07-05T12:07:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XPS6PH25VERPCHV6SYJ6TWBSHM","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04378","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T16:40:15Z","cross_cats_sorted":[],"title_canon_sha256":"a9e62176241ca3ff9948b047cce53f93a0663a0099c7dd2dda130f267171780d","abstract_canon_sha256":"fdfb755e210f6cd557db6be0c6104c93b0a94771e6653da21d63bb75507a2615"},"schema_version":"1.0"},"canonical_sha256":"bbe5e79f5da922f11ebe9613e9d8323b237c5fb6344cf8664389ee6ddceebee1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:11.929649Z","signature_b64":"N9NdbB8LMWwaSuhsOOoWAjb5XwLeVc22kZAWvCzoNnBZOU1LZa+MLhKcku2DHNfqJeqRTyGN3oJvB++l5QLCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbe5e79f5da922f11ebe9613e9d8323b237c5fb6344cf8664389ee6ddceebee1","last_reissued_at":"2026-07-05T12:07:11.929213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:11.929213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04378","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"onyLThlgCzYEczbMgIsCt2oJH18AZW2sPt3ItjMifld8vrU5fczQO2CLooM2ZfNxhuO/36OP6kRcI9pjV0Y7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:51:45.271395Z"},"content_sha256":"6e01ecba862b59795028fb5641e548e20fab5b9e9578afc70065bf8d163d5a4d","schema_version":"1.0","event_id":"sha256:6e01ecba862b59795028fb5641e548e20fab5b9e9578afc70065bf8d163d5a4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XPS6PH25VERPCHV6SYJ6TWBSHM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aesthetic Image Captioning with Saliency Enhanced MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaze Xu, Jiashui Huang, Ling Shao, Yilin Tao","submitted_at":"2025-09-04T16:40:15Z","abstract_excerpt":"Aesthetic Image Captioning (AIC) aims to generate textual descriptions of image aesthetics, becoming a key research direction in the field of computational aesthetics. In recent years, pretrained Multimodal Large Language Models (MLLMs) have advanced rapidly, leading to a significant increase in image aesthetics research that integrates both visual and textual modalities. However, most existing studies on image aesthetics primarily focus on predicting aesthetic ratings and have shown limited application in AIC. Existing AIC works leveraging MLLMs predominantly rely on fine-tuning methods witho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04378","kind":"arxiv","version":3},"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/2509.04378/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":"2026-07-05T12:07:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gdMHk3VLjmTDICsNTJQmzqBgzyhf7rUV79xjJeY4LCMm5iUBNXZ0Zzhxe5qAkgDYiJ9404RVKsxC69bDwfOuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:51:45.272673Z"},"content_sha256":"0fa4459f59f81affe94bca70497b4a0e449289fca2332076bc1afe1356ce8966","schema_version":"1.0","event_id":"sha256:0fa4459f59f81affe94bca70497b4a0e449289fca2332076bc1afe1356ce8966"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPS6PH25VERPCHV6SYJ6TWBSHM/bundle.json","state_url":"https://pith.science/pith/XPS6PH25VERPCHV6SYJ6TWBSHM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPS6PH25VERPCHV6SYJ6TWBSHM/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":"2026-08-06T10:51:45Z","links":{"resolver":"https://pith.science/pith/XPS6PH25VERPCHV6SYJ6TWBSHM","bundle":"https://pith.science/pith/XPS6PH25VERPCHV6SYJ6TWBSHM/bundle.json","state":"https://pith.science/pith/XPS6PH25VERPCHV6SYJ6TWBSHM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPS6PH25VERPCHV6SYJ6TWBSHM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPS6PH25VERPCHV6SYJ6TWBSHM","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":"fdfb755e210f6cd557db6be0c6104c93b0a94771e6653da21d63bb75507a2615","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T16:40:15Z","title_canon_sha256":"a9e62176241ca3ff9948b047cce53f93a0663a0099c7dd2dda130f267171780d"},"schema_version":"1.0","source":{"id":"2509.04378","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04378","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04378v3","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04378","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"XPS6PH25VERP","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"XPS6PH25VERPCHV6","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"XPS6PH25","created_at":"2026-07-05T12:07:11Z"}],"graph_snapshots":[{"event_id":"sha256:0fa4459f59f81affe94bca70497b4a0e449289fca2332076bc1afe1356ce8966","target":"graph","created_at":"2026-07-05T12:07:11Z","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/2509.04378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aesthetic Image Captioning (AIC) aims to generate textual descriptions of image aesthetics, becoming a key research direction in the field of computational aesthetics. In recent years, pretrained Multimodal Large Language Models (MLLMs) have advanced rapidly, leading to a significant increase in image aesthetics research that integrates both visual and textual modalities. However, most existing studies on image aesthetics primarily focus on predicting aesthetic ratings and have shown limited application in AIC. Existing AIC works leveraging MLLMs predominantly rely on fine-tuning methods witho","authors_text":"Huaze Xu, Jiashui Huang, Ling Shao, Yilin Tao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T16:40:15Z","title":"Aesthetic Image Captioning with Saliency Enhanced MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04378","kind":"arxiv","version":3},"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":"sha256:6e01ecba862b59795028fb5641e548e20fab5b9e9578afc70065bf8d163d5a4d","target":"record","created_at":"2026-07-05T12:07:11Z","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":"fdfb755e210f6cd557db6be0c6104c93b0a94771e6653da21d63bb75507a2615","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T16:40:15Z","title_canon_sha256":"a9e62176241ca3ff9948b047cce53f93a0663a0099c7dd2dda130f267171780d"},"schema_version":"1.0","source":{"id":"2509.04378","kind":"arxiv","version":3}},"canonical_sha256":"bbe5e79f5da922f11ebe9613e9d8323b237c5fb6344cf8664389ee6ddceebee1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbe5e79f5da922f11ebe9613e9d8323b237c5fb6344cf8664389ee6ddceebee1","first_computed_at":"2026-07-05T12:07:11.929213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:11.929213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N9NdbB8LMWwaSuhsOOoWAjb5XwLeVc22kZAWvCzoNnBZOU1LZa+MLhKcku2DHNfqJeqRTyGN3oJvB++l5QLCDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:11.929649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04378","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e01ecba862b59795028fb5641e548e20fab5b9e9578afc70065bf8d163d5a4d","sha256:0fa4459f59f81affe94bca70497b4a0e449289fca2332076bc1afe1356ce8966"],"state_sha256":"95280116c0892aafc08a08ff18939ad838fa66756b2d8658528d0eb67d75373b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+WXSkaXdSDh40L30SGL2hg81Zw+HbCoFk2jew2Lt4uFaolWecCuBLk1w78qx/3cUabFVndnVnaUFdd+iYfhjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:51:45.279706Z","bundle_sha256":"a04c783f9786d4929e617bcabb84de368487b1161d2691149be65097e0768bec"}}