{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S3CDZKXNGJKCSIRQWLS565EOXS","short_pith_number":"pith:S3CDZKXN","canonical_record":{"source":{"id":"2411.09955","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T05:18:15Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"title_canon_sha256":"4c592446ca287ab0e63501d36ada41a326461ac37f8c611c88f86d196d6a10e6","abstract_canon_sha256":"3c4ce46631f79c6df046d39d064411db74d707c547ee7a22a8b2261c96c5678b"},"schema_version":"1.0"},"canonical_sha256":"96c43caaed3254292230b2e5df748ebc852220e64c9a7e73873d105b533bfb7e","source":{"kind":"arxiv","id":"2411.09955","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09955","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09955v2","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09955","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"pith_short_12","alias_value":"S3CDZKXNGJKC","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"pith_short_16","alias_value":"S3CDZKXNGJKCSIRQ","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"pith_short_8","alias_value":"S3CDZKXN","created_at":"2026-07-05T09:38:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S3CDZKXNGJKCSIRQWLS565EOXS","target":"record","payload":{"canonical_record":{"source":{"id":"2411.09955","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T05:18:15Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"title_canon_sha256":"4c592446ca287ab0e63501d36ada41a326461ac37f8c611c88f86d196d6a10e6","abstract_canon_sha256":"3c4ce46631f79c6df046d39d064411db74d707c547ee7a22a8b2261c96c5678b"},"schema_version":"1.0"},"canonical_sha256":"96c43caaed3254292230b2e5df748ebc852220e64c9a7e73873d105b533bfb7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:32.501019Z","signature_b64":"KRLExmCpuSeHkPoJvR/hcxofAbAqfDNLJbIrcTX9YdqwMkWayS5VeEkFB+dfQlUMueCYwNiqSDZ7MnytdPXyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96c43caaed3254292230b2e5df748ebc852220e64c9a7e73873d105b533bfb7e","last_reissued_at":"2026-07-05T09:38:32.500512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:32.500512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.09955","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":"2026-07-05T09:38:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ELRPblcBS24Fl12mIc3eRzjQk7I5ZvlKPYxrlCqFMFBa+dh972l5rwPOX6/n6U5aeyH2MDg9+R8G7PjxT8f+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:01:53.185483Z"},"content_sha256":"952b4a82dd795eb9d5b5d54b935f2fbe35e64b9a022998a8185e0d84b30c8672","schema_version":"1.0","event_id":"sha256:952b4a82dd795eb9d5b5d54b935f2fbe35e64b9a022998a8185e0d84b30c8672"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S3CDZKXNGJKCSIRQWLS565EOXS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instruction-Guided Editing Controls for Images and Multimedia: A Survey in LLM era","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hongzhi Yin, Phi Le Nguyen, Quoc Viet Hung Nguyen, Thanh Tam Nguyen, Thanh Trung Huynh, Trinh Pham, Zhao Ren","submitted_at":"2024-11-15T05:18:15Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) and multimodal learning has transformed digital content creation and manipulation. Traditional visual editing tools require significant expertise, limiting accessibility. Recent strides in instruction-based editing have enabled intuitive interaction with visual content, using natural language as a bridge between user intent and complex editing operations. This survey provides an overview of these techniques, focusing on how LLMs and multimodal models empower users to achieve precise visual modifications without deep technical knowledge. By "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09955","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/2411.09955/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":"2026-07-05T09:38:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xm10wCQnGcSoyEHJckQ9sOrQuVqIyF2cplPAIXlAhWcIlVvEmM0+K/pL81tvPRTGXrNlpvAdX14voV+aAajBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:01:53.186454Z"},"content_sha256":"0535e77709a0f9c474d80bffba0119d660fe719cd6a4f950bdd89c8511f0da10","schema_version":"1.0","event_id":"sha256:0535e77709a0f9c474d80bffba0119d660fe719cd6a4f950bdd89c8511f0da10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S3CDZKXNGJKCSIRQWLS565EOXS/bundle.json","state_url":"https://pith.science/pith/S3CDZKXNGJKCSIRQWLS565EOXS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S3CDZKXNGJKCSIRQWLS565EOXS/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":"2026-08-04T22:01:53Z","links":{"resolver":"https://pith.science/pith/S3CDZKXNGJKCSIRQWLS565EOXS","bundle":"https://pith.science/pith/S3CDZKXNGJKCSIRQWLS565EOXS/bundle.json","state":"https://pith.science/pith/S3CDZKXNGJKCSIRQWLS565EOXS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S3CDZKXNGJKCSIRQWLS565EOXS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S3CDZKXNGJKCSIRQWLS565EOXS","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":"3c4ce46631f79c6df046d39d064411db74d707c547ee7a22a8b2261c96c5678b","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T05:18:15Z","title_canon_sha256":"4c592446ca287ab0e63501d36ada41a326461ac37f8c611c88f86d196d6a10e6"},"schema_version":"1.0","source":{"id":"2411.09955","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09955","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09955v2","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09955","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"pith_short_12","alias_value":"S3CDZKXNGJKC","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"pith_short_16","alias_value":"S3CDZKXNGJKCSIRQ","created_at":"2026-07-05T09:38:32Z"},{"alias_kind":"pith_short_8","alias_value":"S3CDZKXN","created_at":"2026-07-05T09:38:32Z"}],"graph_snapshots":[{"event_id":"sha256:0535e77709a0f9c474d80bffba0119d660fe719cd6a4f950bdd89c8511f0da10","target":"graph","created_at":"2026-07-05T09:38:32Z","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/2411.09955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large language models (LLMs) and multimodal learning has transformed digital content creation and manipulation. Traditional visual editing tools require significant expertise, limiting accessibility. Recent strides in instruction-based editing have enabled intuitive interaction with visual content, using natural language as a bridge between user intent and complex editing operations. This survey provides an overview of these techniques, focusing on how LLMs and multimodal models empower users to achieve precise visual modifications without deep technical knowledge. By ","authors_text":"Hongzhi Yin, Phi Le Nguyen, Quoc Viet Hung Nguyen, Thanh Tam Nguyen, Thanh Trung Huynh, Trinh Pham, Zhao Ren","cross_cats":["cs.AI","cs.HC","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T05:18:15Z","title":"Instruction-Guided Editing Controls for Images and Multimedia: A Survey in LLM era"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09955","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":"sha256:952b4a82dd795eb9d5b5d54b935f2fbe35e64b9a022998a8185e0d84b30c8672","target":"record","created_at":"2026-07-05T09:38:32Z","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":"3c4ce46631f79c6df046d39d064411db74d707c547ee7a22a8b2261c96c5678b","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T05:18:15Z","title_canon_sha256":"4c592446ca287ab0e63501d36ada41a326461ac37f8c611c88f86d196d6a10e6"},"schema_version":"1.0","source":{"id":"2411.09955","kind":"arxiv","version":2}},"canonical_sha256":"96c43caaed3254292230b2e5df748ebc852220e64c9a7e73873d105b533bfb7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96c43caaed3254292230b2e5df748ebc852220e64c9a7e73873d105b533bfb7e","first_computed_at":"2026-07-05T09:38:32.500512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:32.500512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KRLExmCpuSeHkPoJvR/hcxofAbAqfDNLJbIrcTX9YdqwMkWayS5VeEkFB+dfQlUMueCYwNiqSDZ7MnytdPXyDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:32.501019Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09955","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:952b4a82dd795eb9d5b5d54b935f2fbe35e64b9a022998a8185e0d84b30c8672","sha256:0535e77709a0f9c474d80bffba0119d660fe719cd6a4f950bdd89c8511f0da10"],"state_sha256":"148945682df7807b4d754e33698f42ea724c9edd85e63a3bf6c901c87715501b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"02h5IBqO6kvIVrq+39zvxnrhAXoEMDYWAUoVwiTyNhVVXBhB53Ep4aJ4ojzfuAjtylR4trRcvFqPmseRaosaDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:01:53.258915Z","bundle_sha256":"9650f5ae2580766379b90bb0ad11f30509fd4c8b5b0c4784f01a5cb6fb129867"}}