{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PTVC2YOBZ6IUM2B34RAMIEYK6N","short_pith_number":"pith:PTVC2YOB","canonical_record":{"source":{"id":"2412.01027","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T01:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"1d4362ee60e86dd58db722389e7baccabadb41464074bf45bde5f868873020b0","abstract_canon_sha256":"068eef23f8fa8a079133c1c61d53d7915db8384d5ad5de869b9bf2d6db2d1ec5"},"schema_version":"1.0"},"canonical_sha256":"7cea2d61c1cf9146683be440c4130af354917632a3a5dc7df53cd810f161c6c0","source":{"kind":"arxiv","id":"2412.01027","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01027","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01027v2","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01027","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"PTVC2YOBZ6IU","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"pith_short_16","alias_value":"PTVC2YOBZ6IUM2B3","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"pith_short_8","alias_value":"PTVC2YOB","created_at":"2026-07-05T09:43:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PTVC2YOBZ6IUM2B34RAMIEYK6N","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01027","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T01:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"1d4362ee60e86dd58db722389e7baccabadb41464074bf45bde5f868873020b0","abstract_canon_sha256":"068eef23f8fa8a079133c1c61d53d7915db8384d5ad5de869b9bf2d6db2d1ec5"},"schema_version":"1.0"},"canonical_sha256":"7cea2d61c1cf9146683be440c4130af354917632a3a5dc7df53cd810f161c6c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:38.448440Z","signature_b64":"3r6LWidvO7mpB+Mvj2abHBBtVTEzExUSRfESy1hSxtO9QkAwRHgNRpRfprGS0qBUmEQhTp4VO+hzo2f9tD2iDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cea2d61c1cf9146683be440c4130af354917632a3a5dc7df53cd810f161c6c0","last_reissued_at":"2026-07-05T09:43:38.447968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:38.447968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01027","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":"2026-07-05T09:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/JemfukO+E/6PmDUUTeWI47fHw41KvShdo7RZN8xBscTZy3Oq/DdtwWRAa50UH3Rh1ENerkTEeIE/8HzHJNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T22:03:25.733216Z"},"content_sha256":"73ba97c7e571ab9ecf1d64109f096564428642ca3f6ee06eeed0e42a9fee00df","schema_version":"1.0","event_id":"sha256:73ba97c7e571ab9ecf1d64109f096564428642ca3f6ee06eeed0e42a9fee00df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PTVC2YOBZ6IUM2B34RAMIEYK6N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolin Lai, Chenguang Zhu, Felix Juefei-Xu, James M. Rehg, Miao Liu, Nikhil Mehta, Ning Zhang, Sangmin Lee, Tong Xiao, Xiaoliang Dai, Zeyi Huang","submitted_at":"2024-12-02T01:19:21Z","abstract_excerpt":"Text-guided image manipulation has experienced notable advancement in recent years. In order to mitigate linguistic ambiguity, few-shot learning with visual examples has been applied for instructions that are underrepresented in the training set, or difficult to describe purely in language. However, learning from visual prompts requires strong reasoning capability, which diffusion models are struggling with. To address this issue, we introduce a novel multi-modal autoregressive model, dubbed $\\textbf{InstaManip}$, that can $\\textbf{insta}$ntly learn a new image $\\textbf{manip}$ulation operatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01027","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/2412.01027/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":"2026-07-05T09:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"waRVvMEuIiEn0fMw0GfzWzDR/AEOkus0OCizYMzHnoTLkmkk+QtXrSH327dzLm4Bfiz8AvILYaFjzzC48AkBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T22:03:25.734148Z"},"content_sha256":"66a924a7498e7f2f42fa077cd2b7eabd00d21bbe50667e5a056e24b8f163b3ec","schema_version":"1.0","event_id":"sha256:66a924a7498e7f2f42fa077cd2b7eabd00d21bbe50667e5a056e24b8f163b3ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTVC2YOBZ6IUM2B34RAMIEYK6N/bundle.json","state_url":"https://pith.science/pith/PTVC2YOBZ6IUM2B34RAMIEYK6N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTVC2YOBZ6IUM2B34RAMIEYK6N/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":"2026-08-11T22:03:25Z","links":{"resolver":"https://pith.science/pith/PTVC2YOBZ6IUM2B34RAMIEYK6N","bundle":"https://pith.science/pith/PTVC2YOBZ6IUM2B34RAMIEYK6N/bundle.json","state":"https://pith.science/pith/PTVC2YOBZ6IUM2B34RAMIEYK6N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTVC2YOBZ6IUM2B34RAMIEYK6N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PTVC2YOBZ6IUM2B34RAMIEYK6N","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":"068eef23f8fa8a079133c1c61d53d7915db8384d5ad5de869b9bf2d6db2d1ec5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T01:19:21Z","title_canon_sha256":"1d4362ee60e86dd58db722389e7baccabadb41464074bf45bde5f868873020b0"},"schema_version":"1.0","source":{"id":"2412.01027","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01027","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01027v2","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01027","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"PTVC2YOBZ6IU","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"pith_short_16","alias_value":"PTVC2YOBZ6IUM2B3","created_at":"2026-07-05T09:43:38Z"},{"alias_kind":"pith_short_8","alias_value":"PTVC2YOB","created_at":"2026-07-05T09:43:38Z"}],"graph_snapshots":[{"event_id":"sha256:66a924a7498e7f2f42fa077cd2b7eabd00d21bbe50667e5a056e24b8f163b3ec","target":"graph","created_at":"2026-07-05T09:43:38Z","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/2412.01027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-guided image manipulation has experienced notable advancement in recent years. In order to mitigate linguistic ambiguity, few-shot learning with visual examples has been applied for instructions that are underrepresented in the training set, or difficult to describe purely in language. However, learning from visual prompts requires strong reasoning capability, which diffusion models are struggling with. To address this issue, we introduce a novel multi-modal autoregressive model, dubbed $\\textbf{InstaManip}$, that can $\\textbf{insta}$ntly learn a new image $\\textbf{manip}$ulation operatio","authors_text":"Bolin Lai, Chenguang Zhu, Felix Juefei-Xu, James M. Rehg, Miao Liu, Nikhil Mehta, Ning Zhang, Sangmin Lee, Tong Xiao, Xiaoliang Dai, Zeyi Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T01:19:21Z","title":"Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01027","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":"sha256:73ba97c7e571ab9ecf1d64109f096564428642ca3f6ee06eeed0e42a9fee00df","target":"record","created_at":"2026-07-05T09:43:38Z","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":"068eef23f8fa8a079133c1c61d53d7915db8384d5ad5de869b9bf2d6db2d1ec5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T01:19:21Z","title_canon_sha256":"1d4362ee60e86dd58db722389e7baccabadb41464074bf45bde5f868873020b0"},"schema_version":"1.0","source":{"id":"2412.01027","kind":"arxiv","version":2}},"canonical_sha256":"7cea2d61c1cf9146683be440c4130af354917632a3a5dc7df53cd810f161c6c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cea2d61c1cf9146683be440c4130af354917632a3a5dc7df53cd810f161c6c0","first_computed_at":"2026-07-05T09:43:38.447968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:38.447968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3r6LWidvO7mpB+Mvj2abHBBtVTEzExUSRfESy1hSxtO9QkAwRHgNRpRfprGS0qBUmEQhTp4VO+hzo2f9tD2iDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:38.448440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01027","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73ba97c7e571ab9ecf1d64109f096564428642ca3f6ee06eeed0e42a9fee00df","sha256:66a924a7498e7f2f42fa077cd2b7eabd00d21bbe50667e5a056e24b8f163b3ec"],"state_sha256":"38b1884d9757cc8506518b6e9b73ceed6b3d58bdc10fa650c44f3088e2d97e3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F2nwCemLhLZpeeewLwymfG6fi13oIB8eBmHxdi5XY8DEt+b7TosElB47nO20owrqrEE7H4a8bi675V4SZekfAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T22:03:25.741720Z","bundle_sha256":"782846c63eb48b0fcbf1124ddaaca4025c0b4ac83c932e4f54fb35518552f9c9"}}