{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WOZJSV7G6V6MVZRZEAMY6CPVR4","short_pith_number":"pith:WOZJSV7G","canonical_record":{"source":{"id":"2507.19882","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T09:27:52Z","cross_cats_sorted":[],"title_canon_sha256":"7c542b0f9196062ba83af4a398c4c71c5c53818c173500a917aca08c85b5ac1f","abstract_canon_sha256":"f373a7fd8710e292c8610733dc71db828e8dd0fbf0d2c057a5c49b6437602956"},"schema_version":"1.0"},"canonical_sha256":"b3b29957e6f57ccae63920198f09f58f0e31488474ab765dd11c76a40cf450e4","source":{"kind":"arxiv","id":"2507.19882","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19882","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19882v1","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19882","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"WOZJSV7G6V6M","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_16","alias_value":"WOZJSV7G6V6MVZRZ","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_8","alias_value":"WOZJSV7G","created_at":"2026-07-05T11:43:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WOZJSV7G6V6MVZRZEAMY6CPVR4","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19882","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T09:27:52Z","cross_cats_sorted":[],"title_canon_sha256":"7c542b0f9196062ba83af4a398c4c71c5c53818c173500a917aca08c85b5ac1f","abstract_canon_sha256":"f373a7fd8710e292c8610733dc71db828e8dd0fbf0d2c057a5c49b6437602956"},"schema_version":"1.0"},"canonical_sha256":"b3b29957e6f57ccae63920198f09f58f0e31488474ab765dd11c76a40cf450e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:44.247493Z","signature_b64":"c5kyvmcQHZ1e00bBdYEbiCOBBIDVyVqmjKpy9aTOMbVJdWXh8ysNYb1YZP5JaIBfe+IsyqbWvQu2cWeTNf2sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3b29957e6f57ccae63920198f09f58f0e31488474ab765dd11c76a40cf450e4","last_reissued_at":"2026-07-05T11:43:44.247033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:44.247033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19882","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":"2026-07-05T11:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6jWnbyOVzybdsN7gLxXhr3Lsug7pyjaPtUv4i+YJtmF3jZ+icTbQaerMR/W9G5FuepAhRdM9l5u8IWfQ4SwUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:46:44.003074Z"},"content_sha256":"8bbba02356b88fce52365af1c0b85224a6621c59eaeeca265ca0a00feec2f9f5","schema_version":"1.0","event_id":"sha256:8bbba02356b88fce52365af1c0b85224a6621c59eaeeca265ca0a00feec2f9f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WOZJSV7G6V6MVZRZEAMY6CPVR4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Erdun Gao, Lina Yao, Mingming Gong, Ruoyu Wang, Xinshu Li","submitted_at":"2025-07-26T09:27:52Z","abstract_excerpt":"Prompt learning has garnered attention for its efficiency over traditional model training and fine-tuning. However, existing methods, constrained by inadequate theoretical foundations, encounter difficulties in achieving causally invariant prompts, ultimately falling short of capturing robust features that generalize effectively across categories. To address these challenges, we introduce the $\\textit{\\textbf{DiCap}}$ model, a theoretically grounded $\\textbf{Di}$ffusion-based $\\textbf{C}$ounterf$\\textbf{a}$ctual $\\textbf{p}$rompt learning framework, which leverages a diffusion process to itera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19882","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/2507.19882/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":"2026-07-05T11:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XAy0UCQPi181wrNvR6kotWsE2Wx84v/xq+PP2g9UChMUVpmDqk35w8PPw0reJvyTy5MTud59XTH1K89oD0qoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:46:44.003461Z"},"content_sha256":"827cd95c9fdea54da26d16e8b9381daa36cf2841313175ffb92f11a6d906ea09","schema_version":"1.0","event_id":"sha256:827cd95c9fdea54da26d16e8b9381daa36cf2841313175ffb92f11a6d906ea09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOZJSV7G6V6MVZRZEAMY6CPVR4/bundle.json","state_url":"https://pith.science/pith/WOZJSV7G6V6MVZRZEAMY6CPVR4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOZJSV7G6V6MVZRZEAMY6CPVR4/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":"2026-07-06T10:46:44Z","links":{"resolver":"https://pith.science/pith/WOZJSV7G6V6MVZRZEAMY6CPVR4","bundle":"https://pith.science/pith/WOZJSV7G6V6MVZRZEAMY6CPVR4/bundle.json","state":"https://pith.science/pith/WOZJSV7G6V6MVZRZEAMY6CPVR4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOZJSV7G6V6MVZRZEAMY6CPVR4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WOZJSV7G6V6MVZRZEAMY6CPVR4","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":"f373a7fd8710e292c8610733dc71db828e8dd0fbf0d2c057a5c49b6437602956","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T09:27:52Z","title_canon_sha256":"7c542b0f9196062ba83af4a398c4c71c5c53818c173500a917aca08c85b5ac1f"},"schema_version":"1.0","source":{"id":"2507.19882","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19882","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19882v1","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19882","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"WOZJSV7G6V6M","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_16","alias_value":"WOZJSV7G6V6MVZRZ","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_8","alias_value":"WOZJSV7G","created_at":"2026-07-05T11:43:44Z"}],"graph_snapshots":[{"event_id":"sha256:827cd95c9fdea54da26d16e8b9381daa36cf2841313175ffb92f11a6d906ea09","target":"graph","created_at":"2026-07-05T11:43:44Z","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/2507.19882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt learning has garnered attention for its efficiency over traditional model training and fine-tuning. However, existing methods, constrained by inadequate theoretical foundations, encounter difficulties in achieving causally invariant prompts, ultimately falling short of capturing robust features that generalize effectively across categories. To address these challenges, we introduce the $\\textit{\\textbf{DiCap}}$ model, a theoretically grounded $\\textbf{Di}$ffusion-based $\\textbf{C}$ounterf$\\textbf{a}$ctual $\\textbf{p}$rompt learning framework, which leverages a diffusion process to itera","authors_text":"Erdun Gao, Lina Yao, Mingming Gong, Ruoyu Wang, Xinshu Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T09:27:52Z","title":"Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19882","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":"sha256:8bbba02356b88fce52365af1c0b85224a6621c59eaeeca265ca0a00feec2f9f5","target":"record","created_at":"2026-07-05T11:43:44Z","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":"f373a7fd8710e292c8610733dc71db828e8dd0fbf0d2c057a5c49b6437602956","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-26T09:27:52Z","title_canon_sha256":"7c542b0f9196062ba83af4a398c4c71c5c53818c173500a917aca08c85b5ac1f"},"schema_version":"1.0","source":{"id":"2507.19882","kind":"arxiv","version":1}},"canonical_sha256":"b3b29957e6f57ccae63920198f09f58f0e31488474ab765dd11c76a40cf450e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3b29957e6f57ccae63920198f09f58f0e31488474ab765dd11c76a40cf450e4","first_computed_at":"2026-07-05T11:43:44.247033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:44.247033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c5kyvmcQHZ1e00bBdYEbiCOBBIDVyVqmjKpy9aTOMbVJdWXh8ysNYb1YZP5JaIBfe+IsyqbWvQu2cWeTNf2sCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:44.247493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19882","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bbba02356b88fce52365af1c0b85224a6621c59eaeeca265ca0a00feec2f9f5","sha256:827cd95c9fdea54da26d16e8b9381daa36cf2841313175ffb92f11a6d906ea09"],"state_sha256":"1df249295c3acd511354dd43eecacbe40e3aaab8cf81f6eb25443f872977606e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nSB2dkTmbcDvob9EBhsJjNOTjc5gD1tO4iUv7QFFTtPputMnnPcLpVezRJEL3pe3IOx7w8fKfx1Ouct4ttVVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:46:44.005389Z","bundle_sha256":"4b0ac4d073b467969cd0baad4fe0c0e38f87cbaada815dfefba5911fd99dc999"}}