{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6BG6LUW4YTK5H2ELBM6UFP257W","short_pith_number":"pith:6BG6LUW4","schema_version":"1.0","canonical_sha256":"f04de5d2dcc4d5d3e88b0b3d42bf5dfdba84d94eb48c227228b4bc6a3a0ea731","source":{"kind":"arxiv","id":"2607.21125","version":1},"attestation_state":"computed","paper":{"title":"Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hu Gao, Lizhuang Ma, Yulong Chen","submitted_at":"2026-07-23T09:59:44Z","abstract_excerpt":"Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Existing agents typically formulate restoration as a tool-using process, where the agent perceives degradations, searches candidate tools, executes restoration operations, and revises the plan through reflection or rollback. However, their knowledge is often stored as static tool descriptions, manually defined degradation priors, or unstructured textual summaries, which limits the accumulation, verification, revision, and forgetting of restoration k"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.21125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T09:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"fd09095a8ca16a7435c60e5af62f0304ef6ede056934f766f2a5ef1fd3904b80","abstract_canon_sha256":"0ed9a41709b95a687ccd42f3c1c137f996b9a2bcc88c23a979c41988ea1f33c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:54.263426Z","signature_b64":"8WP2XRJOqVJPirn+hkVb0IAgCOnuZ+vCgr8AXtE9+plzkXhwddXV8IJqhpG9BOoAx9Y2L+tbMjkzUi8Rh8AVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f04de5d2dcc4d5d3e88b0b3d42bf5dfdba84d94eb48c227228b4bc6a3a0ea731","last_reissued_at":"2026-07-24T01:23:54.262541Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:54.262541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hu Gao, Lizhuang Ma, Yulong Chen","submitted_at":"2026-07-23T09:59:44Z","abstract_excerpt":"Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Existing agents typically formulate restoration as a tool-using process, where the agent perceives degradations, searches candidate tools, executes restoration operations, and revises the plan through reflection or rollback. However, their knowledge is often stored as static tool descriptions, manually defined degradation priors, or unstructured textual summaries, which limits the accumulation, verification, revision, and forgetting of restoration k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21125","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/2607.21125/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.21125","created_at":"2026-07-24T01:23:54.262994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21125v1","created_at":"2026-07-24T01:23:54.262994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21125","created_at":"2026-07-24T01:23:54.262994+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BG6LUW4YTK5","created_at":"2026-07-24T01:23:54.262994+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BG6LUW4YTK5H2EL","created_at":"2026-07-24T01:23:54.262994+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BG6LUW4","created_at":"2026-07-24T01:23:54.262994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W","json":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W.json","graph_json":"https://pith.science/api/pith-number/6BG6LUW4YTK5H2ELBM6UFP257W/graph.json","events_json":"https://pith.science/api/pith-number/6BG6LUW4YTK5H2ELBM6UFP257W/events.json","paper":"https://pith.science/paper/6BG6LUW4"},"agent_actions":{"view_html":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W","download_json":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W.json","view_paper":"https://pith.science/paper/6BG6LUW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21125&json=true","fetch_graph":"https://pith.science/api/pith-number/6BG6LUW4YTK5H2ELBM6UFP257W/graph.json","fetch_events":"https://pith.science/api/pith-number/6BG6LUW4YTK5H2ELBM6UFP257W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W/action/storage_attestation","attest_author":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W/action/author_attestation","sign_citation":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W/action/citation_signature","submit_replication":"https://pith.science/pith/6BG6LUW4YTK5H2ELBM6UFP257W/action/replication_record"}},"created_at":"2026-07-24T01:23:54.262994+00:00","updated_at":"2026-07-24T01:23:54.262994+00:00"}