{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Q75BPDFGA2NL22DM4BGIIB3A2R","short_pith_number":"pith:Q75BPDFG","canonical_record":{"source":{"id":"2606.23625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T17:19:57Z","cross_cats_sorted":[],"title_canon_sha256":"e120437c05664894ba6b38d5159600fbb629c36135d0db46c9b308f9128091d7","abstract_canon_sha256":"ddb94c66ee4627da495b3f6b7bd8dee48a7b0f76de82e2a8ea8f0bca6f6f2231"},"schema_version":"1.0"},"canonical_sha256":"87fa178ca6069abd686ce04c840760d458486084139f81044bc56e1fa9d7315e","source":{"kind":"arxiv","id":"2606.23625","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23625","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23625v1","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23625","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"Q75BPDFGA2NL","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"Q75BPDFGA2NL22DM","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"Q75BPDFG","created_at":"2026-06-23T03:14:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Q75BPDFGA2NL22DM4BGIIB3A2R","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T17:19:57Z","cross_cats_sorted":[],"title_canon_sha256":"e120437c05664894ba6b38d5159600fbb629c36135d0db46c9b308f9128091d7","abstract_canon_sha256":"ddb94c66ee4627da495b3f6b7bd8dee48a7b0f76de82e2a8ea8f0bca6f6f2231"},"schema_version":"1.0"},"canonical_sha256":"87fa178ca6069abd686ce04c840760d458486084139f81044bc56e1fa9d7315e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:32.680781Z","signature_b64":"UGb4cvJGTHTpZ27l2HS/ux4LqPXsDhSycZoU0VkvPizxRVLoJd3jVq+Mf9sfkuKZ4CDD8vAze2W67d/m45nZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87fa178ca6069abd686ce04c840760d458486084139f81044bc56e1fa9d7315e","last_reissued_at":"2026-06-23T03:14:32.680357Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:32.680357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23625","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":"2026-06-23T03:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T4mju0c1bMpVA+iRTdOSLja2/O3sj87ZiD7+Ya36BKLfwE4DsZDj9PekBnT5SAQHH3pnBkFsRZpC77e7c8cFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T05:00:00.303110Z"},"content_sha256":"1d89db9bc0de03abe84712b5e84ae1f7d00b5eb1170c8e820ba82d8dc67248aa","schema_version":"1.0","event_id":"sha256:1d89db9bc0de03abe84712b5e84ae1f7d00b5eb1170c8e820ba82d8dc67248aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Q75BPDFGA2NL22DM4BGIIB3A2R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Danfei Xu, Kuancheng Wang, Shuo Cheng, Vaibhav Saxena, Yotto Koga","submitted_at":"2026-06-22T17:19:57Z","abstract_excerpt":"Most imitation learning methods assume full observability in table-top settings. In practice, objects are often occluded, requiring robots to both search and act, and learning this coupled behavior from limited demonstrations remains challenging. We propose See2Act, an imitation learning approach that conditions action prediction on a sequence of actively-inferred viewpoints at test time, by coupling action denoising with viewpoint refinement. The policy is trained using camera poses anchored to keyframe actions from offline demonstrations, enabling implicit learning of where to see, while lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23625","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/2606.23625/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":"2026-06-23T03:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysbLIqoY7O3XmsQCVB+pFGAoliYuGRANLbNwgXBUSVwNLUsueSY5Aw1KcPZzQg3cSnyTVIlkG0iIrTwf0055BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T05:00:00.303484Z"},"content_sha256":"f6c47743c698861ff936b8b9ec5239cfc73eb9427f2776b61d7b21d867ea08e0","schema_version":"1.0","event_id":"sha256:f6c47743c698861ff936b8b9ec5239cfc73eb9427f2776b61d7b21d867ea08e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q75BPDFGA2NL22DM4BGIIB3A2R/bundle.json","state_url":"https://pith.science/pith/Q75BPDFGA2NL22DM4BGIIB3A2R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q75BPDFGA2NL22DM4BGIIB3A2R/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":"2026-06-30T05:00:00Z","links":{"resolver":"https://pith.science/pith/Q75BPDFGA2NL22DM4BGIIB3A2R","bundle":"https://pith.science/pith/Q75BPDFGA2NL22DM4BGIIB3A2R/bundle.json","state":"https://pith.science/pith/Q75BPDFGA2NL22DM4BGIIB3A2R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q75BPDFGA2NL22DM4BGIIB3A2R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q75BPDFGA2NL22DM4BGIIB3A2R","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":"ddb94c66ee4627da495b3f6b7bd8dee48a7b0f76de82e2a8ea8f0bca6f6f2231","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T17:19:57Z","title_canon_sha256":"e120437c05664894ba6b38d5159600fbb629c36135d0db46c9b308f9128091d7"},"schema_version":"1.0","source":{"id":"2606.23625","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23625","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23625v1","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23625","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"Q75BPDFGA2NL","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"Q75BPDFGA2NL22DM","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"Q75BPDFG","created_at":"2026-06-23T03:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:f6c47743c698861ff936b8b9ec5239cfc73eb9427f2776b61d7b21d867ea08e0","target":"graph","created_at":"2026-06-23T03:14:32Z","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/2606.23625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most imitation learning methods assume full observability in table-top settings. In practice, objects are often occluded, requiring robots to both search and act, and learning this coupled behavior from limited demonstrations remains challenging. We propose See2Act, an imitation learning approach that conditions action prediction on a sequence of actively-inferred viewpoints at test time, by coupling action denoising with viewpoint refinement. The policy is trained using camera poses anchored to keyframe actions from offline demonstrations, enabling implicit learning of where to see, while lea","authors_text":"Danfei Xu, Kuancheng Wang, Shuo Cheng, Vaibhav Saxena, Yotto Koga","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T17:19:57Z","title":"Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23625","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":"sha256:1d89db9bc0de03abe84712b5e84ae1f7d00b5eb1170c8e820ba82d8dc67248aa","target":"record","created_at":"2026-06-23T03:14:32Z","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":"ddb94c66ee4627da495b3f6b7bd8dee48a7b0f76de82e2a8ea8f0bca6f6f2231","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T17:19:57Z","title_canon_sha256":"e120437c05664894ba6b38d5159600fbb629c36135d0db46c9b308f9128091d7"},"schema_version":"1.0","source":{"id":"2606.23625","kind":"arxiv","version":1}},"canonical_sha256":"87fa178ca6069abd686ce04c840760d458486084139f81044bc56e1fa9d7315e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87fa178ca6069abd686ce04c840760d458486084139f81044bc56e1fa9d7315e","first_computed_at":"2026-06-23T03:14:32.680357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:32.680357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UGb4cvJGTHTpZ27l2HS/ux4LqPXsDhSycZoU0VkvPizxRVLoJd3jVq+Mf9sfkuKZ4CDD8vAze2W67d/m45nZDA==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:32.680781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23625","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d89db9bc0de03abe84712b5e84ae1f7d00b5eb1170c8e820ba82d8dc67248aa","sha256:f6c47743c698861ff936b8b9ec5239cfc73eb9427f2776b61d7b21d867ea08e0"],"state_sha256":"f6c94ed5da9982d94f8bffe867162fa0500dd25c215b2477c29aa5097fe51f7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wMypXFqccvVPA7+If+/mzHUiB6FWkLfynOOkEIAEpFJsRaRKyEHuZqchYghe/cpTdN9wy3lg3nvI+T+Wy8uTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T05:00:00.305768Z","bundle_sha256":"f7b063db4c67bbb5075b10f5bfe4cde24d19e07e1681421f48f02d1a94e36fc5"}}