{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4GJKF4DMLBOONN3PJOEQ7SPYXT","short_pith_number":"pith:4GJKF4DM","canonical_record":{"source":{"id":"2504.04040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-05T03:16:22Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"ac466280b140f48a9479faf9b4bf955460ae6a83069976f321720c238f712f82","abstract_canon_sha256":"1cd34ad34ff1dca094871a83a39ff32ff0e3440d2cd6ed5d85db5b481c6c6413"},"schema_version":"1.0"},"canonical_sha256":"e192a2f06c585ce6b76f4b890fc9f8bccd80716c70f11dcd80401fd65e116c99","source":{"kind":"arxiv","id":"2504.04040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04040","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04040v1","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04040","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"4GJKF4DMLBOO","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_16","alias_value":"4GJKF4DMLBOONN3P","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_8","alias_value":"4GJKF4DM","created_at":"2026-07-05T10:44:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4GJKF4DMLBOONN3PJOEQ7SPYXT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-05T03:16:22Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"ac466280b140f48a9479faf9b4bf955460ae6a83069976f321720c238f712f82","abstract_canon_sha256":"1cd34ad34ff1dca094871a83a39ff32ff0e3440d2cd6ed5d85db5b481c6c6413"},"schema_version":"1.0"},"canonical_sha256":"e192a2f06c585ce6b76f4b890fc9f8bccd80716c70f11dcd80401fd65e116c99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:53.421466Z","signature_b64":"ndRB41Ci9j6DrsXTZMUD5IzLEyBEBrVvFkCv0eKYTDj6C/9nuhSTOg+ZUlwtE2eEBgWZmUfXF588jjAD7UltAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e192a2f06c585ce6b76f4b890fc9f8bccd80716c70f11dcd80401fd65e116c99","last_reissued_at":"2026-07-05T10:44:53.420917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:53.420917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04040","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":"2026-07-05T10:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gidXstOZlRuipQKkYQZ3vB1Z7ktmvqnLpQVjBd8O0HA845klPCxOvOpaKTHMEtctnNgefUpGZAct+bFNUiWoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:50:23.344115Z"},"content_sha256":"280bbfb452042b12385a1ce3708c1c5734e553dd0b3f75a3cee462316452550f","schema_version":"1.0","event_id":"sha256:280bbfb452042b12385a1ce3708c1c5734e553dd0b3f75a3cee462316452550f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4GJKF4DMLBOONN3PJOEQ7SPYXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ADAPT: Actively Discovering and Adapting to Preferences for any Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Akshara Rai, Joanne Truong, Maithili Patel, Roozbeh Mottaghi, Ruta Desai, Sonia Chernova, Xavier Puig","submitted_at":"2025-04-05T03:16:22Z","abstract_excerpt":"Assistive agents should be able to perform under-specified long-horizon tasks while respecting user preferences. We introduce Actively Discovering and Adapting to Preferences for any Task (ADAPT) -- a benchmark designed to evaluate agents' ability to adhere to user preferences across various household tasks through active questioning. Next, we propose Reflection-DPO, a novel training approach for adapting large language models (LLMs) to the task of active questioning. Reflection-DPO finetunes a 'student' LLM to follow the actions of a privileged 'teacher' LLM, and optionally ask a question to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04040","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/2504.04040/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":"2026-07-05T10:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sumq0P1nr0o3DoC6l1tSIc5d4UbC8Dv1b5dE8o0rzutrb13crQWF5P+oiDnObCjcP41fc3AQPY4RE+eWtB64Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:50:23.344511Z"},"content_sha256":"1fdb23a51553281b0f858a9f2e1a2c1487f021b45528307413a356ed9c0758ed","schema_version":"1.0","event_id":"sha256:1fdb23a51553281b0f858a9f2e1a2c1487f021b45528307413a356ed9c0758ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4GJKF4DMLBOONN3PJOEQ7SPYXT/bundle.json","state_url":"https://pith.science/pith/4GJKF4DMLBOONN3PJOEQ7SPYXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4GJKF4DMLBOONN3PJOEQ7SPYXT/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":"2026-07-07T07:50:23Z","links":{"resolver":"https://pith.science/pith/4GJKF4DMLBOONN3PJOEQ7SPYXT","bundle":"https://pith.science/pith/4GJKF4DMLBOONN3PJOEQ7SPYXT/bundle.json","state":"https://pith.science/pith/4GJKF4DMLBOONN3PJOEQ7SPYXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4GJKF4DMLBOONN3PJOEQ7SPYXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4GJKF4DMLBOONN3PJOEQ7SPYXT","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":"1cd34ad34ff1dca094871a83a39ff32ff0e3440d2cd6ed5d85db5b481c6c6413","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-05T03:16:22Z","title_canon_sha256":"ac466280b140f48a9479faf9b4bf955460ae6a83069976f321720c238f712f82"},"schema_version":"1.0","source":{"id":"2504.04040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04040","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04040v1","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04040","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"4GJKF4DMLBOO","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_16","alias_value":"4GJKF4DMLBOONN3P","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_8","alias_value":"4GJKF4DM","created_at":"2026-07-05T10:44:53Z"}],"graph_snapshots":[{"event_id":"sha256:1fdb23a51553281b0f858a9f2e1a2c1487f021b45528307413a356ed9c0758ed","target":"graph","created_at":"2026-07-05T10:44:53Z","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/2504.04040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Assistive agents should be able to perform under-specified long-horizon tasks while respecting user preferences. We introduce Actively Discovering and Adapting to Preferences for any Task (ADAPT) -- a benchmark designed to evaluate agents' ability to adhere to user preferences across various household tasks through active questioning. Next, we propose Reflection-DPO, a novel training approach for adapting large language models (LLMs) to the task of active questioning. Reflection-DPO finetunes a 'student' LLM to follow the actions of a privileged 'teacher' LLM, and optionally ask a question to ","authors_text":"Akshara Rai, Joanne Truong, Maithili Patel, Roozbeh Mottaghi, Ruta Desai, Sonia Chernova, Xavier Puig","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-05T03:16:22Z","title":"ADAPT: Actively Discovering and Adapting to Preferences for any Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04040","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":"sha256:280bbfb452042b12385a1ce3708c1c5734e553dd0b3f75a3cee462316452550f","target":"record","created_at":"2026-07-05T10:44:53Z","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":"1cd34ad34ff1dca094871a83a39ff32ff0e3440d2cd6ed5d85db5b481c6c6413","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-05T03:16:22Z","title_canon_sha256":"ac466280b140f48a9479faf9b4bf955460ae6a83069976f321720c238f712f82"},"schema_version":"1.0","source":{"id":"2504.04040","kind":"arxiv","version":1}},"canonical_sha256":"e192a2f06c585ce6b76f4b890fc9f8bccd80716c70f11dcd80401fd65e116c99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e192a2f06c585ce6b76f4b890fc9f8bccd80716c70f11dcd80401fd65e116c99","first_computed_at":"2026-07-05T10:44:53.420917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:53.420917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ndRB41Ci9j6DrsXTZMUD5IzLEyBEBrVvFkCv0eKYTDj6C/9nuhSTOg+ZUlwtE2eEBgWZmUfXF588jjAD7UltAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:53.421466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:280bbfb452042b12385a1ce3708c1c5734e553dd0b3f75a3cee462316452550f","sha256:1fdb23a51553281b0f858a9f2e1a2c1487f021b45528307413a356ed9c0758ed"],"state_sha256":"15f8dbc3aea827a7f152521b74623c03bdb685d5079ef9341a3156f6fddee2d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJV2ckRa347JC8v5Hs3uGO7eQpJE4yQmaU1IoeRvl3hR85PUENmlZ6jYcSX9EKDX04zrqXo2mmOYn4kg//8CDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:50:23.346532Z","bundle_sha256":"fba7d90151beb30bed95ca7c49e36cabca74002179c39485575831c0d670417e"}}