{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3DYOZFXNUZZSQGQNB2TIPRKJMN","short_pith_number":"pith:3DYOZFXN","canonical_record":{"source":{"id":"2505.22050","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-28T07:21:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a78a3953880166ee067518eeb61db44342ea79de6a75bd400b89202f4d3b9a77","abstract_canon_sha256":"93c72b0ea7601900990838f8581fe7381f829be1d7f7acdb6daeab32ac29515b"},"schema_version":"1.0"},"canonical_sha256":"d8f0ec96eda673281a0d0ea687c549635c0504e4cbe11be5c3bbd0c605937c5b","source":{"kind":"arxiv","id":"2505.22050","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22050","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22050v2","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22050","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"pith_short_12","alias_value":"3DYOZFXNUZZS","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"pith_short_16","alias_value":"3DYOZFXNUZZSQGQN","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"pith_short_8","alias_value":"3DYOZFXN","created_at":"2026-07-05T11:35:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3DYOZFXNUZZSQGQNB2TIPRKJMN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22050","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-28T07:21:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a78a3953880166ee067518eeb61db44342ea79de6a75bd400b89202f4d3b9a77","abstract_canon_sha256":"93c72b0ea7601900990838f8581fe7381f829be1d7f7acdb6daeab32ac29515b"},"schema_version":"1.0"},"canonical_sha256":"d8f0ec96eda673281a0d0ea687c549635c0504e4cbe11be5c3bbd0c605937c5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:56.352965Z","signature_b64":"RyOtHwmkBjWX5PhkurARL5TEl2+vEHJ12eYdExmg6+/yeEHlraJ9cIjj7u8+3MtwW8S+yFgOalPCQrS8cbP2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8f0ec96eda673281a0d0ea687c549635c0504e4cbe11be5c3bbd0c605937c5b","last_reissued_at":"2026-07-05T11:35:56.352443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:56.352443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22050","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":"2026-07-05T11:35:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgMLVhQaqDA/GavVes46F8r2ohsRR+ioqfr850NX0Siq8STwXBJMBJG+kWdnrB+tCTCRGZGv4B14ikIRavewAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:52:50.563731Z"},"content_sha256":"f325e817792af459e7144c941c9810723e8ee416aad400199026766d28dacf66","schema_version":"1.0","event_id":"sha256:f325e817792af459e7144c941c9810723e8ee416aad400199026766d28dacf66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3DYOZFXNUZZSQGQNB2TIPRKJMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforced Reasoning for Embodied Planning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bo Jin, Di Wu, Guanbo Wang, Jiaxin Fan, Junzhe Zang, Wei Yin, Wenhao Li","submitted_at":"2025-05-28T07:21:37Z","abstract_excerpt":"Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle with the temporal reasoning, spatial understanding, and commonsense grounding needed for planning in interactive environments. In this work, we introduce a reinforcement fine-tuning framework that brings R1-style reasoning enhancement into embodied planning. We first distill a high-quality dataset from a powerful closed-source model and perform supervised fine-tuning (S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22050","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/2505.22050/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":"2026-07-05T11:35:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L9uB9YO99yogZVrt/FdMOHpvJS+jGE+zIvLlLHFDuVk3WDMWf/wonRi6iXFp9B1uyjVwPjC6f1xmSbeskiS2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:52:50.564087Z"},"content_sha256":"533c9eff258487e22b4ddec0c664ecb3a35411a86156381c67af7d70691e9b73","schema_version":"1.0","event_id":"sha256:533c9eff258487e22b4ddec0c664ecb3a35411a86156381c67af7d70691e9b73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3DYOZFXNUZZSQGQNB2TIPRKJMN/bundle.json","state_url":"https://pith.science/pith/3DYOZFXNUZZSQGQNB2TIPRKJMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3DYOZFXNUZZSQGQNB2TIPRKJMN/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":"2026-07-07T13:52:50Z","links":{"resolver":"https://pith.science/pith/3DYOZFXNUZZSQGQNB2TIPRKJMN","bundle":"https://pith.science/pith/3DYOZFXNUZZSQGQNB2TIPRKJMN/bundle.json","state":"https://pith.science/pith/3DYOZFXNUZZSQGQNB2TIPRKJMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3DYOZFXNUZZSQGQNB2TIPRKJMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3DYOZFXNUZZSQGQNB2TIPRKJMN","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":"93c72b0ea7601900990838f8581fe7381f829be1d7f7acdb6daeab32ac29515b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-28T07:21:37Z","title_canon_sha256":"a78a3953880166ee067518eeb61db44342ea79de6a75bd400b89202f4d3b9a77"},"schema_version":"1.0","source":{"id":"2505.22050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22050","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22050v2","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22050","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"pith_short_12","alias_value":"3DYOZFXNUZZS","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"pith_short_16","alias_value":"3DYOZFXNUZZSQGQN","created_at":"2026-07-05T11:35:56Z"},{"alias_kind":"pith_short_8","alias_value":"3DYOZFXN","created_at":"2026-07-05T11:35:56Z"}],"graph_snapshots":[{"event_id":"sha256:533c9eff258487e22b4ddec0c664ecb3a35411a86156381c67af7d70691e9b73","target":"graph","created_at":"2026-07-05T11:35:56Z","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/2505.22050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle with the temporal reasoning, spatial understanding, and commonsense grounding needed for planning in interactive environments. In this work, we introduce a reinforcement fine-tuning framework that brings R1-style reasoning enhancement into embodied planning. We first distill a high-quality dataset from a powerful closed-source model and perform supervised fine-tuning (S","authors_text":"Bo Jin, Di Wu, Guanbo Wang, Jiaxin Fan, Junzhe Zang, Wei Yin, Wenhao Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-28T07:21:37Z","title":"Reinforced Reasoning for Embodied Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22050","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:f325e817792af459e7144c941c9810723e8ee416aad400199026766d28dacf66","target":"record","created_at":"2026-07-05T11:35:56Z","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":"93c72b0ea7601900990838f8581fe7381f829be1d7f7acdb6daeab32ac29515b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-28T07:21:37Z","title_canon_sha256":"a78a3953880166ee067518eeb61db44342ea79de6a75bd400b89202f4d3b9a77"},"schema_version":"1.0","source":{"id":"2505.22050","kind":"arxiv","version":2}},"canonical_sha256":"d8f0ec96eda673281a0d0ea687c549635c0504e4cbe11be5c3bbd0c605937c5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8f0ec96eda673281a0d0ea687c549635c0504e4cbe11be5c3bbd0c605937c5b","first_computed_at":"2026-07-05T11:35:56.352443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:56.352443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RyOtHwmkBjWX5PhkurARL5TEl2+vEHJ12eYdExmg6+/yeEHlraJ9cIjj7u8+3MtwW8S+yFgOalPCQrS8cbP2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:56.352965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f325e817792af459e7144c941c9810723e8ee416aad400199026766d28dacf66","sha256:533c9eff258487e22b4ddec0c664ecb3a35411a86156381c67af7d70691e9b73"],"state_sha256":"1b91f6b9ee807086f325c29f2d1a9a8906be7e1b52d6b20d57a446cdcf15a234"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wk0m/4lOoxsdmrSy9wlrInlUxk0HNUwISfJVCzcQX663hbBFmsyQ6wgSaoNlGBCB+xEpK2VaeiYnO9P1BFAxAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:52:50.565993Z","bundle_sha256":"b884d7d6d49f7b5b1ecace8803da22e44c318a440ed50b6cac4cb2c553f5262f"}}