{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZK6IRPDTRHUCG7SYVBB3J4ARGH","short_pith_number":"pith:ZK6IRPDT","canonical_record":{"source":{"id":"2607.06522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T17:27:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cd8bfe6df31f96abf95f2289556b4003250253d0469313e0bf70cd7905ac35a0","abstract_canon_sha256":"650cfb00930758537520b88504581ad18882fd52ce7aa78bf55cb309ed22d751"},"schema_version":"1.0"},"canonical_sha256":"cabc88bc7389e8237e58a843b4f01131dd26d9a75ed1f8f4cd913625d94cf8e3","source":{"kind":"arxiv","id":"2607.06522","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06522","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06522v1","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06522","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZK6IRPDTRHUC","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZK6IRPDTRHUCG7SY","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZK6IRPDT","created_at":"2026-07-08T01:19:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZK6IRPDTRHUCG7SYVBB3J4ARGH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.06522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T17:27:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cd8bfe6df31f96abf95f2289556b4003250253d0469313e0bf70cd7905ac35a0","abstract_canon_sha256":"650cfb00930758537520b88504581ad18882fd52ce7aa78bf55cb309ed22d751"},"schema_version":"1.0"},"canonical_sha256":"cabc88bc7389e8237e58a843b4f01131dd26d9a75ed1f8f4cd913625d94cf8e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:28.829498Z","signature_b64":"MEQm9ZKA1OVPH5Dh+1WHHbKNv6zlrI8y5Elq+U+RKX5pqiCvGKvvdgcUHBhxmNdx6+XApfG4adM4tg39ujTfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cabc88bc7389e8237e58a843b4f01131dd26d9a75ed1f8f4cd913625d94cf8e3","last_reissued_at":"2026-07-08T01:19:28.829056Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:28.829056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.06522","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":"2026-07-08T01:19:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tjlUE0uxSjqqgUHbB76Sz8wQKdKVTOy5SKJ7SFr/kTV/9DX+dS8AFNLuc/Kuq0tUaz2YUeiV2NdVdWHcnvqkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:22:06.681501Z"},"content_sha256":"27e9ce234bfb4c284b48d5fde50df452b7997eb8c57bdea938ee0642888d396a","schema_version":"1.0","event_id":"sha256:27e9ce234bfb4c284b48d5fde50df452b7997eb8c57bdea938ee0642888d396a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZK6IRPDTRHUCG7SYVBB3J4ARGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Han-Jun Ko, Haobo Yuan, Hsin-Ying Lee, Jr-Jen Chen, Ming-Hsuan Yang, Tiancheng Shen, Yu-Chiang Frank Wang","submitted_at":"2026-07-07T17:27:59Z","abstract_excerpt":"Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated chain-of-thought (CoT) reasoning that contradicts physical reality, and misalignment between the model's reasoning and actions. We present VAORA (Visual Action Outcome Reasoning Alignment), a novel reward design that directly addresses both issues. VAORA introduces two complementary rewards: Visual Alignment Reward, which anchors VLM reasoning to the visual context independent of the agent action itself, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06522","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/2607.06522/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":"2026-07-08T01:19:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ZqXSPor0L6XOg7YHoPRihRT97Jf7W9tQgyttJe30vhL/FelqL5p69ZqpdZpUAWYIfnwBk9tFFoT9sk9h/O0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:22:06.682403Z"},"content_sha256":"9a059917d9f42ccec4d7813edf1e7b20abee3712ec784fcfddc64e329ce39a45","schema_version":"1.0","event_id":"sha256:9a059917d9f42ccec4d7813edf1e7b20abee3712ec784fcfddc64e329ce39a45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZK6IRPDTRHUCG7SYVBB3J4ARGH/bundle.json","state_url":"https://pith.science/pith/ZK6IRPDTRHUCG7SYVBB3J4ARGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZK6IRPDTRHUCG7SYVBB3J4ARGH/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":"2026-08-05T17:22:06Z","links":{"resolver":"https://pith.science/pith/ZK6IRPDTRHUCG7SYVBB3J4ARGH","bundle":"https://pith.science/pith/ZK6IRPDTRHUCG7SYVBB3J4ARGH/bundle.json","state":"https://pith.science/pith/ZK6IRPDTRHUCG7SYVBB3J4ARGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZK6IRPDTRHUCG7SYVBB3J4ARGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZK6IRPDTRHUCG7SYVBB3J4ARGH","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":"650cfb00930758537520b88504581ad18882fd52ce7aa78bf55cb309ed22d751","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T17:27:59Z","title_canon_sha256":"cd8bfe6df31f96abf95f2289556b4003250253d0469313e0bf70cd7905ac35a0"},"schema_version":"1.0","source":{"id":"2607.06522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06522","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06522v1","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06522","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZK6IRPDTRHUC","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZK6IRPDTRHUCG7SY","created_at":"2026-07-08T01:19:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZK6IRPDT","created_at":"2026-07-08T01:19:28Z"}],"graph_snapshots":[{"event_id":"sha256:9a059917d9f42ccec4d7813edf1e7b20abee3712ec784fcfddc64e329ce39a45","target":"graph","created_at":"2026-07-08T01:19:28Z","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/2607.06522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated chain-of-thought (CoT) reasoning that contradicts physical reality, and misalignment between the model's reasoning and actions. We present VAORA (Visual Action Outcome Reasoning Alignment), a novel reward design that directly addresses both issues. VAORA introduces two complementary rewards: Visual Alignment Reward, which anchors VLM reasoning to the visual context independent of the agent action itself, and ","authors_text":"Han-Jun Ko, Haobo Yuan, Hsin-Ying Lee, Jr-Jen Chen, Ming-Hsuan Yang, Tiancheng Shen, Yu-Chiang Frank Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T17:27:59Z","title":"Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06522","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":"sha256:27e9ce234bfb4c284b48d5fde50df452b7997eb8c57bdea938ee0642888d396a","target":"record","created_at":"2026-07-08T01:19:28Z","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":"650cfb00930758537520b88504581ad18882fd52ce7aa78bf55cb309ed22d751","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T17:27:59Z","title_canon_sha256":"cd8bfe6df31f96abf95f2289556b4003250253d0469313e0bf70cd7905ac35a0"},"schema_version":"1.0","source":{"id":"2607.06522","kind":"arxiv","version":1}},"canonical_sha256":"cabc88bc7389e8237e58a843b4f01131dd26d9a75ed1f8f4cd913625d94cf8e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cabc88bc7389e8237e58a843b4f01131dd26d9a75ed1f8f4cd913625d94cf8e3","first_computed_at":"2026-07-08T01:19:28.829056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:28.829056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MEQm9ZKA1OVPH5Dh+1WHHbKNv6zlrI8y5Elq+U+RKX5pqiCvGKvvdgcUHBhxmNdx6+XApfG4adM4tg39ujTfAw==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:28.829498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27e9ce234bfb4c284b48d5fde50df452b7997eb8c57bdea938ee0642888d396a","sha256:9a059917d9f42ccec4d7813edf1e7b20abee3712ec784fcfddc64e329ce39a45"],"state_sha256":"8b1fe228eb8f6ee464936a15788d9cbeb13f8850fe66360c3f66344b0cff1ccb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUdA+idtK92/iJh4XBAeMJF+UKkJREvG/RFxkb8GBQrWH6CMGlT6DrxsIEZg/OkbGDKgIQ81tb9c9BshASyeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:22:06.731761Z","bundle_sha256":"c198103585065e8d381fb780f4dcf93cde8abc07eef8124502aff30aaaf11754"}}