{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D6C2HRXBHOYZP7OIF3LDUZS3GS","short_pith_number":"pith:D6C2HRXB","canonical_record":{"source":{"id":"2507.08496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T11:18:49Z","cross_cats_sorted":[],"title_canon_sha256":"efb2acb500e9bacd827c5ead28777cb0d2ef1d6ded67a805770b937366f0c4e5","abstract_canon_sha256":"f373147baf39a86bc728553fd29687271a551a878da302a5e921e0594bfc94cb"},"schema_version":"1.0"},"canonical_sha256":"1f85a3c6e13bb197fdc82ed63a665b34b46882ce6f84f32eee9520e589673baf","source":{"kind":"arxiv","id":"2507.08496","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08496","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08496v1","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08496","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"pith_short_12","alias_value":"D6C2HRXBHOYZ","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"pith_short_16","alias_value":"D6C2HRXBHOYZP7OI","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"pith_short_8","alias_value":"D6C2HRXB","created_at":"2026-07-05T11:35:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D6C2HRXBHOYZP7OIF3LDUZS3GS","target":"record","payload":{"canonical_record":{"source":{"id":"2507.08496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T11:18:49Z","cross_cats_sorted":[],"title_canon_sha256":"efb2acb500e9bacd827c5ead28777cb0d2ef1d6ded67a805770b937366f0c4e5","abstract_canon_sha256":"f373147baf39a86bc728553fd29687271a551a878da302a5e921e0594bfc94cb"},"schema_version":"1.0"},"canonical_sha256":"1f85a3c6e13bb197fdc82ed63a665b34b46882ce6f84f32eee9520e589673baf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:40.968381Z","signature_b64":"Bb1FWnaPm0r9BPSuMSAakJL+DfgGmdzWPupIxi3JIjDYXJHbzu+C/NJ6JZfoCbwEPfvAPE9QgNVYGpxi65GuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f85a3c6e13bb197fdc82ed63a665b34b46882ce6f84f32eee9520e589673baf","last_reissued_at":"2026-07-05T11:35:40.967844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:40.967844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.08496","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":"2026-07-05T11:35:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FLayOdQKljq3Bpw+5FlOQGNVdiffiRqctdLpkUnaSMqQxZRDH/e3LSU0DK06i7qvwkQ3y/HK5wIesboaI3DyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:00:34.558227Z"},"content_sha256":"0f109155aaf9a8631de34e281c26df6d8a2375e4db3fac2ee2c1c444f4c3bc21","schema_version":"1.0","event_id":"sha256:0f109155aaf9a8631de34e281c26df6d8a2375e4db3fac2ee2c1c444f4c3bc21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D6C2HRXBHOYZP7OIF3LDUZS3GS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dechen Zhan, Donglin Di, Lanshun Nie, Lei Fan, Mingjie Wei, Shibo Sun, Wei-Nan Zhang, Xue Li, Yang Song","submitted_at":"2025-07-11T11:18:49Z","abstract_excerpt":"While large language models (LLMs) have advanced procedural planning for embodied AI systems through strong reasoning abilities, the integration of multimodal inputs and counterfactual reasoning remains underexplored. To tackle these challenges, we introduce LLaPa, a vision-language model framework designed for multimodal procedural planning. LLaPa generates executable action sequences from textual task descriptions and visual environmental images using vision-language models (VLMs). Furthermore, we enhance LLaPa with two auxiliary modules to improve procedural planning. The first module, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08496","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/2507.08496/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":"2026-07-05T11:35:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5k9yjec9nagOek4rMsNfMQvfcxsn50UKFVzHA1DAE73foSpqrbGu9MXM6xT7vX2RgBFEtTEuCT5K84M/7q2LAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:00:34.558788Z"},"content_sha256":"30996c2981408c658322f34ad04969fd47e09cbec0bb46857f31b1f4e6d0e01c","schema_version":"1.0","event_id":"sha256:30996c2981408c658322f34ad04969fd47e09cbec0bb46857f31b1f4e6d0e01c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6C2HRXBHOYZP7OIF3LDUZS3GS/bundle.json","state_url":"https://pith.science/pith/D6C2HRXBHOYZP7OIF3LDUZS3GS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6C2HRXBHOYZP7OIF3LDUZS3GS/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":"2026-08-07T18:00:34Z","links":{"resolver":"https://pith.science/pith/D6C2HRXBHOYZP7OIF3LDUZS3GS","bundle":"https://pith.science/pith/D6C2HRXBHOYZP7OIF3LDUZS3GS/bundle.json","state":"https://pith.science/pith/D6C2HRXBHOYZP7OIF3LDUZS3GS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6C2HRXBHOYZP7OIF3LDUZS3GS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D6C2HRXBHOYZP7OIF3LDUZS3GS","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":"f373147baf39a86bc728553fd29687271a551a878da302a5e921e0594bfc94cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T11:18:49Z","title_canon_sha256":"efb2acb500e9bacd827c5ead28777cb0d2ef1d6ded67a805770b937366f0c4e5"},"schema_version":"1.0","source":{"id":"2507.08496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08496","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08496v1","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08496","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"pith_short_12","alias_value":"D6C2HRXBHOYZ","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"pith_short_16","alias_value":"D6C2HRXBHOYZP7OI","created_at":"2026-07-05T11:35:40Z"},{"alias_kind":"pith_short_8","alias_value":"D6C2HRXB","created_at":"2026-07-05T11:35:40Z"}],"graph_snapshots":[{"event_id":"sha256:30996c2981408c658322f34ad04969fd47e09cbec0bb46857f31b1f4e6d0e01c","target":"graph","created_at":"2026-07-05T11:35:40Z","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/2507.08496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) have advanced procedural planning for embodied AI systems through strong reasoning abilities, the integration of multimodal inputs and counterfactual reasoning remains underexplored. To tackle these challenges, we introduce LLaPa, a vision-language model framework designed for multimodal procedural planning. LLaPa generates executable action sequences from textual task descriptions and visual environmental images using vision-language models (VLMs). Furthermore, we enhance LLaPa with two auxiliary modules to improve procedural planning. The first module, the ","authors_text":"Dechen Zhan, Donglin Di, Lanshun Nie, Lei Fan, Mingjie Wei, Shibo Sun, Wei-Nan Zhang, Xue Li, Yang Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T11:18:49Z","title":"LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08496","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":"sha256:0f109155aaf9a8631de34e281c26df6d8a2375e4db3fac2ee2c1c444f4c3bc21","target":"record","created_at":"2026-07-05T11:35:40Z","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":"f373147baf39a86bc728553fd29687271a551a878da302a5e921e0594bfc94cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T11:18:49Z","title_canon_sha256":"efb2acb500e9bacd827c5ead28777cb0d2ef1d6ded67a805770b937366f0c4e5"},"schema_version":"1.0","source":{"id":"2507.08496","kind":"arxiv","version":1}},"canonical_sha256":"1f85a3c6e13bb197fdc82ed63a665b34b46882ce6f84f32eee9520e589673baf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f85a3c6e13bb197fdc82ed63a665b34b46882ce6f84f32eee9520e589673baf","first_computed_at":"2026-07-05T11:35:40.967844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:40.967844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bb1FWnaPm0r9BPSuMSAakJL+DfgGmdzWPupIxi3JIjDYXJHbzu+C/NJ6JZfoCbwEPfvAPE9QgNVYGpxi65GuAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:40.968381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f109155aaf9a8631de34e281c26df6d8a2375e4db3fac2ee2c1c444f4c3bc21","sha256:30996c2981408c658322f34ad04969fd47e09cbec0bb46857f31b1f4e6d0e01c"],"state_sha256":"901009cc9e41e396347e82b22a10a79b77cc702371197830201fbb64875818de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjioC2mjgleNdOT/T8BZcdyU5jOW55fscrHwYrLhvw6EnKDeoLDwevTabz8n+7spRKCJSaPsshaAP9Apk0fqDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:00:34.563944Z","bundle_sha256":"f5e2c92892ab7e5d6c70dd04f4c480c8f8928be04319692f9606514d626e4ba5"}}