{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RGHNV7UQRDI3YDTXOCA5GDXILK","short_pith_number":"pith:RGHNV7UQ","schema_version":"1.0","canonical_sha256":"898edafe9088d1bc0e777081d30ee85a984a8ace294dda1bc830e0f4c367331d","source":{"kind":"arxiv","id":"2511.11132","version":3},"attestation_state":"computed","paper":{"title":"From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baohang Zhou, Dacheng Tao, Li Shen, Xuhui Sui, Ying Zhang, Yu Zhao","submitted_at":"2025-11-14T10:03:23Z","abstract_excerpt":"Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA methods either utilize implicit knowledge in multimodal large language models (MLLMs) via in-context learning or explicit knowledge via retrieval augmented generation. However, their reasoning processes remain implicit, without explicit multi-step trajectories from MLLMs. To address this gap, we provide a Hindsight Distilled Reasoning (HinD) framework with Knowledge Encouragement Preference Optimization, aiming at self-encouraging the knowledge reason"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2511.11132","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-14T10:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"205e2a95d6e125469443685c4f0bb74af9eca4a0028e167f8d5aa4b818670f59","abstract_canon_sha256":"b651ef7fe01a16ff26282ec0482ca9b255bfe68179ea8e2e2f545d23e36c7514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:02.183081Z","signature_b64":"Kykqkc0EhA5TMt3+z+zA0L+JLiD0bRSBQi4bBLYjVMwjblSEKTxItSfkEw8WskbS9gYanw4rI8LOEILtB4QyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"898edafe9088d1bc0e777081d30ee85a984a8ace294dda1bc830e0f4c367331d","last_reissued_at":"2026-07-14T01:22:02.182151Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:02.182151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baohang Zhou, Dacheng Tao, Li Shen, Xuhui Sui, Ying Zhang, Yu Zhao","submitted_at":"2025-11-14T10:03:23Z","abstract_excerpt":"Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA methods either utilize implicit knowledge in multimodal large language models (MLLMs) via in-context learning or explicit knowledge via retrieval augmented generation. However, their reasoning processes remain implicit, without explicit multi-step trajectories from MLLMs. To address this gap, we provide a Hindsight Distilled Reasoning (HinD) framework with Knowledge Encouragement Preference Optimization, aiming at self-encouraging the knowledge reason"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.11132","kind":"arxiv","version":3},"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/2511.11132/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2511.11132","created_at":"2026-07-14T01:22:02.182617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.11132v3","created_at":"2026-07-14T01:22:02.182617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.11132","created_at":"2026-07-14T01:22:02.182617+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGHNV7UQRDI3","created_at":"2026-07-14T01:22:02.182617+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGHNV7UQRDI3YDTX","created_at":"2026-07-14T01:22:02.182617+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGHNV7UQ","created_at":"2026-07-14T01:22:02.182617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK","json":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK.json","graph_json":"https://pith.science/api/pith-number/RGHNV7UQRDI3YDTXOCA5GDXILK/graph.json","events_json":"https://pith.science/api/pith-number/RGHNV7UQRDI3YDTXOCA5GDXILK/events.json","paper":"https://pith.science/paper/RGHNV7UQ"},"agent_actions":{"view_html":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK","download_json":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK.json","view_paper":"https://pith.science/paper/RGHNV7UQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.11132&json=true","fetch_graph":"https://pith.science/api/pith-number/RGHNV7UQRDI3YDTXOCA5GDXILK/graph.json","fetch_events":"https://pith.science/api/pith-number/RGHNV7UQRDI3YDTXOCA5GDXILK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK/action/storage_attestation","attest_author":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK/action/author_attestation","sign_citation":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK/action/citation_signature","submit_replication":"https://pith.science/pith/RGHNV7UQRDI3YDTXOCA5GDXILK/action/replication_record"}},"created_at":"2026-07-14T01:22:02.182617+00:00","updated_at":"2026-07-14T01:22:02.182617+00:00"}