{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GIAVHG4KB2ZBHRH3DZ4QA6LYKF","short_pith_number":"pith:GIAVHG4K","canonical_record":{"source":{"id":"2312.16012","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T11:45:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"11710c0a2e9baa91ae3aa277974efd51cea9f0f6e7ef2e748deb70366c79790d","abstract_canon_sha256":"a265911211a6756f927d2c60f0b0452a98642f039326fa00dd8a4579d924fe5b"},"schema_version":"1.0"},"canonical_sha256":"3201539b8a0eb213c4fb1e79007978514f49b4f04c6dd7b16732b606f1db981c","source":{"kind":"arxiv","id":"2312.16012","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16012","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16012v1","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16012","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"GIAVHG4KB2ZB","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"GIAVHG4KB2ZBHRH3","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"GIAVHG4K","created_at":"2026-07-05T07:28:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GIAVHG4KB2ZBHRH3DZ4QA6LYKF","target":"record","payload":{"canonical_record":{"source":{"id":"2312.16012","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T11:45:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"11710c0a2e9baa91ae3aa277974efd51cea9f0f6e7ef2e748deb70366c79790d","abstract_canon_sha256":"a265911211a6756f927d2c60f0b0452a98642f039326fa00dd8a4579d924fe5b"},"schema_version":"1.0"},"canonical_sha256":"3201539b8a0eb213c4fb1e79007978514f49b4f04c6dd7b16732b606f1db981c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:04.912803Z","signature_b64":"VmMXOnGOfWh80sVpAoMgGk238HBmj0mI0Rn/hB++Hm9RK+ZTeg5gcDM0aFbR653f9qmDsoMEeqbZTVjI0Hm/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3201539b8a0eb213c4fb1e79007978514f49b4f04c6dd7b16732b606f1db981c","last_reissued_at":"2026-07-05T07:28:04.912392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:04.912392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.16012","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":"2026-07-05T07:28:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zwxOFEYB1pEEOiRWNv4V7kFB4Curkcrjb2PutXGA4G+GIVbMM403foZYNXELBvEK5li8+FR9s8vRwFMok3WODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:17:49.599974Z"},"content_sha256":"cb887802f928c919b2fe3175f6d57f176ae2bd977683254e66951ac58de91e57","schema_version":"1.0","event_id":"sha256:cb887802f928c919b2fe3175f6d57f176ae2bd977683254e66951ac58de91e57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GIAVHG4KB2ZBHRH3DZ4QA6LYKF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detection-based Intermediate Supervision for Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dangyang Chen, Daowan Peng, Wei Wei, Wenfeng Xie, Yuanyuan Fu, Yuhang Liu","submitted_at":"2023-12-26T11:45:22Z","abstract_excerpt":"Recently, neural module networks (NMNs) have yielded ongoing success in answering compositional visual questions, especially those involving multi-hop visual and logical reasoning. NMNs decompose the complex question into several sub-tasks using instance-modules from the reasoning paths of that question and then exploit intermediate supervisions to guide answer prediction, thereby improving inference interpretability. However, their performance may be hindered due to sketchy modeling of intermediate supervisions. For instance, (1) a prior assumption that each instance-module refers to only one"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16012","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/2312.16012/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":"2026-07-05T07:28:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9NlCB29x+72Sx0Aj/VMd8BD6Jo5sO7OfbfxWvOK+K5Aya3BoNoNsr+PTI0o/ji30Gr18ezC324FXJQW7AVVnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:17:49.600892Z"},"content_sha256":"94df1651cb021dd4d3e9ad232729c87d9c687878cc171618775355f285f2a7e2","schema_version":"1.0","event_id":"sha256:94df1651cb021dd4d3e9ad232729c87d9c687878cc171618775355f285f2a7e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GIAVHG4KB2ZBHRH3DZ4QA6LYKF/bundle.json","state_url":"https://pith.science/pith/GIAVHG4KB2ZBHRH3DZ4QA6LYKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GIAVHG4KB2ZBHRH3DZ4QA6LYKF/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":"2026-08-11T02:17:49Z","links":{"resolver":"https://pith.science/pith/GIAVHG4KB2ZBHRH3DZ4QA6LYKF","bundle":"https://pith.science/pith/GIAVHG4KB2ZBHRH3DZ4QA6LYKF/bundle.json","state":"https://pith.science/pith/GIAVHG4KB2ZBHRH3DZ4QA6LYKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GIAVHG4KB2ZBHRH3DZ4QA6LYKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GIAVHG4KB2ZBHRH3DZ4QA6LYKF","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":"a265911211a6756f927d2c60f0b0452a98642f039326fa00dd8a4579d924fe5b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T11:45:22Z","title_canon_sha256":"11710c0a2e9baa91ae3aa277974efd51cea9f0f6e7ef2e748deb70366c79790d"},"schema_version":"1.0","source":{"id":"2312.16012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16012","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16012v1","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16012","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"GIAVHG4KB2ZB","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"GIAVHG4KB2ZBHRH3","created_at":"2026-07-05T07:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"GIAVHG4K","created_at":"2026-07-05T07:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:94df1651cb021dd4d3e9ad232729c87d9c687878cc171618775355f285f2a7e2","target":"graph","created_at":"2026-07-05T07:28:04Z","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/2312.16012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, neural module networks (NMNs) have yielded ongoing success in answering compositional visual questions, especially those involving multi-hop visual and logical reasoning. NMNs decompose the complex question into several sub-tasks using instance-modules from the reasoning paths of that question and then exploit intermediate supervisions to guide answer prediction, thereby improving inference interpretability. However, their performance may be hindered due to sketchy modeling of intermediate supervisions. For instance, (1) a prior assumption that each instance-module refers to only one","authors_text":"Dangyang Chen, Daowan Peng, Wei Wei, Wenfeng Xie, Yuanyuan Fu, Yuhang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T11:45:22Z","title":"Detection-based Intermediate Supervision for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16012","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:cb887802f928c919b2fe3175f6d57f176ae2bd977683254e66951ac58de91e57","target":"record","created_at":"2026-07-05T07:28:04Z","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":"a265911211a6756f927d2c60f0b0452a98642f039326fa00dd8a4579d924fe5b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T11:45:22Z","title_canon_sha256":"11710c0a2e9baa91ae3aa277974efd51cea9f0f6e7ef2e748deb70366c79790d"},"schema_version":"1.0","source":{"id":"2312.16012","kind":"arxiv","version":1}},"canonical_sha256":"3201539b8a0eb213c4fb1e79007978514f49b4f04c6dd7b16732b606f1db981c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3201539b8a0eb213c4fb1e79007978514f49b4f04c6dd7b16732b606f1db981c","first_computed_at":"2026-07-05T07:28:04.912392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:04.912392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VmMXOnGOfWh80sVpAoMgGk238HBmj0mI0Rn/hB++Hm9RK+ZTeg5gcDM0aFbR653f9qmDsoMEeqbZTVjI0Hm/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:04.912803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb887802f928c919b2fe3175f6d57f176ae2bd977683254e66951ac58de91e57","sha256:94df1651cb021dd4d3e9ad232729c87d9c687878cc171618775355f285f2a7e2"],"state_sha256":"7d64604e64d60ffe10c333add0a9440e5536c0cf3efe6cce11ed364ab43d8070"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NpxwYmklmrOf9rovCAmchIaJEz5D/xuVj1FI0HZ1luXMpOExyZsJ4hn9YdLbBKDKqNkBKvFZ5O/UHWyMKKXFCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:17:49.613571Z","bundle_sha256":"b7753d3428de6360f0768976c6d102fb68c7eba49bd223c8df21c7c52aa64d89"}}