{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:B2P5SWELOEXCJVQ7NLI6FADHKP","short_pith_number":"pith:B2P5SWEL","canonical_record":{"source":{"id":"2103.12975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T04:05:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"fdab7f21beb0728ceb0f94d739a3788cd3cf24c7fe5f8bb753a1d79e1eb27942","abstract_canon_sha256":"824233ffd404b8721ac2a7120958d55e025286ea592e56ca546bfbe95c45ab3f"},"schema_version":"1.0"},"canonical_sha256":"0e9fd9588b712e24d61f6ad1e2806753d292ff3cdfdcc58d66d5f9e8a5570c67","source":{"kind":"arxiv","id":"2103.12975","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12975","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12975v1","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12975","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"B2P5SWELOEXC","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"B2P5SWELOEXCJVQ7","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"B2P5SWEL","created_at":"2026-07-05T02:26:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:B2P5SWELOEXCJVQ7NLI6FADHKP","target":"record","payload":{"canonical_record":{"source":{"id":"2103.12975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T04:05:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"fdab7f21beb0728ceb0f94d739a3788cd3cf24c7fe5f8bb753a1d79e1eb27942","abstract_canon_sha256":"824233ffd404b8721ac2a7120958d55e025286ea592e56ca546bfbe95c45ab3f"},"schema_version":"1.0"},"canonical_sha256":"0e9fd9588b712e24d61f6ad1e2806753d292ff3cdfdcc58d66d5f9e8a5570c67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:04.296944Z","signature_b64":"jQIyWO4I9sJwaSArMISKnTuqWkY2RjWRgItXiFh4ZD5wgk4mhekMh7CgVXap1+Zds1sOXv3OVAAtLg9Iy89yBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e9fd9588b712e24d61f6ad1e2806753d292ff3cdfdcc58d66d5f9e8a5570c67","last_reissued_at":"2026-07-05T02:26:04.296501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:04.296501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.12975","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":"2026-07-05T02:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GV87OVURfd/DabhpzgZXzxqKS2rNQ5UnYAXcf1C+qWMN5Di3uO8yoolF7GExOoabqmDy/v/JWfEmw2SqrkXuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:35:59.480690Z"},"content_sha256":"19b4916f47e4af903b4129848037251c08e4a86e1e2cea071da98e4457baa8c7","schema_version":"1.0","event_id":"sha256:19b4916f47e4af903b4129848037251c08e4a86e1e2cea071da98e4457baa8c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:B2P5SWELOEXCJVQ7NLI6FADHKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLGrammar: Grounded Grammar Induction of Vision and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Qing Li, Siyuan Huang, Song-Chun Zhu, Yining Hong","submitted_at":"2021-03-24T04:05:08Z","abstract_excerpt":"Cognitive grammar suggests that the acquisition of language grammar is grounded within visual structures. While grammar is an essential representation of natural language, it also exists ubiquitously in vision to represent the hierarchical part-whole structure. In this work, we study grounded grammar induction of vision and language in a joint learning framework. Specifically, we present VLGrammar, a method that uses compound probabilistic context-free grammars (compound PCFGs) to induce the language grammar and the image grammar simultaneously. We propose a novel contrastive learning framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12975","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/2103.12975/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":"2026-07-05T02:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9p+/Y7/fQYILHpkrdWZVFP27AVKIzZzlvdI01lb4n4q9+uGbBEkhQ2hiuX46Sz9GQaH169BDSXLtexCiRYscCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:35:59.481063Z"},"content_sha256":"c7c256cf6930b52b94cebf31c691c9e002d9594b46421b7d0accb08f724ffaa6","schema_version":"1.0","event_id":"sha256:c7c256cf6930b52b94cebf31c691c9e002d9594b46421b7d0accb08f724ffaa6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2P5SWELOEXCJVQ7NLI6FADHKP/bundle.json","state_url":"https://pith.science/pith/B2P5SWELOEXCJVQ7NLI6FADHKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2P5SWELOEXCJVQ7NLI6FADHKP/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":"2026-07-07T09:35:59Z","links":{"resolver":"https://pith.science/pith/B2P5SWELOEXCJVQ7NLI6FADHKP","bundle":"https://pith.science/pith/B2P5SWELOEXCJVQ7NLI6FADHKP/bundle.json","state":"https://pith.science/pith/B2P5SWELOEXCJVQ7NLI6FADHKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2P5SWELOEXCJVQ7NLI6FADHKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B2P5SWELOEXCJVQ7NLI6FADHKP","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":"824233ffd404b8721ac2a7120958d55e025286ea592e56ca546bfbe95c45ab3f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T04:05:08Z","title_canon_sha256":"fdab7f21beb0728ceb0f94d739a3788cd3cf24c7fe5f8bb753a1d79e1eb27942"},"schema_version":"1.0","source":{"id":"2103.12975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12975","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12975v1","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12975","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"B2P5SWELOEXC","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"B2P5SWELOEXCJVQ7","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"B2P5SWEL","created_at":"2026-07-05T02:26:04Z"}],"graph_snapshots":[{"event_id":"sha256:c7c256cf6930b52b94cebf31c691c9e002d9594b46421b7d0accb08f724ffaa6","target":"graph","created_at":"2026-07-05T02:26:04Z","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/2103.12975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cognitive grammar suggests that the acquisition of language grammar is grounded within visual structures. While grammar is an essential representation of natural language, it also exists ubiquitously in vision to represent the hierarchical part-whole structure. In this work, we study grounded grammar induction of vision and language in a joint learning framework. Specifically, we present VLGrammar, a method that uses compound probabilistic context-free grammars (compound PCFGs) to induce the language grammar and the image grammar simultaneously. We propose a novel contrastive learning framewor","authors_text":"Qing Li, Siyuan Huang, Song-Chun Zhu, Yining Hong","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T04:05:08Z","title":"VLGrammar: Grounded Grammar Induction of Vision and Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12975","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":"sha256:19b4916f47e4af903b4129848037251c08e4a86e1e2cea071da98e4457baa8c7","target":"record","created_at":"2026-07-05T02:26:04Z","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":"824233ffd404b8721ac2a7120958d55e025286ea592e56ca546bfbe95c45ab3f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T04:05:08Z","title_canon_sha256":"fdab7f21beb0728ceb0f94d739a3788cd3cf24c7fe5f8bb753a1d79e1eb27942"},"schema_version":"1.0","source":{"id":"2103.12975","kind":"arxiv","version":1}},"canonical_sha256":"0e9fd9588b712e24d61f6ad1e2806753d292ff3cdfdcc58d66d5f9e8a5570c67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e9fd9588b712e24d61f6ad1e2806753d292ff3cdfdcc58d66d5f9e8a5570c67","first_computed_at":"2026-07-05T02:26:04.296501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:04.296501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jQIyWO4I9sJwaSArMISKnTuqWkY2RjWRgItXiFh4ZD5wgk4mhekMh7CgVXap1+Zds1sOXv3OVAAtLg9Iy89yBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:04.296944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19b4916f47e4af903b4129848037251c08e4a86e1e2cea071da98e4457baa8c7","sha256:c7c256cf6930b52b94cebf31c691c9e002d9594b46421b7d0accb08f724ffaa6"],"state_sha256":"77a88332b5bfa75fe22b990320ade5723f6ab7d10377381e3c5a12a90ffcc5a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q7ccmrpElJXb1UUdh5kOIaj7KBW2TbDggmUcX62lwekyoZiWXIJBhNnOkXAd+r6t9kJicrxkLZkrBEQjTdcNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:35:59.483023Z","bundle_sha256":"711e8ddf3afda9342009383f95c675c9a9b760ef8b51c1a448d377c6e49f9e80"}}