{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6NCLSFAXVZAGDJDRFMJ3GFYRL4","short_pith_number":"pith:6NCLSFAX","canonical_record":{"source":{"id":"2310.01356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:19:04Z","cross_cats_sorted":[],"title_canon_sha256":"75b74bec127c9e06e91364808b4880825d1210e2aefa840d81b00a9bf87a4ab8","abstract_canon_sha256":"f81dbd403c1dcd78c71cc1f505492c686316caef19cc91e9f51d990b2160c699"},"schema_version":"1.0"},"canonical_sha256":"f344b91417ae4061a4712b13b317115f2a03b44b32d193d459b1f466a19ab6a8","source":{"kind":"arxiv","id":"2310.01356","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01356","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01356v1","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01356","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"pith_short_12","alias_value":"6NCLSFAXVZAG","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"pith_short_16","alias_value":"6NCLSFAXVZAGDJDR","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"pith_short_8","alias_value":"6NCLSFAX","created_at":"2026-07-05T06:56:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6NCLSFAXVZAGDJDRFMJ3GFYRL4","target":"record","payload":{"canonical_record":{"source":{"id":"2310.01356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:19:04Z","cross_cats_sorted":[],"title_canon_sha256":"75b74bec127c9e06e91364808b4880825d1210e2aefa840d81b00a9bf87a4ab8","abstract_canon_sha256":"f81dbd403c1dcd78c71cc1f505492c686316caef19cc91e9f51d990b2160c699"},"schema_version":"1.0"},"canonical_sha256":"f344b91417ae4061a4712b13b317115f2a03b44b32d193d459b1f466a19ab6a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:25.724086Z","signature_b64":"z6dO73Yd2jXkXA9svn/xXLP6VEP5WJ/PLupthCAgLngvZCpblqw3FTAmRrF3ZdyVFBfQ0MsAP9loxFqliHcgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f344b91417ae4061a4712b13b317115f2a03b44b32d193d459b1f466a19ab6a8","last_reissued_at":"2026-07-05T06:56:25.723602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:25.723602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.01356","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":"2026-07-05T06:56:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+wv7l/Jij6fhlh/OB71ONHJ2lqZCbKFbSfdrHS6CiVucOYGr60foJZjNKAcYyd2DKbGXAwHMsEpICGReqEmODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:28:09.658733Z"},"content_sha256":"845a92abaead4bdf8d3c1c420f8cd9fe5cec489674493f6035e45184d0328435","schema_version":"1.0","event_id":"sha256:845a92abaead4bdf8d3c1c420f8cd9fe5cec489674493f6035e45184d0328435"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6NCLSFAXVZAGDJDRFMJ3GFYRL4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huijuan Xu, Shu Zhao","submitted_at":"2023-10-02T17:19:04Z","abstract_excerpt":"Humans inherently recognize objects via selective visual perception, transform specific regions from the visual field into structured symbolic knowledge, and reason their relationships among regions based on the allocation of limited attention resources in line with humans' goals. While it is intuitive for humans, contemporary perception systems falter in extracting structural information due to the intricate cognitive abilities and commonsense knowledge required. To fill this gap, we present a new task called Local Scene Graph Generation. Distinct from the conventional scene graph generation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01356","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/2310.01356/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":"2026-07-05T06:56:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NITgfclDJJi5lR01dS8V9yioGIcxYeKIw7tRIOganq4ljxHoFQWb0fMwLttGzKn6eMr/OfFesqecu7IM1QnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:28:09.659215Z"},"content_sha256":"63f6a33ff1754f6d26d9b84c9cd74e61307e8e4c427bd48efd600dc7e53cc800","schema_version":"1.0","event_id":"sha256:63f6a33ff1754f6d26d9b84c9cd74e61307e8e4c427bd48efd600dc7e53cc800"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6NCLSFAXVZAGDJDRFMJ3GFYRL4/bundle.json","state_url":"https://pith.science/pith/6NCLSFAXVZAGDJDRFMJ3GFYRL4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6NCLSFAXVZAGDJDRFMJ3GFYRL4/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":"2026-08-01T02:28:09Z","links":{"resolver":"https://pith.science/pith/6NCLSFAXVZAGDJDRFMJ3GFYRL4","bundle":"https://pith.science/pith/6NCLSFAXVZAGDJDRFMJ3GFYRL4/bundle.json","state":"https://pith.science/pith/6NCLSFAXVZAGDJDRFMJ3GFYRL4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6NCLSFAXVZAGDJDRFMJ3GFYRL4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6NCLSFAXVZAGDJDRFMJ3GFYRL4","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":"f81dbd403c1dcd78c71cc1f505492c686316caef19cc91e9f51d990b2160c699","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:19:04Z","title_canon_sha256":"75b74bec127c9e06e91364808b4880825d1210e2aefa840d81b00a9bf87a4ab8"},"schema_version":"1.0","source":{"id":"2310.01356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01356","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01356v1","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01356","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"pith_short_12","alias_value":"6NCLSFAXVZAG","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"pith_short_16","alias_value":"6NCLSFAXVZAGDJDR","created_at":"2026-07-05T06:56:25Z"},{"alias_kind":"pith_short_8","alias_value":"6NCLSFAX","created_at":"2026-07-05T06:56:25Z"}],"graph_snapshots":[{"event_id":"sha256:63f6a33ff1754f6d26d9b84c9cd74e61307e8e4c427bd48efd600dc7e53cc800","target":"graph","created_at":"2026-07-05T06:56:25Z","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/2310.01356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans inherently recognize objects via selective visual perception, transform specific regions from the visual field into structured symbolic knowledge, and reason their relationships among regions based on the allocation of limited attention resources in line with humans' goals. While it is intuitive for humans, contemporary perception systems falter in extracting structural information due to the intricate cognitive abilities and commonsense knowledge required. To fill this gap, we present a new task called Local Scene Graph Generation. Distinct from the conventional scene graph generation ","authors_text":"Huijuan Xu, Shu Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:19:04Z","title":"Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01356","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":"sha256:845a92abaead4bdf8d3c1c420f8cd9fe5cec489674493f6035e45184d0328435","target":"record","created_at":"2026-07-05T06:56:25Z","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":"f81dbd403c1dcd78c71cc1f505492c686316caef19cc91e9f51d990b2160c699","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:19:04Z","title_canon_sha256":"75b74bec127c9e06e91364808b4880825d1210e2aefa840d81b00a9bf87a4ab8"},"schema_version":"1.0","source":{"id":"2310.01356","kind":"arxiv","version":1}},"canonical_sha256":"f344b91417ae4061a4712b13b317115f2a03b44b32d193d459b1f466a19ab6a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f344b91417ae4061a4712b13b317115f2a03b44b32d193d459b1f466a19ab6a8","first_computed_at":"2026-07-05T06:56:25.723602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:25.723602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z6dO73Yd2jXkXA9svn/xXLP6VEP5WJ/PLupthCAgLngvZCpblqw3FTAmRrF3ZdyVFBfQ0MsAP9loxFqliHcgBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:25.724086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:845a92abaead4bdf8d3c1c420f8cd9fe5cec489674493f6035e45184d0328435","sha256:63f6a33ff1754f6d26d9b84c9cd74e61307e8e4c427bd48efd600dc7e53cc800"],"state_sha256":"d16e6d4e1109a2746b806948863723a651617d2586cda7f6058aa7616f96d3df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"agUgpepa2FGzJVBsxKPk73unytPsrKdNviORU3aW3bRYwHiZzckZ0CIdja1qXRGajFsIg9UZBfCnVdMIbaeWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T02:28:09.665169Z","bundle_sha256":"1419a27b9dc0a24679ebeffff28a024314d6c07dc469dff59a2b6089fbb03ddc"}}