{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KZHCXSEGRKUWT7LJIKNURNANCM","short_pith_number":"pith:KZHCXSEG","canonical_record":{"source":{"id":"2607.03595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T20:34:42Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b1044f09eaaebc4c9f3127abffdf6448908087f1b94538b4ec0574515138d642","abstract_canon_sha256":"7714e0cbe78fe47d3b8e069b3f3ee86df9c3cd8604ee9772a60ce4853e49e3a6"},"schema_version":"1.0"},"canonical_sha256":"564e2bc8868aa969fd69429b48b40d1331fa2cab1f8b8b834f1b490b5eaeac17","source":{"kind":"arxiv","id":"2607.03595","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03595","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03595v1","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03595","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"pith_short_12","alias_value":"KZHCXSEGRKUW","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"pith_short_16","alias_value":"KZHCXSEGRKUWT7LJ","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"pith_short_8","alias_value":"KZHCXSEG","created_at":"2026-07-07T02:17:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KZHCXSEGRKUWT7LJIKNURNANCM","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T20:34:42Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b1044f09eaaebc4c9f3127abffdf6448908087f1b94538b4ec0574515138d642","abstract_canon_sha256":"7714e0cbe78fe47d3b8e069b3f3ee86df9c3cd8604ee9772a60ce4853e49e3a6"},"schema_version":"1.0"},"canonical_sha256":"564e2bc8868aa969fd69429b48b40d1331fa2cab1f8b8b834f1b490b5eaeac17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:56.576465Z","signature_b64":"5WaGXhS/xO54nrc9ZG70p5dsbq8tac6neWYTRJOa6MYy/c0C19JF56/6eoHySKV9YKrdFZW56LmPqRSAUwInBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"564e2bc8868aa969fd69429b48b40d1331fa2cab1f8b8b834f1b490b5eaeac17","last_reissued_at":"2026-07-07T02:17:56.575682Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:56.575682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03595","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":"2026-07-07T02:17:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PvlhOSx+/bRwzhDxRuiZ3VirrDrxKoUZ20Zt8JW2Xddt/v06UrUtjiepxQgMfxtUw5Apb4VQqnu2jO0C8szaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:40:09.453110Z"},"content_sha256":"fddf9bfd9637f7e4514c78c7f01d5b7538cfc188039365b89bbb466293e1ab0f","schema_version":"1.0","event_id":"sha256:fddf9bfd9637f7e4514c78c7f01d5b7538cfc188039365b89bbb466293e1ab0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KZHCXSEGRKUWT7LJIKNURNANCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Token-Based Affordance Grounding with Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bo Wang, Daguang Xu, Dong Yang, Qinqian Lei, Robby T. Tan, Seung Il Lee, Yixin Chen","submitted_at":"2026-07-03T20:34:42Z","abstract_excerpt":"Affordance grounding aims to localize image regions that support a specific action, serving as a core capability for physical intelligence and embodied perception. Previous studies have primarily relied on weakly supervised learning with action labels from exocentric images. However, these methods often struggle with visually ambiguous exocentric images containing co-occurring actions; moreover, they fail to distinguish semantically similar actions because existing methods typically rely on brief action phrases that lack rich semantic details for action-specific localization. Although large vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03595","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/2607.03595/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":"2026-07-07T02:17:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yvNA6/oP3DpnyKgzX1iC3Tii1hINClZVEftErfkIX1CGTMXPZUCnloSoyw9NjT6aceMdi6wDnDhQDkmrElBLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:40:09.454057Z"},"content_sha256":"99df9c7c86af777f4e791e7dae40f264a89a4686640696752de59a4bb1da9ee9","schema_version":"1.0","event_id":"sha256:99df9c7c86af777f4e791e7dae40f264a89a4686640696752de59a4bb1da9ee9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZHCXSEGRKUWT7LJIKNURNANCM/bundle.json","state_url":"https://pith.science/pith/KZHCXSEGRKUWT7LJIKNURNANCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZHCXSEGRKUWT7LJIKNURNANCM/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":"2026-08-03T19:40:09Z","links":{"resolver":"https://pith.science/pith/KZHCXSEGRKUWT7LJIKNURNANCM","bundle":"https://pith.science/pith/KZHCXSEGRKUWT7LJIKNURNANCM/bundle.json","state":"https://pith.science/pith/KZHCXSEGRKUWT7LJIKNURNANCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZHCXSEGRKUWT7LJIKNURNANCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KZHCXSEGRKUWT7LJIKNURNANCM","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":"7714e0cbe78fe47d3b8e069b3f3ee86df9c3cd8604ee9772a60ce4853e49e3a6","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T20:34:42Z","title_canon_sha256":"b1044f09eaaebc4c9f3127abffdf6448908087f1b94538b4ec0574515138d642"},"schema_version":"1.0","source":{"id":"2607.03595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03595","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03595v1","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03595","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"pith_short_12","alias_value":"KZHCXSEGRKUW","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"pith_short_16","alias_value":"KZHCXSEGRKUWT7LJ","created_at":"2026-07-07T02:17:56Z"},{"alias_kind":"pith_short_8","alias_value":"KZHCXSEG","created_at":"2026-07-07T02:17:56Z"}],"graph_snapshots":[{"event_id":"sha256:99df9c7c86af777f4e791e7dae40f264a89a4686640696752de59a4bb1da9ee9","target":"graph","created_at":"2026-07-07T02:17:56Z","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/2607.03595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Affordance grounding aims to localize image regions that support a specific action, serving as a core capability for physical intelligence and embodied perception. Previous studies have primarily relied on weakly supervised learning with action labels from exocentric images. However, these methods often struggle with visually ambiguous exocentric images containing co-occurring actions; moreover, they fail to distinguish semantically similar actions because existing methods typically rely on brief action phrases that lack rich semantic details for action-specific localization. Although large vi","authors_text":"Bo Wang, Daguang Xu, Dong Yang, Qinqian Lei, Robby T. Tan, Seung Il Lee, Yixin Chen","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T20:34:42Z","title":"Token-Based Affordance Grounding with Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03595","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:fddf9bfd9637f7e4514c78c7f01d5b7538cfc188039365b89bbb466293e1ab0f","target":"record","created_at":"2026-07-07T02:17:56Z","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":"7714e0cbe78fe47d3b8e069b3f3ee86df9c3cd8604ee9772a60ce4853e49e3a6","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T20:34:42Z","title_canon_sha256":"b1044f09eaaebc4c9f3127abffdf6448908087f1b94538b4ec0574515138d642"},"schema_version":"1.0","source":{"id":"2607.03595","kind":"arxiv","version":1}},"canonical_sha256":"564e2bc8868aa969fd69429b48b40d1331fa2cab1f8b8b834f1b490b5eaeac17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"564e2bc8868aa969fd69429b48b40d1331fa2cab1f8b8b834f1b490b5eaeac17","first_computed_at":"2026-07-07T02:17:56.575682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:56.575682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5WaGXhS/xO54nrc9ZG70p5dsbq8tac6neWYTRJOa6MYy/c0C19JF56/6eoHySKV9YKrdFZW56LmPqRSAUwInBg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:56.576465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fddf9bfd9637f7e4514c78c7f01d5b7538cfc188039365b89bbb466293e1ab0f","sha256:99df9c7c86af777f4e791e7dae40f264a89a4686640696752de59a4bb1da9ee9"],"state_sha256":"9fbe96a83f737c1cb4b0e487375f35a9e8d519cc7d05d40eb64e33987ca6e214"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D8s9GPXsA+er1YWzadEdJ7f5BWvUcwH9wHZnFIOzrTwUXfvQdOV/0twvuCpS987jpSTfvxQhGJ2USEhAx1GODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:40:09.459603Z","bundle_sha256":"43a12e6d4a3caeaf600151448a42071c88489421a84d79a65ced6a7c6f92aa3a"}}